agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/convergence/skills/coherence-diagnosis/SKILL.md

coherence-diagnosis

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Strategy for auditing preference consistency using Consistency Ratio, cycle enumeration, and mElo to detect and resolve intransitivities.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Run cycle-detection on full comparison matrix

    line 57
  2. Distinctive:

    If consistent (CR < 0.1): proceed to ranking-synthesis

    line 59
  3. Distinctive:

    If inconsistent: run inconsistency-localization

    line 60
  4. Distinctive:

    Document all repairs in audit trail

    line 64

≈ “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

Coherence Diagnosis

Purpose

Audit an existing comparison matrix for logical consistency. Detect cycles, quantify transitivity violations, localize problematic judgments, and recommend corrections. Essential as a quality gate before finalizing any ranking.

When to use

  • Existing comparison data needs validation
  • Suspicion of inconsistent judgments
  • Pre-finalization quality gate
  • AHP consistency ratio check required
  • Debugging unexpected ranking results

Budget

ResourceAllocation
Cycle detectionFull matrix scan
Consistency metricCR < 0.1 (AHP) or transitivity > 90%
Repair comparisons≤ 20% of original comparisons
Iterations1-3 audit-repair cycles

State Ledger

comparison_matrix: {}   # pair → winner
candidates: []
consistency_metrics: {cr: null, transitivity: null, cycles_count: 0}
cycles: []              # [[a>b, b>c, c>a], ...]
problematic_pairs: []   # pairs involved in most cycles
repair_log: []          # [{pair, old_judgment, new_judgment, reason}]
iteration: 0

Available Tactics

  • consistency-audit-loop — detect, localize, repair, recompute

Available SOPs

  • cycle-detection
  • inconsistency-localization
  • comparison-executor (for re-comparison)
  • rating-update (for recomputation)
  • convergence-check
  • ranking-synthesis

Execution Guidance

  1. Run cycle-detection on full comparison matrix
  2. Compute consistency metrics (CR, transitivity score)
  3. If consistent (CR < 0.1): proceed to ranking-synthesis
  4. If inconsistent: run inconsistency-localization
  5. Re-compare problematic pairs via comparison-executor
  6. Recompute ratings and re-check consistency
  7. Repeat until consistent or repair budget exhausted
  8. Document all repairs in audit trail

Output Format

diagnosis:
  consistency_ratio: 0.04
  transitivity_score: 0.97
  cycles_found: 1
  cycles_resolved: 1
  repairs_made: 2
audit_trail:
  - {pair: ["b", "d"], original: "b", revised: "d", reason: "..."}
final_ranking_valid: true
method: consistency-ratio

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