agentleFS
Sign inStart free
AnthonyPoschenAnthonyPoschen/agent-skills/skills/in-your-own-words/SKILL.md

in-your-own-words

Skill2 starsChanged 20 days agoMITView on GitHub

Use before starting ambiguous or multi-step work, when the user says "in your own words" or "restate my goal", or when intent is unclear. Restate the goal, the problem being solved, the constraints, and what done looks like in plain words; flag assumptions and open questions; wait for a correction if anything looks off.

29 other projects use a version of this, 14 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ketchup-video, maintain-formal-verification-skill and 10 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.
  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • TheOnlyFusionCubeSkill

    maintain-formal-verification-skill

    Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.

    Also in 19 projects that use this

  • TheOnlyFusionCubeSkill

    create-formal-verification-skill

    Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.

    Also in 20 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 10 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 20 projects that use this

  • jaydubya818Skill

    principle-test-behavior-not-implementation

    Apply when tests mirror internals instead of asserting observable outcomes.

    Also in 21 projects that use this

  • +1 more from TheOnlyFusionCube

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    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:

    Before non-trivial work, play back the request in your own plain words so a misread goal is caught before the run starts.

    line 13
  2. Distinctive:

    Read only enough of the message, linked files, and conversation to understand the ask.

    line 30
  3. Distinctive:

    Keep exact names and values (paths, IDs, amounts, dates, error strings).

    line 47
  4. Distinctive:

    If anything looks off, stop and wait for a correction.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 7 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

In Your Own Words

Before non-trivial work, play back the request in your own plain words so a misread goal is caught before the run starts. A short play-back costs one reply; a wrong goal can waste the whole session.

When To Play Back

Do this when:

  • The task is ambiguous, multi-step, or spans more than one decision.
  • The user asks for /in-your-own-words, says "in your own words", or "restate my goal".
  • You are about to spend meaningful effort and the done check is not obvious.

Skip it for a clear, one-step request with an obvious done check.

Play Back

Read only enough of the message, linked files, and conversation to understand the ask. Do not investigate causes, design a fix, or start the work yet.

Restate in your own words:

  1. Goal — what success looks like, and for whom.
  2. Problem — what is wrong or missing today.
  3. Constraints — limits, must-nots, deadlines, and authority boundaries.
  4. Done — the concrete check that would pass or fail.

Then briefly flag:

  • Assumptions — guesses you filled in; mark each as a guess.
  • Open questions — at most one question, only when the answer changes the work. Say what each answer would change. Never ask the user to restate their request.

Keep exact names and values (paths, IDs, amounts, dates, error strings). Do not parrot the user's sentences. Do not propose a plan or fix. Stay under about 120 words. Leave out any section that has nothing useful in it.

If anything looks off, stop and wait for a correction. If the play-back is clear and the user only confirms, proceed as described. Do not play it back again unless they ask.

Source

Inspired by poteto's /in-your-own-words prompt and pstack skill; first-party wording owned here.

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