{
  "schemaVersion": 1,
  "version": 1,
  "updated": "2026-11-04",
  "author": "Jasmine James",
  "skillSource": {
    "repository": "https://github.com/jasminelsjames/leading-deeper-ai-skills",
    "commit": "e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7"
  },
  "evaluationStudy": {
    "id": "2026-11-04-starters-v1",
    "skillIds": [
      "daily-debrief",
      "find-low-leverage-workflows"
    ],
    "htmlUrl": "https://jasminejames.dev/leading-deeper/evals",
    "resultsUrl": "https://jasminejames.dev/leading-deeper/skill-evaluations.json",
    "revision": {
      "id": "2026-11-04-starters-v2",
      "sourceCommit": "cfb7338c138386b7fb06cdbf3fd646cf29aea893",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/evals#revision",
      "resultsUrl": "https://jasminejames.dev/leading-deeper/skill-evaluation-revision.json"
    }
  },
  "skills": [
    {
      "id": "find-low-leverage-workflows",
      "type": "agent-skill",
      "title": "Find low-leverage workflows",
      "talkTitle": "Choose Where Attention Belongs",
      "summary": "Break repeated work into steps and choose one small AI experiment. Keep useful learning and ownership visible.",
      "firstUse": {
        "result": "One repeated task to improve, with a small AI experiment to try.",
        "context": [
          "One recurring task and its current steps.",
          "Who does the work and who owns the outcome.",
          "Human judgment or useful practice to protect.",
          "Time spent and a recent example, if available."
        ],
        "checks": [
          "Protect the person’s ownership and learning.",
          "Agree on success checks and a stopping point."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/find-low-leverage-workflows/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/find-low-leverage-workflows/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
      "request": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nRecurring task: [what happens and how often]\nCurrent steps: [how you do it today]\nPeople: [who does it and who owns the outcome]\nKeep human: [judgment, relationships or learning to protect]\nTime and example: [if available]\n\nStart with my recent work. Identify repeated steps I could improve, what judgment or learning to protect and one small experiment to try. Work from the examples I provide or read access I authorize. Propose what to make room for and how to assess whether the experiment helped.",
      "sampleRequest": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: One repeated task to improve, with a small AI experiment to try.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[A1] Fictional weekly status workflow\nMira owns the weekly customer status report. Analyst Sam gathers dated ticket updates, groups them by customer, proposes an interpretation of risks, and reviews the report with Mira. Mira decides priorities and what to tell customers.\n\n[A2] Intended improvement and growth to protect\nSam wants less repeated copying and searching, but is learning to recognize delivery risks. Keep Sam's first interpretation and Mira's coaching discussion. The customer outcome to support is an accurate status report; there is no evidence yet that assistance improves it.\n\n[A3] Baseline and available evidence\nFor three comparable weekly reports, Sam recorded 18, 22 and 20 active minutes gathering updates. Review, correction and maintenance time were not measured. Approved excerpts can include ticket IDs, update dates and status text. No live connector access is needed for a first trial.\n\nReturn:\n- One step to assist\n- Responsibility and growth to protect\n- Quality, effort and review point\n- Stop or revise condition\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Choose+Where+Attention+Belongs&body=**Which+skill+did+you+try%3F**%0A%0AChoose+Where+Attention+Belongs+%28find-low-leverage-workflows%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "choose-ai-assistance",
      "toolingSummary": "Works with supplied examples. Slack or Teams, issue trackers, repositories and document connectors are optional when the chosen context needs them.",
      "executionScope": "Identify opportunities and propose a reviewed experiment; installing or reading the skill does not grant tool access or authorize external changes."
    },
    {
      "id": "daily-debrief",
      "type": "agent-skill",
      "title": "Daily debrief and follow-through",
      "talkTitle": "Daily Debrief",
      "summary": "Turn scattered notes and messages into an action list that checks earlier commitments and links back to evidence.",
      "firstUse": {
        "result": "A sourced action list for Tonight, Tomorrow and Tracking.",
        "context": [
          "Your name, the day and your timezone.",
          "Calendar entries, meeting notes and messages from that day.",
          "Your previous debrief, if you have one."
        ],
        "checks": [
          "Confirm commitments against their sources.",
          "Choose your priorities; the agent sends nothing."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/daily-debrief#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/daily-debrief/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/daily-debrief/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
      "request": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nMe: [name or handle]. Work focus: [leader, individual contributor or mixed]. Ask if my identity, focus, timezone, day or source scope is unclear. Use supplied material or scoped read access I authorize. A previous brief is optional. Compare commitments with observed evidence and return a private Tonight, Tomorrow and Tracking draft. Keep uncertainty visible. Do not send messages, change tasks or create a schedule.",
      "sampleRequest": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nWork focus: Leader. Prioritize requests, decisions, feedback and follow through in the selected email, messages, documents and comment threads.\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A sourced action list for Tonight, Tomorrow and Tracking.\nFor this exercise, refer to me as the reviewer. Morgan and Avery are colleagues; their commitments are not mine. Use the past day and timezone in the supplied context. A role choice changes emphasis only; do not invent PR, CI, email or other evidence absent from this source pack.\n\nSupplied context:\nOne day\n8 April 2030 · Europe/Berlin. Calendar, note, two threads + previous brief; no email or tracker.\n\nEarlier commitments\nMorgan: post checklist before Wednesday. Avery: check dependencies, no due date. [Previous brief + msg-21, 7 April]\n\nToday’s updates\n14:10: checklist posted [msg-44]. Thursday review proposed, unconfirmed [note-12]. No new Avery update. [8 April]\n\nReturn:\n- Red: Tonight, with only supported needs before signing off\n- Yellow: Tomorrow, with proposed next actions\n- Green: Tracking, including open questions and unknown progress, not a completed-work status\n- Source references and coverage limits; no message or task changes without your instruction\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Daily+Debrief&body=**Which+skill+did+you+try%3F**%0A%0ADaily+Debrief+%28daily-debrief%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "daily-debrief",
      "toolingSummary": "Start with approved excerpts. For connected use, choose only the email, chat, documents, comments or delivery records relevant to your focus.",
      "executionScope": "Prepare a private reviewable brief. Reading the skill does not authorize sending follow-ups, changing tasks or creating a recurring schedule."
    },
    {
      "id": "review-feedback",
      "type": "agent-skill",
      "title": "Review feedback and propose improvements",
      "talkTitle": "Review feedback and propose improvements",
      "summary": "Turn recurring feedback into a proposed correction, with evidence and a way to check it.",
      "firstUse": {
        "result": "A proposed fix, with the feedback and evidence behind it.",
        "context": [
          "Feedback or support threads with dates and source labels.",
          "The current answer, content or guidance.",
          "Criteria for judging it and one change to investigate."
        ],
        "checks": [
          "Verify the finding against the source.",
          "Approve, revise or reject the proposed change."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/support-improvement#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/review-feedback/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/review-feedback/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md",
      "request": "Read this GitHub agent skill and use it to review selected feedback and propose an improvement:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md\n\nFeedback: [dated excerpts and source labels]\nCurrent guidance: [the content or answer to check]\nCriteria: [what a good result must satisfy]\nFocus: [one issue to investigate]\n\nUse the feedback, sources and criteria I provide, or scoped read access I authorize. Keep observations separate from AI assessments. Return the finding, a proposed correction and the evidence a person needs to decide. Do not publish the change.",
      "sampleRequest": "Read this GitHub agent skill and use it to review selected feedback and propose an improvement:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A proposed fix, with the feedback and evidence behind it.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[S1] Two selected fictional threads · 26–30 October 2026\nThread A: a Harbor v2 owner asks, 'Which part of Settings contains Export?' Thread B: a Harbor v2 member asks, 'Why do I not see Export?' These are the only threads in the sample; no resolution evidence was supplied.\n\n[S2] Current quick-start guide\nTo download a CSV, export your project data from Settings.\n\n[S3] Approved Harbor v2 product note and review scope\nOnly project owners can create CSV exports: Project settings → Data → Export. Members do not see Export. A workspace administrator can identify an unknown project owner. Reviewer and publication owner: Lee. Compare an owner asking where to click, a member missing the action, and an unknown product version. For an unknown version, ask for the version rather than assuming these steps apply. No replay runner is available.\n\nReturn:\n- Finding and evidence\n- Proposed replacement\n- Comparison plan · not run\n- Recommendation and uncertainty\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Review+feedback+and+propose+improvements&body=**Which+skill+did+you+try%3F**%0A%0AReview+feedback+and+propose+improvements+%28review-feedback%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "support-improvement",
      "toolingSummary": "Use selected feedback, current guidance and criteria. Slack or Teams, document or repository read tools are optional; a replay runner is needed only to claim an executed comparison.",
      "executionScope": "Return a reviewable proposal and actual comparisons or an unrun plan. Publishing, messaging and scheduling require separate authorization."
    },
    {
      "id": "build-reusable-context",
      "type": "agent-skill",
      "title": "Build reusable context",
      "talkTitle": "Build reusable context",
      "summary": "Put answers, sources and open questions in one starting point the next person or agent can reuse.",
      "firstUse": {
        "result": "A referenced guide for the next reader, with an entry point and unanswered questions.",
        "context": [
          "The questions the next reader needs to answer.",
          "Relevant documents, code or conversations with source labels.",
          "The intended reader and any scope limits."
        ],
        "checks": [
          "Check important claims and conflicting sources.",
          "Resolve gaps before publishing shared guidance."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/knowledge-foundation#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/build-reusable-context/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/build-reusable-context/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md",
      "request": "Read this GitHub agent skill and use it to build a reusable knowledge starting point:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md\n\nReader: [who needs this]\nQuestions: [what they need to understand]\nSources: [approved excerpts with dates and references]\nScope: [what to include or leave out]\n\nAsk which questions the next reader needs to answer. Use the material I provide or scoped read access I authorize. Return referenced explanations, an entry point and gaps to review. Keep uncertain claims visible and return a draft.",
      "sampleRequest": "Read this GitHub agent skill and use it to build a reusable knowledge starting point:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A referenced guide for the next reader, with an entry point and unanswered questions.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[K1] Digest README · revision 4\nThe team digest collects items marked ready in the queue and sends one email to the subscribed team. Ask: when is the digest scheduled, and where should I begin if someone reports a missing email? The operations team owns investigations.\n\n[K2] Supplied config and runbook excerpt · current repository snapshot\ndigest.schedule: weekdays at 09:00 UTC. Runbook: for a missing email, inspect the run record for the relevant date and its delivery result. A successful job run alone does not establish that a recipient received the email.\n\n[K3] Onboarding notes · revision 1\nThe digest goes out at 10:00 UTC on weekdays. The deployment schedule and recipient delivery records are not included in this source pack.\n\nReturn:\n- System overview\n- When does it run?\n- Where do I start with a missing email?\n- Gaps and proposed entry point\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Build+reusable+context&body=**Which+skill+did+you+try%3F**%0A%0ABuild+reusable+context+%28build-reusable-context%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "knowledge-foundation",
      "toolingSummary": "Use approved documents, code and conversations or supplied excerpts. Repository, document and Slack or Teams read tools are optional when the context needs them.",
      "executionScope": "Prepare a draft with sources and gaps. Reading this skill does not authorize publishing documentation or changing shared sources."
    },
    {
      "id": "delegate-reviewable-work",
      "type": "agent-skill",
      "title": "Give agents more autonomy",
      "talkTitle": "Give agents more autonomy",
      "summary": "Turn a vague handoff into a task brief or reviewable result, with boundaries, acceptance checks and a stopping point.",
      "firstUse": {
        "result": "A task brief or reviewable result, with clear checks and a stopping point.",
        "context": [
          "The outcome you want and the current material.",
          "What may change and what must stay unchanged.",
          "Acceptance checks and where the agent should stop."
        ],
        "checks": [
          "Confirm the scope and acceptance checks.",
          "Review evidence before accepting any completed work."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/bounded-agent-work#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/delegate-reviewable-work/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/delegate-reviewable-work/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md",
      "request": "Read this GitHub agent skill and use it to prepare or carry out work I can review:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md\n\nGoal: [the outcome]\nCurrent material: [approved context or working area]\nBoundaries: [allowed changes and constraints]\nAcceptance: [how to check the result]\nStop after: [brief, draft or another explicit stopping point]\n\nStart from my goal and establish the scope, constraints, acceptance checks and stopping point. If I request a brief, return the brief. If I request execution, use only the working area and actions I authorize. Return an inspectable result and actual checks.",
      "sampleRequest": "Read this GitHub agent skill and use it to prepare or carry out work I can review:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A task brief or reviewable result, with clear checks and a stopping point.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[B1] Task and boundaries\nDraft a replacement for the registration answer in our fictional workshop FAQ. Add the approved closing time and what happens after it. Preserve the booking link and cancellation rule. Return the text here; do not edit a file or publish. Acceptance: include the timezone, keep the existing cancellation rule, and do not invent a waitlist. Event owner: Jo.\n\n[B2] Current FAQ · registration answer\nBook at example.org/workshop. Cancel your booking at least 24 hours before the workshop.\n\n[B3] Approved event note · 2 November 2026\nRegistration closes on 12 November 2026 at 17:00 Europe/Berlin. After that time, direct registration questions to the event owner. No waitlist process has been agreed.\n\nReturn:\n- Replacement answer\n- Acceptance check\n- Decision and stopping point\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Give+agents+more+autonomy&body=**Which+skill+did+you+try%3F**%0A%0AGive+agents+more+autonomy+%28delegate-reviewable-work%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "bounded-agent-work",
      "toolingSummary": "Supplied context is enough for a brief. Implementation needs an authorized working area and relevant checks; remote repository or document access is optional.",
      "executionScope": "Follow the actual request for planning or execution. A skill is not permission to write, create a remote review, merge, deploy or run without a stopping point."
    },
    {
      "id": "assess-workflow-value",
      "type": "agent-skill",
      "title": "Check whether the automation is helping",
      "talkTitle": "Check whether the automation is helping",
      "summary": "Compare preparation, review, corrections and upkeep before deciding whether to keep an automation.",
      "firstUse": {
        "result": "An effort comparison and a keep, revise or stop recommendation.",
        "context": [
          "The task, time period and comparable completed cases.",
          "Human preparation, review, correction and maintenance time.",
          "Quality checks, setup costs and anything not measured."
        ],
        "checks": [
          "Check comparable cases and arithmetic.",
          "Keep unknowns visible; you decide whether to keep, revise or stop the automation."
        ]
      },
      "updated": "2026-11-04",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/assess-workflow-value#agent-skill",
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/assess-workflow-value/SKILL.md",
      "sourceUrl": "https://jasminejames.dev/leading-deeper/skills/assess-workflow-value/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md",
      "request": "Read this GitHub agent skill and use it to assess whether one workflow is helping:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md\n\nTask and period: [what you compared]\nCases: [comparable completed work, including failures]\nHuman effort: [preparation, review, corrections and upkeep]\nQuality and setup: [measured results and costs]\nUnknowns: [anything not measured]\n\nUse comparable cases and the measurements I provide. Include human preparation, review, correction and maintenance. Keep unknowns and setup costs visible. Separate effort from quality, cost and what the attention enabled. Return a decision draft and one next measurement.",
      "sampleRequest": "Read this GitHub agent skill and use it to assess whether one workflow is helping:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: An effort comparison and a keep, revise or stop recommendation.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\nComparable work | Fictional week\nFive completed drafts per approach, with the same acceptance requirements assumed. No failed or unfinished cases in this illustration. Effort is active person-minutes, not agent runtime or elapsed time.\n\nEffort records | Invented measurements\nManual work: 25 minutes per draft including preparation and checks, with zero separate baseline maintenance explicitly assumed. Assisted work: 7 minutes per draft including preparation, review and corrections, plus 10 minutes of maintenance for the week.\n\nUnknowns and request\nSetup effort, monetary cost and use of attention are unknown. Equal quality is assumed for the example, not independently verified. Return a decision draft and one next measurement; make no workflow or staffing changes.\n\nReturn:\n- Comparable cases, units and a traceable calculation\n- Assumptions, missing evidence and setup treatment\n- Quality, monetary cost and use of attention kept distinct from effort\n- A reviewed keep, revise or stop proposal and one next measurement\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Check+whether+the+automation+is+helping&body=**Which+skill+did+you+try%3F**%0A%0ACheck+whether+the+automation+is+helping+%28assess-workflow-value%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "companionWorkflowId": "assess-workflow-value",
      "toolingSummary": "Works with supplied measurements. Reporting, issue, timing-log or file read tools are optional; no live connector is required.",
      "executionScope": "Assess the evidence and propose the next measurement. This skill does not change workflows, assign people or create tracking."
    }
  ],
  "gettingStarted": {
    "walkthroughUrl": "https://jasminejames.dev/leading-deeper/daily-debrief#start-here",
    "chooseWorkflowUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance#start-here",
    "examplesUrl": "https://jasminejames.dev/leading-deeper/workflow-starters.json",
    "featuredSkills": [
      {
        "id": "daily-debrief",
        "title": "Daily Debrief",
        "htmlUrl": "https://jasminejames.dev/leading-deeper/daily-debrief#agent-skill",
        "skillUrl": "https://jasminejames.dev/leading-deeper/skills/daily-debrief/SKILL.md",
        "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
        "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
        "request": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nMe: [name or handle]. Work focus: [leader, individual contributor or mixed]. Ask if my identity, focus, timezone, day or source scope is unclear. Use supplied material or scoped read access I authorize. A previous brief is optional. Compare commitments with observed evidence and return a private Tonight, Tomorrow and Tracking draft. Keep uncertainty visible. Do not send messages, change tasks or create a schedule.",
        "sampleRequest": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nWork focus: Leader. Prioritize requests, decisions, feedback and follow through in the selected email, messages, documents and comment threads.\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A sourced action list for Tonight, Tomorrow and Tracking.\nFor this exercise, refer to me as the reviewer. Morgan and Avery are colleagues; their commitments are not mine. Use the past day and timezone in the supplied context. A role choice changes emphasis only; do not invent PR, CI, email or other evidence absent from this source pack.\n\nSupplied context:\nOne day\n8 April 2030 · Europe/Berlin. Calendar, note, two threads + previous brief; no email or tracker.\n\nEarlier commitments\nMorgan: post checklist before Wednesday. Avery: check dependencies, no due date. [Previous brief + msg-21, 7 April]\n\nToday’s updates\n14:10: checklist posted [msg-44]. Thursday review proposed, unconfirmed [note-12]. No new Avery update. [8 April]\n\nReturn:\n- Red: Tonight, with only supported needs before signing off\n- Yellow: Tomorrow, with proposed next actions\n- Green: Tracking, including open questions and unknown progress, not a completed-work status\n- Source references and coverage limits; no message or task changes without your instruction\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
        "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Daily+Debrief&body=**Which+skill+did+you+try%3F**%0A%0ADaily+Debrief+%28daily-debrief%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others."
      },
      {
        "id": "find-low-leverage-workflows",
        "title": "Choose Where Attention Belongs",
        "htmlUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance#agent-skill",
        "skillUrl": "https://jasminejames.dev/leading-deeper/skills/find-low-leverage-workflows/SKILL.md",
        "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
        "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
        "request": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nRecurring task: [what happens and how often]\nCurrent steps: [how you do it today]\nPeople: [who does it and who owns the outcome]\nKeep human: [judgment, relationships or learning to protect]\nTime and example: [if available]\n\nStart with my recent work. Identify repeated steps I could improve, what judgment or learning to protect and one small experiment to try. Work from the examples I provide or read access I authorize. Propose what to make room for and how to assess whether the experiment helped.",
        "sampleRequest": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: One repeated task to improve, with a small AI experiment to try.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[A1] Fictional weekly status workflow\nMira owns the weekly customer status report. Analyst Sam gathers dated ticket updates, groups them by customer, proposes an interpretation of risks, and reviews the report with Mira. Mira decides priorities and what to tell customers.\n\n[A2] Intended improvement and growth to protect\nSam wants less repeated copying and searching, but is learning to recognize delivery risks. Keep Sam's first interpretation and Mira's coaching discussion. The customer outcome to support is an accurate status report; there is no evidence yet that assistance improves it.\n\n[A3] Baseline and available evidence\nFor three comparable weekly reports, Sam recorded 18, 22 and 20 active minutes gathering updates. Review, correction and maintenance time were not measured. Approved excerpts can include ticket IDs, update dates and status text. No live connector access is needed for a first trial.\n\nReturn:\n- One step to assist\n- Responsibility and growth to protect\n- Quality, effort and review point\n- Stop or revise condition\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
        "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Choose+Where+Attention+Belongs&body=**Which+skill+did+you+try%3F**%0A%0AChoose+Where+Attention+Belongs+%28find-low-leverage-workflows%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others."
      }
    ],
    "modelAgnosticNote": "Use the AI tool approved for your work with supplied material. Wording and layout will vary by model; look for the evidence, uncertainty and review decisions shown here. Connections and recurring runs depend on your setup."
  },
  "guides": [
    {
      "id": "framework-artifacts",
      "title": "What each quadrant leaves behind",
      "summary": "Turn repeated work into reusable AI workflows. Make decisions, ownership and growth visible.",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance/#framework-artifacts",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/framework-artifacts.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/framework-artifacts.json"
    }
  ],
  "provenance": "Adaptable templates based on Leading Deeper with AI, not the original internal prompts.",
  "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
  "modelGuidanceReviewedOn": "2026-10-30",
  "resources": [
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/delegate-reviewable-work/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to prepare or carry out work I can review:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md\n\nGoal: [the outcome]\nCurrent material: [approved context or working area]\nBoundaries: [allowed changes and constraints]\nAcceptance: [how to check the result]\nStop after: [brief, draft or another explicit stopping point]\n\nStart from my goal and establish the scope, constraints, acceptance checks and stopping point. If I request a brief, return the brief. If I request execution, use only the working area and actions I authorize. Return an inspectable result and actual checks.",
      "sampleRequest": "Read this GitHub agent skill and use it to prepare or carry out work I can review:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A task brief or reviewable result, with clear checks and a stopping point.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[B1] Task and boundaries\nDraft a replacement for the registration answer in our fictional workshop FAQ. Add the approved closing time and what happens after it. Preserve the booking link and cancellation rule. Return the text here; do not edit a file or publish. Acceptance: include the timezone, keep the existing cancellation rule, and do not invent a waitlist. Event owner: Jo.\n\n[B2] Current FAQ · registration answer\nBook at example.org/workshop. Cancel your booking at least 24 hours before the workshop.\n\n[B3] Approved event note · 2 November 2026\nRegistration closes on 12 November 2026 at 17:00 Europe/Berlin. After that time, direct registration questions to the event owner. No waitlist process has been agreed.\n\nReturn:\n- Replacement answer\n- Acceptance check\n- Decision and stopping point\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Give+agents+more+autonomy&body=**Which+skill+did+you+try%3F**%0A%0AGive+agents+more+autonomy+%28delegate-reviewable-work%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "bounded-agent-work",
      "title": "Give agents more autonomy",
      "summary": "Hand over a defined task and get a result you can inspect, with clear checks and a stopping point.",
      "value": {
        "id": "bounded-agent-work",
        "cardSummary": "Turn a vague handoff into a task brief or reviewable result, with boundaries, acceptance checks and a stopping point.",
        "outcome": "Turn a vague handoff into a task brief or reviewable result, with boundaries, acceptance checks and a stopping point.",
        "bridge": {
          "practice": "Longer running Softball IQ work used clear briefs and checks, with artifacts or unmerged pull requests to inspect.",
          "work": "Workplace knowledge investigations used agents to gather existing context and produce a starting point the team could check and extend.",
          "relationship": "shared-pattern"
        },
        "humanDecision": "You choose the scope, inspect the evidence and result, and keep responsibility for accepting or publishing the work.",
        "valueToCheck": "Record whether the result met its acceptance checks, how much review and rework it needed, and the human effort involved."
      },
      "toolingSummary": "Local repository, file-editing and test tools are sufficient. A repository MCP is optional when the task includes remote issues or pull requests.",
      "modelStartingPoint": "gpt-6.1-sol",
      "modelGuidanceReviewedOn": "2026-10-30",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/bounded-agent-work",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/bounded-agent-work.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/bounded-agent-work.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/bounded-agent-work.txt",
      "requiresHumanReview": true
    },
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/build-reusable-context/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to build a reusable knowledge starting point:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md\n\nReader: [who needs this]\nQuestions: [what they need to understand]\nSources: [approved excerpts with dates and references]\nScope: [what to include or leave out]\n\nAsk which questions the next reader needs to answer. Use the material I provide or scoped read access I authorize. Return referenced explanations, an entry point and gaps to review. Keep uncertain claims visible and return a draft.",
      "sampleRequest": "Read this GitHub agent skill and use it to build a reusable knowledge starting point:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A referenced guide for the next reader, with an entry point and unanswered questions.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[K1] Digest README · revision 4\nThe team digest collects items marked ready in the queue and sends one email to the subscribed team. Ask: when is the digest scheduled, and where should I begin if someone reports a missing email? The operations team owns investigations.\n\n[K2] Supplied config and runbook excerpt · current repository snapshot\ndigest.schedule: weekdays at 09:00 UTC. Runbook: for a missing email, inspect the run record for the relevant date and its delivery result. A successful job run alone does not establish that a recipient received the email.\n\n[K3] Onboarding notes · revision 1\nThe digest goes out at 10:00 UTC on weekdays. The deployment schedule and recipient delivery records are not included in this source pack.\n\nReturn:\n- System overview\n- When does it run?\n- Where do I start with a missing email?\n- Gaps and proposed entry point\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Build+reusable+context&body=**Which+skill+did+you+try%3F**%0A%0ABuild+reusable+context+%28build-reusable-context%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "knowledge-foundation",
      "title": "Build a starting point from existing context",
      "summary": "Help the next person answer questions without reconstructing the same history. Get a starting point with sources and visible gaps.",
      "value": {
        "id": "knowledge-foundation",
        "cardSummary": "Put answers, sources and open questions in one starting point the next person or agent can reuse.",
        "outcome": "Put answers, sources and open questions in one starting point the next person or agent can reuse.",
        "bridge": {
          "practice": "Curated questions and project instructions made Softball IQ context reusable, including corrections that should inform the next attempt.",
          "work": "The team used existing code, documentation and conversations to build shared knowledge for colleagues, support and agents.",
          "relationship": "shared-pattern"
        },
        "humanDecision": "A knowledgeable person verifies claims, resolves conflicts and decides what belongs in the shared source.",
        "valueToCheck": "Test whether people can answer real questions from the material, then track corrections, remaining gaps and repeated requests for context."
      },
      "toolingSummary": "The agent needs the source material, not a particular MCP. Add conversation access only if live team discussions are part of the agreed scope.",
      "modelStartingPoint": "claude-haiku-5-5",
      "modelGuidanceReviewedOn": "2026-10-30",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/knowledge-foundation",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/knowledge-foundation.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/knowledge-foundation.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/knowledge-foundation.txt",
      "requiresHumanReview": true
    },
    {
      "id": "grounded-support",
      "title": "Draft a support answer from shared knowledge",
      "summary": "Make relevant context easier to find while preserving uncertainty, source references and a route to human help.",
      "value": {
        "id": "grounded-support",
        "cardSummary": "Prepare an answer people can check against the shared source.",
        "outcome": "A draft answer with relevant sources, visible uncertainty and a route to human help.",
        "bridge": {
          "practice": "Softball IQ uses curated content and instructions to give AI context it can work from.",
          "work": "An existing assistant answered from shared knowledge; Perch reviewed answers to improve the guidance.",
          "relationship": "shared-pattern"
        },
        "humanDecision": "The answer owner checks applicability and decides whether to respond, investigate or escalate.",
        "valueToCheck": "Assess source correctness, confirmed resolution and human review effort separately."
      },
      "toolingSummary": "A grounded answer requires approved knowledge sources. Access to a live support thread is optional when the question and its context are supplied directly.",
      "modelStartingPoint": "gpt-6-luna",
      "modelGuidanceReviewedOn": "2026-10-30",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/grounded-support",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/grounded-support.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/grounded-support.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/grounded-support.txt",
      "requiresHumanReview": true
    },
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/review-feedback/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to review selected feedback and propose an improvement:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md\n\nFeedback: [dated excerpts and source labels]\nCurrent guidance: [the content or answer to check]\nCriteria: [what a good result must satisfy]\nFocus: [one issue to investigate]\n\nUse the feedback, sources and criteria I provide, or scoped read access I authorize. Keep observations separate from AI assessments. Return the finding, a proposed correction and the evidence a person needs to decide. Do not publish the change.",
      "sampleRequest": "Read this GitHub agent skill and use it to review selected feedback and propose an improvement:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A proposed fix, with the feedback and evidence behind it.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[S1] Two selected fictional threads · 26–30 October 2026\nThread A: a Harbor v2 owner asks, 'Which part of Settings contains Export?' Thread B: a Harbor v2 member asks, 'Why do I not see Export?' These are the only threads in the sample; no resolution evidence was supplied.\n\n[S2] Current quick-start guide\nTo download a CSV, export your project data from Settings.\n\n[S3] Approved Harbor v2 product note and review scope\nOnly project owners can create CSV exports: Project settings → Data → Export. Members do not see Export. A workspace administrator can identify an unknown project owner. Reviewer and publication owner: Lee. Compare an owner asking where to click, a member missing the action, and an unknown product version. For an unknown version, ask for the version rather than assuming these steps apply. No replay runner is available.\n\nReturn:\n- Finding and evidence\n- Proposed replacement\n- Comparison plan · not run\n- Recommendation and uncertainty\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Review+feedback+and+propose+improvements&body=**Which+skill+did+you+try%3F**%0A%0AReview+feedback+and+propose+improvements+%28review-feedback%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "support-improvement",
      "title": "Turn support questions into proposed knowledge improvements",
      "summary": "Reduce repeated confusion by turning feedback into proposed fixes to content or guidance. You review what changes.",
      "value": {
        "id": "support-improvement",
        "cardSummary": "Turn recurring feedback into a proposed correction, with evidence and a way to check it.",
        "outcome": "Turn recurring feedback into a proposed correction, with evidence and a way to check it.",
        "bridge": {
          "practice": "Player answers informed recurring content reviews in Softball IQ, where AI assessed questions against criteria and proposed corrections.",
          "work": "Perch assessed support threads against a fixed rubric and proposed knowledge updates for a person to review before publication.",
          "relationship": "shared-pattern"
        },
        "humanDecision": "You verify the finding and proposed correction, then decide whether to approve, revise or reject the change.",
        "valueToCheck": "Check whether the targeted gap recurs, record review corrections, and measure assistance, confirmed resolution and human effort separately."
      },
      "toolingSummary": "Use read access to the scoped support threads and current knowledge. A separate runner is needed to execute replay comparisons; otherwise return a test plan labeled not run.",
      "modelStartingPoint": "claude-sonnet-5-5",
      "modelGuidanceReviewedOn": "2026-10-30",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/support-improvement",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/support-improvement.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/support-improvement.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/support-improvement.txt",
      "requiresHumanReview": true
    },
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/find-low-leverage-workflows/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nRecurring task: [what happens and how often]\nCurrent steps: [how you do it today]\nPeople: [who does it and who owns the outcome]\nKeep human: [judgment, relationships or learning to protect]\nTime and example: [if available]\n\nStart with my recent work. Identify repeated steps I could improve, what judgment or learning to protect and one small experiment to try. Work from the examples I provide or read access I authorize. Propose what to make room for and how to assess whether the experiment helped.",
      "sampleRequest": "Read this GitHub agent skill and use it to help me apply the AI Leverage Framework:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: One repeated task to improve, with a small AI experiment to try.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\n[A1] Fictional weekly status workflow\nMira owns the weekly customer status report. Analyst Sam gathers dated ticket updates, groups them by customer, proposes an interpretation of risks, and reviews the report with Mira. Mira decides priorities and what to tell customers.\n\n[A2] Intended improvement and growth to protect\nSam wants less repeated copying and searching, but is learning to recognize delivery risks. Keep Sam's first interpretation and Mira's coaching discussion. The customer outcome to support is an accurate status report; there is no evidence yet that assistance improves it.\n\n[A3] Baseline and available evidence\nFor three comparable weekly reports, Sam recorded 18, 22 and 20 active minutes gathering updates. Review, correction and maintenance time were not measured. Approved excerpts can include ticket IDs, update dates and status text. No live connector access is needed for a first trial.\n\nReturn:\n- One step to assist\n- Responsibility and growth to protect\n- Quality, effort and review point\n- Stop or revise condition\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Choose+Where+Attention+Belongs&body=**Which+skill+did+you+try%3F**%0A%0AChoose+Where+Attention+Belongs+%28find-low-leverage-workflows%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "choose-ai-assistance",
      "title": "Choose a step to improve—and a responsibility to protect",
      "summary": "Choose one recurring burden to improve with AI while protecting judgment and useful practice.",
      "value": {
        "id": "choose-ai-assistance",
        "cardSummary": "Break repeated work into steps and choose one small AI experiment. Keep useful learning and ownership visible.",
        "outcome": "Break repeated work into steps and choose one small AI experiment. Keep useful learning and ownership visible.",
        "bridge": {
          "practice": "Softball IQ gave me a place to try capabilities and build the judgment to use them.",
          "work": "The framework emerged as I reflected on repeated preparation, leadership attention and the work my team should own.",
          "relationship": "shared-pattern"
        },
        "humanDecision": "You choose which steps to improve in the context of each person, their responsibility and their growth.",
        "valueToCheck": "Check the intended result and the human effort required, alongside the judgment, ownership and useful learning you protect."
      },
      "toolingSummary": "No MCP is needed when you provide the workflow and baseline. Optional read-only data access can help establish a baseline before an experiment.",
      "modelStartingPoint": "gpt-6-luna",
      "modelGuidanceReviewedOn": "2026-10-30",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/choose-ai-assistance.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/choose-ai-assistance.txt",
      "requiresHumanReview": true
    },
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/daily-debrief/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nMe: [name or handle]. Work focus: [leader, individual contributor or mixed]. Ask if my identity, focus, timezone, day or source scope is unclear. Use supplied material or scoped read access I authorize. A previous brief is optional. Compare commitments with observed evidence and return a private Tonight, Tomorrow and Tracking draft. Keep uncertainty visible. Do not send messages, change tasks or create a schedule.",
      "sampleRequest": "Read this GitHub agent skill and use it to prepare my daily debrief:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md\n\nWork focus: Leader. Prioritize requests, decisions, feedback and follow through in the selected email, messages, documents and comment threads.\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: A sourced action list for Tonight, Tomorrow and Tracking.\nFor this exercise, refer to me as the reviewer. Morgan and Avery are colleagues; their commitments are not mine. Use the past day and timezone in the supplied context. A role choice changes emphasis only; do not invent PR, CI, email or other evidence absent from this source pack.\n\nSupplied context:\nOne day\n8 April 2030 · Europe/Berlin. Calendar, note, two threads + previous brief; no email or tracker.\n\nEarlier commitments\nMorgan: post checklist before Wednesday. Avery: check dependencies, no due date. [Previous brief + msg-21, 7 April]\n\nToday’s updates\n14:10: checklist posted [msg-44]. Thursday review proposed, unconfirmed [note-12]. No new Avery update. [8 April]\n\nReturn:\n- Red: Tonight, with only supported needs before signing off\n- Yellow: Tomorrow, with proposed next actions\n- Green: Tracking, including open questions and unknown progress, not a completed-work status\n- Source references and coverage limits; no message or task changes without your instruction\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Daily+Debrief&body=**Which+skill+did+you+try%3F**%0A%0ADaily+Debrief+%28daily-debrief%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "daily-debrief",
      "title": "Prepare a daily debrief and carry commitments forward",
      "summary": "See what needs your attention without piecing your day together again. Get a private brief with sources and commitments to check.",
      "value": {
        "id": "daily-debrief",
        "cardSummary": "Turn scattered notes and messages into an action list that checks earlier commitments and links back to evidence.",
        "outcome": "Turn scattered notes and messages into an action list that checks earlier commitments and links back to evidence.",
        "bridge": {
          "practice": "I built customer service and marketing debriefs for Softball IQ.",
          "work": "I brought that approach into my day job to prepare a source linked daily debrief and check earlier commitments.",
          "relationship": "direct-transfer"
        },
        "humanDecision": "You decide what matters, what needs a response and which commitments should change after checking the supporting evidence.",
        "valueToCheck": "Compare preparation and review time with your previous routine, and track missing commitments, incorrect summaries and useful follow through."
      },
      "toolingSummary": "Start with approved excerpts. Connected use needs only the read tools for your selected focus: messages, email, documents/comments, calendar or delivery records.",
      "modelStartingPoint": "gpt-6-luna",
      "modelGuidanceReviewedOn": "2026-11-02",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/daily-debrief",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/daily-debrief.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/daily-debrief.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/daily-debrief.txt",
      "requiresHumanReview": true
    },
    {
      "skillUrl": "https://jasminejames.dev/leading-deeper/skills/assess-workflow-value/SKILL.md",
      "repositorySourceUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/blob/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md",
      "repositoryRawUrl": "https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md",
      "skillRequest": "Read this GitHub agent skill and use it to assess whether one workflow is helping:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md\n\nTask and period: [what you compared]\nCases: [comparable completed work, including failures]\nHuman effort: [preparation, review, corrections and upkeep]\nQuality and setup: [measured results and costs]\nUnknowns: [anything not measured]\n\nUse comparable cases and the measurements I provide. Include human preparation, review, correction and maintenance. Keep unknowns and setup costs visible. Separate effort from quality, cost and what the attention enabled. Return a decision draft and one next measurement.",
      "sampleRequest": "Read this GitHub agent skill and use it to assess whether one workflow is helping:\nhttps://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md\n\nTry this fictional example. All people, records and measurements below are invented. Use only the supplied context; no connectors, account access or additional records are available.\n\nGoal: An effort comparison and a keep, revise or stop recommendation.\nYou prepare the draft; I review it. Keep any named decision owner in the supplied material responsible for their decision.\n\nSupplied context:\nComparable work | Fictional week\nFive completed drafts per approach, with the same acceptance requirements assumed. No failed or unfinished cases in this illustration. Effort is active person-minutes, not agent runtime or elapsed time.\n\nEffort records | Invented measurements\nManual work: 25 minutes per draft including preparation and checks, with zero separate baseline maintenance explicitly assumed. Assisted work: 7 minutes per draft including preparation, review and corrections, plus 10 minutes of maintenance for the week.\n\nUnknowns and request\nSetup effort, monetary cost and use of attention are unknown. Equal quality is assumed for the example, not independently verified. Return a decision draft and one next measurement; make no workflow or staffing changes.\n\nReturn:\n- Comparable cases, units and a traceable calculation\n- Assumptions, missing evidence and setup treatment\n- Quality, monetary cost and use of attention kept distinct from effort\n- A reviewed keep, revise or stop proposal and one next measurement\n\nStop after returning the private draft in this chat. Keep source labels, assumptions and unknowns visible. Do not send messages, change files or tasks, publish, connect tools or create a schedule. If you cannot read the linked skill, say so rather than claiming to have used it.",
      "feedbackUrl": "https://github.com/jasminelsjames/leading-deeper-ai-skills/issues/new?template=skill-feedback.md&title=Feedback%3A+Check+whether+the+automation+is+helping&body=**Which+skill+did+you+try%3F**%0A%0ACheck+whether+the+automation+is+helping+%28assess-workflow-value%29%0A%0A**What+did+you+use+it+for%2C+and+what+result+did+you+get%3F**%0A%0A**What+did+you+have+to+correct%2C+and+what+would+make+the+next+run+better%3F**%0A%0A**Agent+and+model%2C+if+known%3A**%0A%0AOptional%3A+a+short+fictional+or+sanitized+example.+Do+not+include+private+workplace+content%2C+credentials+or+personal+information+about+others.",
      "id": "assess-workflow-value",
      "title": "Check whether the workflow is helping",
      "summary": "Check whether the workflow reduces human effort after review, correction and maintenance, then decide whether to keep, revise or stop it.",
      "value": {
        "id": "assess-workflow-value",
        "cardSummary": "Compare preparation, review, corrections and upkeep before deciding whether to keep an automation.",
        "outcome": "Compare preparation, review, corrections and upkeep before deciding whether to keep an automation.",
        "bridge": {
          "practice": "Use a repeatable Softball IQ task, such as a debrief or content review, as a proposed measurement exercise.",
          "work": "Apply the same comparison to a workplace workflow, including preparation, review, correction and the outcome people need.",
          "relationship": "new-companion"
        },
        "humanDecision": "You decide whether the evidence supports keeping, changing or stopping the automation, and where any released capacity should go.",
        "valueToCheck": "Compare similar tasks and periods, count all human effort, record quality tradeoffs and label estimates separately from observed results."
      },
      "toolingSummary": "No MCP is needed with supplied measurements and workflow context. Optional scoped read access can help establish case counts, dates and effort evidence.",
      "modelStartingPoint": "gpt-6-luna",
      "modelGuidanceReviewedOn": "2026-11-02",
      "modelGuidanceCatalogUrl": "https://jasminejames.dev/leading-deeper/model-guidance.json",
      "htmlUrl": "https://jasminejames.dev/leading-deeper/assess-workflow-value",
      "markdownUrl": "https://jasminejames.dev/leading-deeper/assess-workflow-value.md",
      "jsonUrl": "https://jasminejames.dev/leading-deeper/assess-workflow-value.json",
      "textUrl": "https://jasminejames.dev/leading-deeper/prompts/assess-workflow-value.txt",
      "requiresHumanReview": true
    }
  ]
}
