agentleFS
playingpossummplayingpossumm/loose-ends/.claude/skills/lint/SKILL.md

lint

Skill0 starsChanged 34 days agoMITView on GitHub

Health-check the vault for citation validity, broken links, orphan pages, contradictions, stale claims, and index drift. Reports; fixes only mechanical problems. Use when the user says "lint", "health check", "check the vault", or before a brief.

82 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use query, coverage and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArtemXTechSkill

    query

    Query data from this vault. USE WHEN user asks about projects, clients, tasks, daily notes. Use grep to extract frontmatter - do NOT read full files.

    Also in 17 projects that use this

  • PydanticSkill

    coverage

    Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.

    Also in 4 projects that use this

  • seongjaeryuSkill

    save

    Complete and save your current thinking to Bindly

    Also in 5 projects that use this

  • BugRogerSkill

    project

    Project lifecycle management. Dispatches to Ada.

    Also in 4 projects that use this

  • AnthropicSkill

    digest

    Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action items, or reviewing a week's decisions and document updates grouped by project.

    Also in 3 projects that use this

  • AWSSkill

    issue

    Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Every claim in wiki/ and every loop must cite a sources/ page plus a locator.

    line 13
  2. Very specific:

    Every [[wikilink]] resolves.

    line 18
  3. Distinctive:

    Do not flag pages merely for being old.

    line 37
  4. Very specific:

    Run python scripts/synthesis.py.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 68 edited versions of this file we could read. “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

Find what has rotted. Report everything; fix only what is unambiguous.

Checks

1. Citation validity (the automated guard, and the one that matters) Every claim in wiki/ and every loop must cite a sources/ page plus a locator. Every cited source id must exist in raw/. Report uncited claims and dangling citations individually, since this metric is how the project is judged, so do not summarise it away.

2. Link integrity Every [[wikilink]] resolves. Report broken ones with their containing page.

3. Orphans Pages with no inbound links. Often means a related page was not updated on ingest.

4. Missing summaries index.md is generated from each page's summary: field, so a page without one appears in the index as a bare title. Report any page in wiki/ or loops/ that has no summary:.

Index drift itself is no longer a class of fault: scripts/build_index.py rebuilds the file from the vault, so it cannot disagree with what is on disk. Run it if the index looks stale.

5. Contradictions Pages asserting incompatible things. Check especially where two sources compiled at different times touched the same entity. Report; never resolve.

6. Staleness, source-relative rather than calendar-relative A claim is stale when a newer source on the same entity exists and was not integrated. Do not flag pages merely for being old; a page untouched for six months because nothing new arrived is healthy, and flagging it trains the user to ignore staleness warnings.

7. Frontmatter conformance Mandatory fields present per CLAUDE.md. Report anything missing sources:, since that field is what makes /unsource possible.

8. Loop hygiene Open loops with no citation; loops open past their due:; loops with surfaced: ≥ 4 not yet escalated; anything in loops/open/ that reads as already done. Also loops missing title: or summary:, or whose summary: narrates the user in the third person, because the nudge email is built from that line alone and silently sends nothing without it.

9. Synthesis gaps Run python scripts/synthesis.py. It lists every name in mem/ mentioned across three or more sources with no entity page, and every category: carrying three or more sources with no concept page. Write the pages it names.

This is the check most likely to find something. The promotion rule in /ingest cannot fire on its own, because one source at a time sees no counts, so gaps accumulate silently while the source count grows.

10. Coverage gaps Entities mentioned across several pages with no page of their own (promote at 3 mentions). Concepts referenced but never compiled. Questions the vault could not answer this week.

Fix vs. report

Fix silently: a stale index (rebuild it), frontmatter fields derivable from context, broken links where the target obviously renamed, surfaced: counters.

Report only, never touch: contradictions, staleness, orphans, coverage gaps, anything in mem/, and anything requiring judgement about what the user meant.

Output

Counts first, then details grouped by check, worst first. End with the three things most worth acting on. Append to log.md: ## [YYYY-MM-DD] lint | N issues, N fixed.

Suggest new questions and missing sources at the end, since a lint pass is also where the vault tells you what to read next.

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.