agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/frontier-ghcp-ttt-rvas/sessions/session-m7-02-interview-and-shape-work/lab/starter/.github/skills/decision-interview/SKILL.md

decision-interview

Skill3 starsChanged 54 days agoMITView on GitHub

Interview a request owner in dependency-ordered rounds before drafting a decision brief or work item.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a request is unclear and the accountable owner must decide product or delivery questions before planning.

    line 8
  2. Distinctive:

    Read only the approved source material.

    line 13
  3. Distinctive:

    Ask questions in dependency-ordered frontiers.

    line 15
  4. Distinctive:

    Ask the request owner to accept, reject, or revise the recommendation.

    line 18
  5. Distinctive:

    Do not draft a brief or work item until the owner confirms shared understanding.

    line 20
  6. Distinctive:

    Stop when each branch has an accepted decision or a named open question with an owner.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Decision interview

Use this skill when a request is unclear and the accountable owner must decide product or delivery questions before planning.

Method

  1. Read only the approved source material.
  2. Separate facts, assumptions, owner decisions, and missing evidence.
  3. Ask questions in dependency-ordered frontiers.
  4. Number every question.
  5. For each question, provide a short recommendation and explain the tradeoff.
  6. Ask the request owner to accept, reject, or revise the recommendation.
  7. Record the decision, reason, owner, and any open branch.
  8. Do not draft a brief or work item until the owner confirms shared understanding.

Required coverage

Cover:

  • target user and problem;
  • outcome and non-goals;
  • success and failure evidence;
  • boundaries, permissions, and unsupported states;
  • dependencies and ownership;
  • approval and readiness.

Stop condition

Stop when each branch has an accepted decision or a named open question with an owner. Do not invent decisions, owners, dates, or evidence.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free