agentleFS
Sign inStart free
teslanikateslanika/pm-second-brain/skills/pm-recall/SKILL.md

pm-recall

Skill0 starsChanged 33 days agoMITView on GitHub

Answers what the team decided about a subject and how that is known. Use when the user asks "what did we decide about X", "why did we do it this way", "что мы решили про X", "почему мы так сделали", or runs /pm-recall.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read index.md. Then follow the links.

    line 14
  2. Distinctive:

    Read what you found.

    line 17
  3. Distinctive:

    If two documents disagree, show both and say which is newer.

    line 20
  4. Distinctive:

    If you found nothing, say so.

    line 22
  5. Distinctive:

    Write nothing. This skill only reads.

    line 26
  6. Distinctive:

    Never give an answer without links.

    line 27
  7. Distinctive:

    Don't pass it off as current work.

    line 29
  8. Very specific:

    If a long-lived file in context/ disagrees with an active topic, show both and say which is newer.

    line 30

≈ “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

Recall a decision

Steps

  1. Read index.md. Then follow the links; don't walk every folder.
  2. Collect what relates to the subject: files in context/, topics in topics/, then decisions/, specs/ and calls/.
  3. Read what you found.
  4. Answer briefly: what was decided, when, and on what basis.
  5. Give every claim a [[file-name]] link.
  6. If two documents disagree, show both and say which is newer. Don't choose for the person.
  7. If you found nothing, say so. Don't assemble an answer out of guesses.

Rules

  • Write nothing. This skill only reads.
  • Never give an answer without links.
  • Present a status: done topic as history: "closed on this date, this way." Don't pass it off as current work.
  • If a long-lived file in context/ disagrees with an active topic, show both and say which is newer.

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