agentleFS
HagaiHenHagaiHen/podcast-wiki/.claude/skills/lint-wiki/SKILL.md

lint-wiki

Skill14 starsChanged 37 days agoMITView on GitHub

Health-check the podcast wiki (wiki/) and fix what's found. Use when the user asks to lint, audit, clean up, or check the wiki, or after a large ingest.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. enzobleuze/machine-claude★ 2same name
    2. artificialbeingz/abz-karpathy-llm-wiki★ 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 repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are 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.

  • 3

    Very specific

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

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

    Run uv run tools/lint_wiki.py.

    line 12
  2. Very specific:

    Read wiki/index.md, then the concept pages (prioritise those with the most sources and those updated most recently).

    line 29
  3. Very specific:

    Don't edit raw/. Don't re-synthesise from raw transcripts: lint works on the wiki as written.

    line 39

≈ “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

Lint the wiki

Two passes: mechanical checks by script, then judgment checks by reading. Fix issues in place following the conventions in CLAUDE.md, then report.

1. Mechanical pass

Run uv run tools/lint_wiki.py. Each line is <check> <page>: <detail>:

CheckFix
broken-linkPoint the link at the right page, or create the missing page if it's warranted
not-in-indexAdd a one-line entry to wiki/index.md under the right hub section ("Unsorted" if no hub page)
orphanLink the concept from related concepts' ## Related and its hub
missing-sectionAdd the missing template section (it may stay empty)
sources-mismatchSet sources: to the number of distinct episodes the page links
no-hubSet hubs: to 1–2 domains
missing-raw / url-mismatchCopy raw: path and spotify_url verbatim from the raw file; never retype
needs-hubCreate wiki/hubs/<domain>.md (hub template) and move its concepts out of "Unsorted" in the index

Re-run until it prints clean.

2. Judgment pass

Read wiki/index.md, then the concept pages (prioritise those with the most sources and those updated most recently). Look for:

  • Near-duplicate concepts: two pages covering the same topic. Merge into the better slug, then redirect every link to it and delete the other.
  • Silent contradictions: claims in Key ideas that conflict within one page but aren't under Disagreements & open questions. Move them there with both sources. Never delete either claim. (/dream step 10 does the systematic cross-page pass.)
  • Stale summaries: a Summary that no longer reflects its Key ideas (e.g. written at 1 source, now 5). Rewrite it.
  • Missing cross-links: concepts that clearly relate but don't link each other in ## Related.
  • Unlinked claims: Key ideas with no episode link.
  • Takeaway drift: concept Takeaways missing from wiki/takeaways/to-try.md, or vice versa.
  • Concept gaps: a topic recurring across 3+ pages with no page of its own. Suggest it; don't create it unless the user agrees.

Don't edit raw/. Don't re-synthesise from raw transcripts: lint works on the wiki as written.

3. Finish

  • Append to wiki/log.md: ## YYYY-MM-DD — lint then fixed: … (counts by check) and suggested: ….
  • Commit: git add wiki && git commit -m "lint: <summary>".
  • Reply with what was fixed, by check, and any suggestions awaiting the user's decision.

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.