agentleFS
Sign inStart free
OshayrOshayr/LLM-Wiki/skills/maintain/SKILL.md

wiki-maintain

Skill50 starsChanged 7 months agoMITView on GitHub

Wiki maintenance — lint broken links, merge near-duplicates, upgrade confidence, flag stale pages via freshness tiers, gap analysis, concept synthesis. Use on: 'wiki maintenance', 'wiki cleanup', 'fix wiki', 'wiki health', 'check wiki', 'consolidate wiki'.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. AGMO-Inc/agmo-everywhere★ 4same name
    2. ankishraj/llm-wiki-md-cli★ 1same name
    3. huxwaitt/claude-wiki★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    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. Distinctive:

    Remove dead index entries

    line 27
  2. Very specific:

    Run fact-checker agent on high-confidence pages to verify claims against external sources

    line 41
  3. Distinctive:

    Write the reason in log.md

    line 42
  4. Very specific:

    Add stale: true to frontmatter

    line 66
  5. Very specific:

    If user approves: generate the synthesis page via wiki-writer agent

    line 74

“Common” is measured: kept by at least 6 in 10 of the 3 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 Maintain

Comprehensive wiki maintenance: lint, deduplicate, upgrade, and analyze.

Resolve .wiki/ from plugin install scope. If not found, say "No wiki found."

Arguments

  • /wiki-maintain — run full maintenance (all steps below)
  • /wiki-maintain lint — only fix broken links, missing frontmatter, orphans
  • /wiki-maintain dedup — only find and merge near-duplicate pages
  • /wiki-maintain gaps — only analyze knowledge gaps and missing coverage

Full Maintenance Steps

1. Lint

Launch wiki-auditor agent to:

  • Find [[wiki-links]] that point to non-existent pages — list for user
  • Fix missing frontmatter fields (add defaults)
  • Find orphan pages (no incoming links) — suggest connections
  • Remove dead index entries
  • Fix stale updated: dates on pages that were modified but not date-bumped

2. Deduplicate

Find pages with >60% slug token overlap (Jaccard similarity on slug words split by -):

  • Report pairs for review
  • For confirmed duplicates: auto-merge into one page, update all backlinks, add redirect note to absorbed page

3. Confidence Upgrade

Pages with 3+ independent sources in frontmatter get upgraded:

  • low → medium (if 2+ sources)
  • medium → high (if 3+ corroborating sources)
  • Run fact-checker agent on high-confidence pages to verify claims against external sources
  • Write the reason in log.md

4. Stale Detection (Freshness Tiers)

Pages are evaluated against an intelligent freshness system — not a flat threshold. Each page has a TTL based on its content type:

TierTTLExamples
live15 minstock prices, live scores, server status, deployment state
breaking1-6 hoursbreaking news, incident updates, release announcements
current1-3 daysnews articles, current events, trending topics
fast1-4 weeksAI/LLM/MCP, API changes, model benchmarks
moderate1-3 monthssoftware versions, frameworks, libraries, tools
standard6 monthsgeneral knowledge, how-to guides (default)
academic1 yearresearch papers, studies, formal publications
evergreen5 yearshistory, biographies, foundational concepts, laws, theorems
permanentneverpersonal notes, ideas, memories, journal entries

Resolution order:

  1. Explicit freshness_tier: in page frontmatter (user override)
  2. Explicit ttl: in frontmatter (custom duration like ttl: 30m or ttl: 2d)
  3. Auto-classification from tags, type, and content keywords

For stale pages:

  • Add stale: true to frontmatter
  • Suggest running /wiki-write --refresh-stale or /wiki-read to refresh

5. Concept Auto-Generation

Detect patterns spanning 3+ pages:

  • Find groups of pages that share 3+ common [[wiki-links]] targets
  • For each cluster: suggest a synthesis article that connects the concepts
  • If user approves: generate the synthesis page via wiki-writer agent

6. Regenerate Index

Rebuild .wiki/index.md from all pages:

  • Group by type: field (concept, entity, source, idea, status, etc.)
  • Alphabetical within each group
  • Include confidence badge and one-line description

7. Report

Print summary: broken links fixed, duplicates found, confidence upgrades, stale flags, concepts suggested, index updated.

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.

Check your setup, free