agentleFS
Sign inStart free
The-AI-ThinkerThe-AI-Thinker/claude-code-pm-starter/.claude/skills/file-feedback/SKILL.md

file-feedback

Skill13 starsChanged 3 months agoMITView on GitHub

Make a correction permanent. Takes something the user just fixed or disliked in a session and routes it to the right file (context, a skill, or the preferences log) so it never has to be said twice. Use whenever the user corrects the same thing again, or says "remember this".

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. celo-org/buy-skill★ 1same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what the correction was (or take it from the conversation if it just happened), then route it with four questions, in order:

    line 12
  2. Very specific:

    Is it taste?: Not wrong, just not how the user likes it.

    line 17
  3. Distinctive:

    Write the Why by asking the user if it isn't obvious.

    line 28
  4. Distinctive:

    Never file the same rule twice.

    line 29

≈ “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

File feedback

A correction made in chat is gone when the session ends. This skill files it so every future session already knows.

The router

Ask what the correction was (or take it from the conversation if it just happened), then route it with four questions, in order:

  1. Is it a one-off slip? A typo, a misread, a fluke. Let it go; tell the user nothing needs filing.
  2. Was the output wrong because a fact was missing or outdated? File the fact. Company, product, or user knowledge goes into the matching context/ file; project knowledge goes into that project's brief.md (usually under Decisions made). Quote the exact line you added.
  3. Was the process wrong? The steps, the format, the quality bar of a recurring piece of work. Edit the matching skill in .claude/skills/ so the fix runs every time. If no skill exists for that work yet and this is at least the second time it repeats, offer to create one from the correction.

  4. Is it taste? Not wrong, just not how the user likes it. Add an entry to the Corrections log in context/preferences.md in this exact shape:

    **[The rule, one line.]**
Why: [what makes this matter to the user]
How to apply: [how a future session should act on it, including edge cases]

Rules

  • One correction per entry. If the user gives three corrections, route each separately.
  • Write the Why by asking the user if it isn't obvious; a rule without a why gets applied blindly and badly.
  • Never file the same rule twice. If an entry already covers it, sharpen that entry instead.
  • End by quoting exactly what was written and where, so the user can adjust the wording on the spot.

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