agentleFS
keysersoosekeysersoose/claude-code-setup/skills/wiki-lint/SKILL.md

wiki-lint

Skill2 starsChanged 4 months agoMITView on GitHub

Lint the global LLM wiki (the knowledge base path defined in your global CLAUDE.md) — the maintenance half of the Karpathy LLM-wiki loop. Checks contradictions, stale claims, orphan pages, index freshness, and broken links, then fixes what it can and reports what needs the user. Use when asked to "lint the wiki", "wiki health check", "clean up the wiki", or roughly weekly when the wiki hasn't been linted in 7+ days.

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-capture, wiki-status and 10 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.
  • jehrhardtSkill

    wiki-capture

    Quickly capture raw thoughts, links, images, or notes to today's Obsidian daily note from anywhere in Pi. Use when the user wants to jot something down for later wiki processing.

    Also in 6 projects that use this

  • nexuschainsSkill

    wiki-status

    Reports the current state of the wiki vault — page counts, category breakdown, hub pages, orphans, stale entries, and a delta showing what has changed since the last ingest. Use this skill when the operator asks "what's the status", "wiki dashboard", "how many pages", "what's stale", "what's been ingested", "show me the delta", or "wiki health overview". Also surfaces structural insights (top hubs, fragmented clusters, bridge pages) when the operator asks "wiki insights", "what's central", or "show me the hubs". Read-only: this skill reports and recommends; it does not modify any files.

    Also in 5 projects that use this

  • nexuschainsSkill

    cross-linker

    Scans the wiki vault and adds missing [[wikilinks]] between pages that are related but not yet connected. Use this skill when the operator says "link my pages", "find missing links", "cross-reference the wiki", "connect my wiki", "add wikilinks", or after any large ingest to weave new pages into the existing knowledge graph. Also trigger when orphaned pages need connecting or when wiki-lint reports fragmented tag clusters. This is a write-heavy skill — it modifies page files to insert links, unlike wiki-lint which only reports.

    Also in 4 projects that use this

  • Ivy-Chen1999Skill

    wiki-synthesize

    Systematically discover synthesis opportunities across the Obsidian wiki — pairs or clusters of concepts that co-occur frequently across pages but have no synthesis page connecting them. Creates new synthesis/ pages that draw explicit cross-cutting conclusions. Use when the user says "synthesize my wiki", "find connections", "what concepts keep coming up together", "/wiki-synthesize", or after a large ingest when the vault has grown significantly.

    Also in 4 projects that use this

  • Ivy-Chen1999Skill

    wiki-setup

    Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up my wiki", "initialize obsidian", "create a new vault", "get started with the wiki". Also use when the user needs to reconfigure their existing vault or fix a broken setup.

    Also in 5 projects that use this

  • bozhouDevSkill

    wiki-init

    Use when bootstrapping a new personal wiki for any knowledge domain — research, codebase documentation, reading notes, competitive analysis, or any long-term knowledge accumulation project.

    Also in 7 projects that use this

  • +1 more from nexuschains
  • +4 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the wiki passes ~100 pages or grep starts missing things phrased differently, install qmd (the search tool Karpathy names) as an MCP …

    line 39

“Common” is measured: kept by at least 6 in 10 of the 33 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

/wiki-lint — wiki maintenance pass

The wiki is the codebase; this is its test suite. WIKI = the global knowledge base path defined in your global CLAUDE.md. It is a git repo — every lint run ends with a commit, so damage is always recoverable.

Checks (run all, cheap subagents for the reading)

Delegate bulk reading to a cheap subagent that returns findings as a packet; verify load-bearing claims yourself before editing (leads, not facts).

  1. Index freshness — does every status line in index.md match the current reality in its project page AND the actual repo state (git log dates, status files)? The index is the highest-traffic file; it rots first.
  2. Stale claims — frontmatter updated: older than 30 days on an ACTIVE project's page = suspect. Cross-check the 2-3 most load-bearing claims per stale page against reality (repo, status files). Fix or mark.
  3. Contradictions — same fact stated differently in two places (index vs page, page vs me/, wiki vs project CLAUDE.md). One fact, one place: fix the copies to reference the canonical location.
  4. Orphans — pages nothing links to (grep for [[name]] and ](path references). Either link them from the right index/_index page or propose deletion.
  5. Broken links — [[wikilinks]] and relative markdown links pointing at files that don't exist. Fix or remove.
  6. Delete-when-wrong sweep — anything proven false (old model names, dead tools, superseded decisions): DELETE the claim, don't annotate around it. Update an existing page rather than creating a duplicate; delete notes that turn out to be wrong.
  7. Log hygiene — daily logs are append-only (never rewrite), but check the last week's rich summaries exist; a run of marker-only days means the session-end summaries aren't being written — flag it.
  8. Size guard — index.md should stay under ~60 lines of content; me/ files under ~30. If growing, tighten: statuses move to pages, index keeps one line each.

Output

  1. Apply all safe fixes directly (index refresh, link repair, deletions of proven-wrong claims, updated: bumps).
  2. git -C <WIKI> add -A && git commit with message lint: <date> — <n> fixes, <n> flags.
  3. Report to the user: fixes applied, contradictions that needed judgment, anything flagged for them (risks noted in pages, decisions only they can make).
  4. Append a one-line entry to today's log: ## [YYYY-MM-DD] lint | wiki | <n> fixes.

Scale guard

When the wiki passes ~100 pages or grep starts missing things phrased differently, install qmd (the search tool Karpathy names) as an MCP server. Not before — at current scale the index IS the search engine.

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.