CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/skill-quality-auditor

Audit and improve skill collections with an 8-dimension scoring framework, duplication detection, remediation planning, and CI quality gates; use when evaluating skill quality, generating remediation plans, validating report format, or enforcing repository-wide skill artifact conventions.

Does it follow best practices?

Evaluation93%

1.33x

Agent success when using this tile

Validation for skill structure

Overview
Skills
Evals
Files

framework-skill-judge-canonical.mdreferences/

category:
framework
priority:
CRITICAL
source:
skill-judge canonical snapshot (vendored notes, 2026-02-20)

Skill-Judge Canonical Integration

This file integrates the canonical skill-judge framework into skill-quality-auditor.

Source

  • Upstream snapshot path: ../deadalus/.agents/skills/skill-judge/SKILL.md
  • Upstream skill name: skill-judge
  • Upstream purpose: evaluate skill design quality against official specifications and best practices.

Canonical Principles

  1. Skills should maximize knowledge delta.
  2. Skills should transfer expert thinking patterns, not tutorials.
  3. Skills should include explicit anti-patterns with consequences.
  4. Description quality controls activation quality.
  5. Progressive disclosure should keep SKILL.md concise.

Canonical Dimensions

The canonical framework evaluates across 8 dimensions totaling 120 points.

DimensionMaxLocal implementation
Knowledge Delta20framework-skill-judge-dimensions.md
Mindset + Procedures15framework-skill-judge-dimensions.md
Anti-Pattern Quality15framework-skill-judge-dimensions.md
Specification Compliance15framework-scoring-rubric.md
Progressive Disclosure15framework-scoring-rubric.md
Freedom Calibration15framework-scoring-rubric.md
Pattern Recognition10framework-scoring-rubric.md
Practical Usability15framework-quality-standards.md

Sync Procedure

  1. Compare this file and framework-skill-judge-dimensions.md against upstream skill-judge.
  2. If upstream semantics change, update local dimensions and rubric references first.
  3. Re-run audits using scripts/evaluate.sh and scripts/audit-skills.sh.
  4. Record version notes in the audit report under .context/analysis/.

Notes

This file intentionally keeps only canonical integration metadata and mapping. Detailed evaluator guidance remains in the existing framework reference files.

Install with Tessl CLI

npx tessl i pantheon-ai/skill-quality-auditor@0.1.4

SKILL.md

tile.json