agentleFS
JsnnmscJsnnmsc/10000x-engineer/skills/decision/SKILL.md

decision

Skill2 starsChanged 2 months agoMITView on GitHub

Surface the actual decision points in a task, plan, or problem — the specific choices that need to be made, the options for each, and a default recommendation.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief, plan and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    brief

    Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 6

    Distinctive

    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:

    Only list decisions that are actually open — skip anything already implied or settled by context.

    line 20
  2. Distinctive:

    If there's only one real decision, give that one and say so.

    line 25
  3. Distinctive:

    Don't list a decision that context already settles.

    line 56
  4. Distinctive:

    Don't write "default: depends on your latency budget".

    line 59
  5. Distinctive:

    Don't pad to three points.

    line 62
  6. Distinctive:

    If no request was supplied, ask: "Decision points for what?"

    line 65

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “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 Point

Goal: engineer sees exactly which choices are still open, what the options are, and which one to default to — without re-deriving the whole problem.

Rules

  • Respond in the same language the user wrote in. If they write in Chinese, reply in Chinese. Technical terms (JWT, Redis, API…) stay in English.
  • Max 10 lines. Hard limit. That's 3 decision points at most.
  • Only list decisions that are actually open — skip anything already implied or settled by context.
  • Each decision point is a bold numbered question, with its options and default on the line below.
  • Each one needs 2-3 concrete options (not "it depends") and a default with a short reason.
  • Order by impact: the decision that most constrains everything else is #1.
  • Bottom line = which one to settle first, or which one can be deferred. Not a recap of the defaults.
  • If there's only one real decision, give that one and say so.
  • No emoji.

Output format

**1. [The choice, as a question]**
[option A] vs [option B] (vs [option C]) → default: [X], [short reason]

**2. [The choice, as a question]**
[option A] vs [option B] → default: [X], [short reason]

**Bottom line:** [which to settle first, or which can wait]

Example

/decision 幫 payment API 加上 retry

**1. Where does the retry logic live?**
client vs middleware vs queue consumer → default: middleware, the one place all callers pass through

**2. How many retries, and spaced how?**
fixed count vs exponential backoff → default: exponential backoff capped at 3, failures are likely transient

**Bottom line:** decide #1 first — it determines whether #2 is even yours to make

Anti-examples

Don't list a decision that context already settles. If the repo has one HTTP client and no appetite for a second, "which HTTP client" is not an open decision.

Don't write "default: depends on your latency budget". That's the question again. Pick one and name the assumption you picked it under.

Don't pad to three points. One real decision stated cleanly beats three where two are theater.

If no request was supplied, ask: "Decision points for what?"

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.