agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/knowledge-structuring/skills/consistency-checking/SKILL.md

consistency-checking

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Tactic for verifying ontology consistency — detect contradictions, cycles, orphans, and type violations.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Verify the ontology is internally consistent.

    line 10
  2. Distinctive:

    Fix root causes: Don't just remove the symptom — understand why the inconsistency arose.

    line 24
  3. Distinctive:

    If vault_lint returns zero issues and graph inspection finds no problems, report clean state.

    line 30

≈ “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

Consistency Checking

Verify the ontology is internally consistent. No contradictions, no cycles in hierarchies, no orphaned concepts, no type violations.

Available SOPs

  • wiki-lint-fix — run structural validation
  • wiki-graph-query — explore suspicious neighborhoods
  • gap-detection — find structural holes
  • merge-candidates — identify near-duplicates

Guiding Principles

  • Contradictions are urgent. Two edges that contradict each other (A supports B, A contradicts B) must be resolved immediately.
  • Orphans are warnings. A concept with no edges is suspicious but not necessarily wrong — it may just need connection.
  • Type violations are errors. An edge type that doesn't make semantic sense (e.g., "question" component_of "source") indicates a classification mistake.
  • Fix root causes. Don't just remove the symptom — understand why the inconsistency arose.

Minimum Yield

<HARD-GATE> ≥1 inconsistency identified and resolved per invocation. If vault_lint returns zero issues and graph inspection finds no problems, report clean state. </HARD-GATE>

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.

Reviews can't be read right now.

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