agentleFS
MicrosoftKnown publishermicrosoft/llmwiki/plugin/skills/wiki-fix/SKILL.md

wiki-fix

Skill116 starsChanged 4 days agoMITView on GitHub

Find and fix problems in the user's LLM Wiki — stale index entries, unindexed pages, missing frontmatter, broken links, orphaned pages — with the LLM Wiki MCP tools, asking before anything is deleted.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    Preview: Call wiki_fix with dryRun: true and summarize what it would change.

    line 9
  2. Very specific:

    Apply: Call wiki_fix without dryRun, only if the preview listed no pages to delete or the user approved deleting them.

    line 11
  3. Very specific:

    Never delete without confirmation: Use wiki_delete_page only after the user explicitly agrees, then fix the links it reports in linkedFrom.

    line 16
  4. Very specific:

    Verify: Run wiki_lint and report what was fixed and what still needs the user's decision.

    line 17
  5. Very specific:

    If a tool reports that no wiki is open, call wiki_open with the absolute path of the current workspace folder, then retry.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Fix wiki issues

  1. Preview. Call wiki_fix with dryRun: true and summarize what it would change.
  2. Confirm deletions. If removed_pages is not empty, list those pages (entity/concept pages whose raw sources were all removed) and ask the user whether to delete them. Wait for an explicit yes. If the user declines or doesn't answer, don't call wiki_fix without dryRun, because it would delete them. Run wiki_lint instead, and continue with step 4 using its findings.
  3. Apply. Call wiki_fix without dryRun, only if the preview listed no pages to delete or the user approved deleting them.
  4. Resolve what remains. Work through the findings that still need judgment:
    • broken-links / missing-pages: read the page with wiki_read_page, find the intended target with wiki_query, then fix the link with wiki_update_page (bodyReplace with the corrected body), or remove the link. Create a missing page only if the user wants it.
    • frontmatter-validation (invalid type): set a valid type (entity, concept, source, summary or query) with wiki_update_page.
    • orphan-pages: link the page from related pages with wiki_add_crosslinks.
  5. Never delete without confirmation. Use wiki_delete_page only after the user explicitly agrees, then fix the links it reports in linkedFrom.
  6. Verify. Run wiki_lint and report what was fixed and what still needs the user's decision.

If a tool reports that no wiki is open, call wiki_open with the absolute path of the current workspace folder, then retry.

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.