agentleFS
Sign inStart free
chanjalmechanjalme/claude-skills/skills/assumption-check/SKILL.md

assumption-check

Skill0 starsChanged 5 months agoMITView on GitHub

Use before starting any non-trivial or ambiguous task to surface hidden assumptions before doing work that a wrong guess would waste. Triggers when a request is multi-step, under-specified, or affects real files/business/shared state. Lists the assumptions being made and flags the riskiest one as a numbered yes/no question, matching Christian's clarifying-questions preference.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Nova-Caelum/no-mistakes★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Before non-trivial work: builds, multi-file edits, business decisions, anything irreversible or affecting shared state.

    line 13
  2. Distinctive:

    If everything is low-risk and obvious, state the assumptions in one line and proceed without asking (per his "act on clear intent" rule).

    line 21
  3. Distinctive:

    Only ask when a wrong guess would be destructive, irreversible, or affect shared state.

    line 25

≈ “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

Assumption Check

Kills wrong-guess waste. Christian prefers scope-defining questions upfront, asked as numbered yes/no items.

When to run

Before non-trivial work: builds, multi-file edits, business decisions, anything irreversible or affecting shared state. Skip for trivial lookups and clear one-liners.

Procedure

  1. List assumptions I'm about to act on (scope, inputs, target files/paths, format, definition of done). Keep to the 3-6 that actually matter.
  2. Flag the riskiest one or two — the assumptions where being wrong costs the most rework.
  3. Ask as numbered yes/no questions, only the risky ones, e.g.:
    1. You want this in the vault, not ~/Downloads? (y/n)
    2. Output is a .docx, not markdown? (y/n)
  4. If everything is low-risk and obvious, state the assumptions in one line and proceed without asking (per his "act on clear intent" rule).

Rules

  • Resolve "it / this / the file" to the most recent referent. Never ask which one.
  • Only ask when a wrong guess would be destructive, irreversible, or affect shared state. Otherwise assume and proceed.
  • Numbered, yes/no, scoped. No open-ended interrogation.

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