All agent skills

Leading Deeper with AI / 01

Give agents more autonomy

Turn a vague handoff into a task brief or reviewable result, with boundaries, acceptance checks and a stopping point.

A bounded task passes through an agent proposal and checks to a human review decision.TaskAI proposalYour review
AI generation or assessmentHuman input or judgment

Fictional example / AI draft

Proposed FAQ replacement · draft

Replacement answer
Book at example.org/workshop. Registration closes on 12 November 2026 at 17:00 Europe/Berlin. After that time, direct registration questions to Jo, the event owner. Cancel your booking at least 24 hours before the workshop. [B1–B3]
See the full example
Acceptance check
The proposed text includes the approved date, time and timezone [B3], retains the booking link and cancellation rule [B2], and adds no waitlist promise [B1, B3]. This is a comparison of the supplied text, not a test of a live website.
Decision and stopping point
Jo should confirm that the event-owner contact route is useful to readers. A contact address was not supplied. No files were changed and nothing was published.
Give your agent this context

All examples use invented sources and results. They are illustrations, not reports from Jasmine’s workplace or measured outcomes.

[B1] Task and boundaries
Draft 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.
[B2] Current FAQ · registration answer
Book at example.org/workshop. Cancel your booking at least 24 hours before the workshop.
[B3] Approved event note · 2 November 2026
Registration 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.
How this example works
  1. 01 / You

    Give the task a clear finish

    Paste the task, existing answer and approved note. Say that the result should be replacement text in the chat, with no file changes.

  2. 02 / AI

    Produce the change and check its scope

    Compare the existing answer with the approved note, draft the replacement, and show which acceptance requirements it satisfies. Keep undecided policy visible.

  3. 03 / You

    Inspect before accepting

    Read the proposed text against both sources. Jo decides whether it is ready to apply and publish; the draft itself changes nothing.

You check before using the result

  • Does every changed detail match the approved note, with the original booking and cancellation details intact?
  • Is the contact route usable before the owner applies the draft?

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.

What the output should include across models
  • Replacement answer
  • Acceptance check
  • Decision and stopping point
Use this agent skill ↑
Connect your sources (optional)
01

Start here

Bring your context.

What you’ll need

  • Problem and intended user outcome
  • Authorized repository or working folder
  • In-scope files or behaviors
  • Constraints and acceptance checks
  • What must remain a human decision

MCP & tool setup

Local repository, file-editing and test tools are sufficient. A repository MCP is optional when the task includes remote issues or pull requests.

Inspect and edit a bounded working areaPossible toolsFilesEditor

Needed when: Required when asking the agent to implement the change; not required for a discussion-only plan.

MCP or tool examples
Local file/editor tools · An approved repository or filesystem MCP
Tools must support
Read relevant files; Edit only the agreed scope; Inspect the resulting diff
Access needed
Read and write access limited to the authorized working area. No merge, deployment or publication capability is needed.
Without that connection
Provide the relevant files and request a proposed patch for a person to apply.
Run the acceptance checksPossible toolsTerminalTest runner

Needed when: Required to claim that the implementation’s checks were actually run.

MCP or tool examples
Local terminal and project test runner · An approved test-execution tool or custom MCP
Tools must support
Run the specified checks; Read their actual output; Report failures or checks not run
Access needed
Permission to run the project’s agreed checks in the approved environment. A repository MCP alone does not guarantee a test runner.
Without that connection
Provide the commands and acceptance criteria as an unrun test plan; do not report a pass.
Read remote work context or create a review requestPossible toolsGitHubGitLab

Needed when: Only when the task relies on remote issues or explicitly requests a pull request or merge request.

MCP or tool examples
GitHub MCP · GitLab MCP · An approved repository CLI
Tools must support
Read relevant issues, files and review context; Create an unmerged review request only if requested
Access needed
Read access to the named repository. Add review-request creation permission only when that output is explicitly requested; no merge or administration permission.
Without that connection
Paste the approved issue context and return a local diff or patch for the owner to submit.

No live connection? Use an authorized local checkout and terminal. If remote access is unavailable, provide the issue or review context as an approved excerpt and return a reviewable local change.

Use the full prompt instead
02

Copy. Adapt. Try.

Make it your own.

01AIHumanBound the task

AI can help draft the brief. You set the outcome, scope and stopping point.

02AIBuild a proposal

Let the agent work inside that boundary.

03Check the result

Run the checks and inspect what changed.

04HumanKeep the decision

The owner reviews before anything is merged or published.

Replace the bracketed inputs. Use context you’re authorized to share.

Download .txt

Copy the template or select the text directly.

Using an agent? Other formats

Adaptable template based on the talk; not the original internal prompt.

Review checks
03

Keep your judgment in the loop

Review the result.

01

Does this solve the intended problem rather than merely satisfy the wording?

02

Are the checks meaningful, and do the claimed results match their output?

03

What did I learn by inspecting the work? What decision remains mine?

What evidence should you look for?
  • Record whether the acceptance criteria were met and what required rework.
  • Track review effort separately from agent run time; faster generation alone is not a time-saving result.
How this connects to the talk

A pattern practiced in both settings

From practice to work.

Softball IQ

Longer running Softball IQ work used clear briefs and checks, with artifacts or unmerged pull requests to inspect.

At work

Workplace knowledge investigations used agents to gather existing context and produce a starting point the team could check and extend.

Your judgmentYou choose the scope, inspect the evidence and result, and keep responsibility for accepting or publishing the work.

Value to checkRecord whether the result met its acceptance checks, how much review and rework it needed, and the human effort involved.