agentleFS
Sign inStart free
DevDizzleDevDizzle/gammarips-harness/.claude/skills/wiki-distill/SKILL.md

wiki-distill

Skill0 starsChanged 3 months agoMITView on GitHub

Ingest a finding into the wiki as a claim-tagged note — from journal lessons, the GammaRips engine research docs, or external literature. Use when a lesson recurs, engine research lands, or a best practice needs encoding.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Read wiki/_index/WIKI-SCHEMA.md first.

    line 8

≈ “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

wiki-distill

Read wiki/_index/WIKI-SCHEMA.md first. One claim per note; edit-over-duplicate; the Exit-context field is mandatory and load-bearing.

Procedure

  1. Check for an existing note (wiki/_index/FINDINGS.md + grep). An update to an existing claim edits that note (and flips Status: superseded on what it replaces if the claim reversed). Only genuinely new claims get new files.
  2. Pick the tag honestly per the schema vocabulary. The two classic errors:
    • upgrading fragile-conditional → proven-on-cohort because it "keeps working" (that's what the forward label arm is for);
    • tagging literature proven-on-cohort because it matches our intuition.
  3. State the evidence with its N, cohort, and exit-context. A finding without its hold/exit assumption is not admissible.
  4. Write the Application paragraph — how the daily loop actually uses it. A note no skill would ever cite is trivia; leave it out.
  5. Wire wikilinks to related notes; register in _index/FINDINGS.md (one line + tag).
  6. python scripts/lint.py.

Allowed sources

Journal lessons; external research docs (research ledger, briefs, docs/DECISIONS — knowledge curation is the one firewall exception); external literature (verify the citation before asserting it). NEVER distill anything that encodes the any external pick or same-day engine state.

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