agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/mistake-review/SKILL.md

mistake-review

Skill0 starsChanged 5 days agoMITView on GitHub

Turn logged mistakes in 50_Review/Mistakes.md into corrected flashcards with a source link, after the learner attempts the correction. Use when the learner asks to review or convert mistakes. Writes only to Mistakes.md, so only run when asked.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read 50_Review/Mistakes.md.

    line 9
  2. Very specific:

    Check the learner's correction against the concept note and its cited source in 40_References.

    line 11
  3. Very specific:

    Never repeat a question already in the vault: run check_cards.py and fix a duplicate by merging.

    line 13
  4. Distinctive:

    Do not edit concept notes.

    line 15
  5. Very specific:

    Run run-checks after writing.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Tutor mode: the learner attempts the correction first; the agent never writes the learner's study layer (concept notes, takeaways, their own cards) or their answers.

  1. Read 50_Review/Mistakes.md. List open entries that have no corrected card yet. Each entry records the kind of error (knowledge, reasoning, execution, careless) and AI use (scaffold, substitute or none); if either is missing, ask the learner and add the learner's answer.
  2. For each entry, show only the question and the learner's wrong answer. Ask the learner to write the correct answer and why they went wrong, with confidence from 1 to 5. Use the hint ladder only after that attempt: hint, strong hint, partial example, answer.
  3. Check the learner's correction against the concept note and its cited source in 40_References. If the vault has no source, say "not verified" and do not invent one.
  4. Draft one card per entry under ## Corrected cards in Mistakes.md: question::answer [[Source_Note|source]]. Phrase it as an application when possible (a new situation, not the definition). Mark the draft (draft) until the learner edits it in their own words.
  5. Never repeat a question already in the vault: run check_cards.py and fix a duplicate by merging.
  6. Close an entry (closed YYYY-MM-DD) only after the learner answers it right later, without help and from memory; a correct answer right after the hint ladder does not close it.
  7. Do not edit concept notes. Suggest which concept to reread, closed-book first.

Run run-checks after writing.

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.