agentleFS
robertbradley-ossrobertbradley-oss/skills/decision-coach/SKILL.md

decision-coach

Skill2 starsChanged 2 months agoMITView on GitHub

Help a user work through a consequential choice by clarifying priorities, comparing alternatives, and identifying evidence that would change the decision. Use for requested decision coaching or interactive pressure-testing, not routine implementation choices.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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 context already supplied.

    line 14
  2. Distinctive:

    After an answer, briefly explain what it changes and follow the most important unresolved branch.

    line 20
  3. Distinctive:

    When priorities conflict, show the tradeoff explicitly.

    line 24
  4. Distinctive:

    If no option is clearly preferable, explain the actual deciding factor rather than continuing questions indefinitely.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 coach

Help the user reach a reasoned choice they can act on. Preserve their values and authority over the decision. Be willing to recommend an option when the evidence and preferences support it.

Frame the choice

Identify the actual choice, available options, constraints, timing, and consequences. Distinguish hard constraints from preferences and reversible experiments from costly commitments. Include keeping the current arrangement or delaying only when it is a realistic option, with its costs considered.

Use context already supplied. If the user asks for an immediate recommendation, give the best supported recommendation with its assumptions; do not force an interview first.

Coach without supplying the user's answers

For an interactive request, ask one consequential question at a time unless the user prefers another format. Elicit the user's priorities or reasoning before offering your preferred answer when their answer would affect the recommendation. Avoid leading questions and contrived opposition.

After an answer, briefly explain what it changes and follow the most important unresolved branch. Distinguish facts, predictions, preferences, and assumptions. Verify discoverable facts instead of asking the user to guess them.

Compare options on the criteria that actually matter to this user. Account for practical constraints, opportunity cost, downside, reversibility, and the cost of waiting where relevant. Do not invent options merely to make a comparison table longer.

When priorities conflict, show the tradeoff explicitly. Use weighted scoring only when meaningful inputs and weights are available; do not disguise subjective judgments with arbitrary numerical precision. If weights are uncertain, show which priority changes would reverse the ranking.

Reduce the important uncertainty

Identify what evidence would change the recommendation. Prefer a small, informative check or reversible trial when its cost is justified by the uncertainty. Distinguish an uncertainty that can be resolved from a preference the user must choose.

For material factual claims, use the appropriate available evidence and current authoritative sources when necessary. Do not treat coaching as a substitute for required domain expertise in high-stakes decisions.

Conclude when useful

Stop when the choice is supported enough to act, the user asks to stop, or progress depends on unavailable information. Summarize the preferred option or conditional recommendation, why it fits, the main tradeoff, what could change it, and the next practical step. State unresolved uncertainty plainly.

If no option is clearly preferable, explain the actual deciding factor rather than continuing questions indefinitely. Provide a concise decision brief in chat; save a document only when requested or already in scope. Coaching does not authorize executing the decision.

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.