agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/knowledge-structuring/skills/vault-maintenance/SKILL.md

vault-maintenance

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Tactic for vault health upkeep — lint, orphan resolution, merge candidates, confidence updates. Minimum yield ≥1 issue resolved per invocation.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Lint first: Start with vault_lint in report mode to assess current health.

    line 21
  2. Distinctive:

    Conservative auto-fix: Only auto-fix safe operations (duplicate edge removal, stale index pruning).

    line 23
  3. Distinctive:

    If vault_lint returns zero issues, report clean state and exit.

    line 31
  4. Distinctive:

    When to update confidence scores

    line 40
  5. Distinctive:

    Run vault_lint (report mode) — assess issue landscape

    line 43

≈ “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

Vault Maintenance

Vault health upkeep. Called when CC judges the vault has accumulated enough entropy to warrant cleanup, or periodically between research phases.

Available SOPs

  • wiki-lint-fix — run lint checks, identify issues, optionally auto-fix
  • wiki-search — find near-duplicate candidates for merging
  • wiki-graph-query — explore orphan neighborhoods for reconnection
  • wiki-add-edge — reconnect orphans to the graph

Guiding Principles

  • Lint first. Start with vault_lint in report mode to assess current health.
  • Triage by severity. Errors (broken links, missing frontmatter) before warnings (orphans, stale entries).
  • Conservative auto-fix. Only auto-fix safe operations (duplicate edge removal, stale index pruning). Manual intervention for ambiguous cases.
  • Merge, don't delete. Near-duplicate pages should be merged (consolidate content, redirect edges) rather than deleted.
  • Confidence decay. Pages with evidence older than the research horizon may need confidence score updates.

Minimum Yield

<HARD-GATE> ≥1 issue resolved per invocation. If vault_lint returns zero issues, report clean state and exit. </HARD-GATE>

Execution Guidance

CC has full autonomy over:

  • Which issues to address and in what order
  • Whether to auto-fix or manually resolve
  • How aggressively to merge near-duplicates
  • When to update confidence scores

Typical flow (reference, not prescription):

  1. Run vault_lint (report mode) — assess issue landscape
  2. Categorize: auto-fixable vs manual
  3. Auto-fix safe issues (duplicate edges, stale index)
  4. For orphans: search for connection candidates, add edges
  5. For near-duplicates: merge content into canonical page, update edges
  6. Re-run vault_lint to confirm resolution

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