agentleFS
SkinnnyJaySkinnnyJay/wiki-llm/skills/wiki-lint/SKILL.md

wiki-lint

Skill0 starsChanged 4 months agoMITView on GitHub

Audits llm-wiki/wiki for orphans, stale claims, missing links, and contradictions. Use when user asks to health-check the wiki.

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-capture, cross-linker and 7 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

    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

  • nexuschainsSkill

    tag-taxonomy

    Enforces and normalizes tags across the wiki against the controlled vocabulary in wiki/schema/tag-taxonomy.md. Use this skill when the operator says "fix my tags", "normalize tags", "tag audit", "clean up tags", "tag taxonomy", or "my tags are a mess". Also use when creating or updating wiki pages and the right tags are unclear. Operates in three modes: Audit (report current state), Normalize (apply fixes), and Classify (tag a single new page). Always reads the taxonomy file before assigning any tags.

    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

  • 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

  • bozhouDevSkill

    wiki-update

    Use when revising existing wiki pages because knowledge has changed, a new piece of information updates or contradicts existing content, or the user wants to directly edit wiki content with LLM assistance.

    Also in 7 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 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.

  • 5

    Very specific

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

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

    Read wiki/index.md and scan wiki//*.md (or scope to paths the user named).

    line 14
  2. Very specific:

    If outputs/ exists, include drafts vs wiki/ duplicate or conflicting claims in scope.

    line 15
  3. Distinctive:

    Run machine lint first (then deepen with this skill):

    line 16
  4. Very specific:

    Check llm-wiki kg conflicts and claim IR in outputs/claims.json.

    line 39
  5. Very specific:

    If outputs/ exists, flag duplicate claims or contradictions between outputs/ and wiki/ (treat outputs as drafts until promoted with …

    line 44
  6. Very specific:

    If auto-fixable edits were applied and viewer.enabled is not false in config:

    line 48

“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 — Auditor

Audit wiki/ for orphans, broken [[wikilinks]], contradictions, and gaps. Prefer the deterministic CLI/MCP gates when available; use skill judgment for semantic contradictions the machine cannot see. For raw/ that is still structurally broken before wiki merge, use wiki-raw-prepare / llm-wiki raw validate first; wiki-lint focuses on wiki/ coherence.

Pre-flight

  1. Read wiki/index.md and scan wiki/**/*.md (or scope to paths the user named).
  2. If outputs/ exists, include drafts vs wiki/ duplicate or conflicting claims in scope.
  3. Run machine lint first (then deepen with this skill):
llm-wiki lint --write-report
# after wiki merge / before shipping:
llm-wiki compile --no-site
# surgical (pages citing one source):
llm-wiki compile --raw raw/path.md --no-site

MCP: wiki_lint, wiki_compile (same gates). Reports: outputs/lint-report.json, outputs/claims.json.

Steps

Step 1 — Index vs filesystem

  • List orphans: pages not linked from wiki/index.md where you expect them listed (project convention from llm-wiki/CLAUDE.md).
  • List broken wikilinks: targets that do not exist.
  • Compare with llm-wiki lint / outputs/lint-report.json (orphan, broken_wikilink).

Step 2 — Contradictions and gaps

  • Note contradictions between pages about the same entity (different claims).
  • Check llm-wiki kg conflicts and claim IR in outputs/claims.json.
  • Suggest next sources or open questions to resolve gaps.

Step 3 — Outputs vs wiki

  • If outputs/ exists, flag duplicate claims or contradictions between outputs/ and wiki/ (treat outputs as drafts until promoted with evidence).

Step 4 — Refresh site viewer

If auto-fixable edits were applied and viewer.enabled is not false in config:

llm-wiki build-site --if-stale
# or fold into:
llm-wiki compile

This rebuilds wiki/.og/ only when wiki content is newer than the last build.

Done looks like

  • Deliverable is a structured report: orphans, broken links, contradictions, gaps — each with concrete next actions (create page, remove link, merge, research).
  • Machine gates (lint / compile / optional knowledge-test) are green or listed with fixes.
  • User knows whether the wiki is ship-ready for their use case or needs follow-up wiki-research / wiki-maintainer work.

Artifacts

ReadsWrites
wiki/index.md, wiki/**/*.md, optional outputs/**Prefer outputs/lint-report.json / claims.json via CLI; optional outputs/lint-report.md

Downstream: wiki-maintainer (fixes), wiki-pipeline (gate). See skills/references/pipeline-artifacts.md. Shared config: skills/references/mcp-and-kg.md (compile.*, aliases, ontology).

Related skills

  • wiki-raw-prepare — structural cleanup in raw/ before merge.
  • wiki-maintainer — apply cross-link and index fixes.
  • wiki-query — Q&A from wiki after lint passes.
  • wiki-session-memory — session memory files under raw/memory/ (optional context).

Smoke check

  • CLI: llm-wiki lint --write-report; llm-wiki compile --no-site; llm-wiki knowledge-test --file examples/knowledge-tests.json (plugin examples; scaffolded vaults pass).
  • Prompt: Invoke this skill; confirm the report structure (orphans, links, gaps) is produced.

Optional: skills/references/context-persona.md when running checks via tools; persona.name in config (default Gennie).

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.