agentleFS
jakubtobiaszjakubtobiasz/second-brain-template/.agents/skills/lint/SKILL.md

lint

Skill0 starsChanged 8 days agoMITView on GitHub

Health-check the second brain. Run the mechanical linter (scripts/lint.py), add a semantic review (contradictions, uncited claims, merge candidates, questions to explore), and save a ranked report to 50-outputs/lint/. Report-only, it never fixes anything. Use when the owner says "lint", "check vault health", "audit the wiki", "what's broken", or for the weekly/monthly maintenance pass.

82 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use coverage, save and 6 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.
  • 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

  • GitHubSkill

    state-management

    CoreAI Sandbox's TanStack Query + mock-JSON data layer. USE WHEN: editing data-fetching hooks (`app/hooks/use*.ts`), adding mock data in `app/data/`, or wiring a component to query state.

    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

  • 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

  • agenticnotetakingSkill

    upgrade

    Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't re-check by hand what the script covers.

    line 17
  2. Very specific:

    Never "fix" 10-raw/ issues by editing raw files.

    line 43

“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: health check (report only)

Never fix anything during lint. Repair is a separate decision (the repair skill).

1. Mechanical pass

scripts/qmd-sync.sh --wait     # fresh search index for the semantic pass (no-op without qmd)
python3 scripts/lint.py --write

This saves 50-outputs/lint/YYYY-MM-DD-lint.md with errors, warnings, and notes: broken links, frontmatter, index coverage, orphans, one-way links, duplicates, stale seeds/state/inbox, and raw-modified (git). Don't re-check by hand what the script covers. If the script fails to run, report that first.

2. Semantic pass

Fill the report's ## Semantic review (agent) section. Don't read every page: sample smartly.

  • Contradictions: pages on overlapping topics (shared links/tags) that state different facts with no ## Contradictions section. Check pages updated recently against their neighbours.
  • Uncited claims: specific numbers, dates, quotes without a nearby [[source]]. Spot-check ~10 pages, prioritizing stable pages and the most-linked hubs.
  • Lost caveats: compare 2-3 recently ingested source pages with their raw files. Did hedges survive?
  • Scatter: several pages covering one topic (merge candidates). With qmd, run a vec: query per hub page title and look for near-duplicate hits in -c wiki; bloat: one page covering many (split candidates).
  • Superseded state: newer sources that changed a fact while other pages still describe the old one.
  • Missing pages: people/concepts mentioned on 3+ pages without their own page.
  • Next questions & sources: 3-5 questions the wiki can almost answer, plus the source that would close each gap.

3. Rank

Finish the report with ## Recommended order: the top 5-10 fixes, ordered by what they unblock (errors that break navigation first, then contradictions, then hygiene). Number them so the owner can say "fix 1-3".

4. Log and report

  • Append to log.md: ## [YYYY-MM-DD] lint | N errors, M warnings + - report: 50-outputs/lint/YYYY-MM-DD-lint.md.
  • Tell the owner the headline counts, the top 3 recommended fixes, and "say fix 1-3 to repair".

Hard constraints

  • Report only: no edits outside 50-outputs/lint/ and log.md.
  • Never "fix" 10-raw/ issues by editing raw files. A raw-modified finding means restore from git (owner decides).

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.