CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/skill-quality-auditor

Audit and improve skill collections with a 9-dimension scoring framework (Knowledge Delta, Mindset, Anti-Patterns, Specification Compliance, Progressive Disclosure, Freedom Calibration, Pattern Recognition, Practical Usability, Eval Validation), duplication detection, remediation planning, baseline comparison, and CI quality gates; use when evaluating skill quality, generating remediation plans, detecting duplicates, validating artifact conventions, or enforcing publication thresholds.

93

1.26x
Quality

89%

Does it follow best practices?

Impact

99%

1.26x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-4/

{
  "context": "Tests whether the agent produces correctly structured anti-patterns with NEVER/WHY/BAD/GOOD format, covering all three original issues and adding at least one new one.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "NEVER statements used",
      "description": "Each anti-pattern leads with 'NEVER: [action]' phrasing",
      "max_score": 15
    },
    {
      "name": "WHY: explanations present",
      "description": "Each NEVER statement is followed by a 'WHY:' line explaining the consequence",
      "max_score": 18
    },
    {
      "name": "BAD code examples",
      "description": "Each anti-pattern includes a fenced BAD code block showing the incorrect pattern",
      "max_score": 18
    },
    {
      "name": "GOOD code examples",
      "description": "Each anti-pattern includes a fenced GOOD code block showing the correct alternative",
      "max_score": 15
    },
    {
      "name": "All 3 original issues covered",
      "description": "Secrets hardcoding, parallel dependency issues, and floating action tags are all addressed",
      "max_score": 14
    },
    {
      "name": "At least 4 anti-patterns total",
      "description": "Section contains 4 or more distinct NEVER entries (original 3 + at least 1 new)",
      "max_score": 10
    },
    {
      "name": "Score impact explained",
      "description": "before-after-diff.md explains which D3 signals the new content satisfies and estimates score delta",
      "max_score": 10
    }
  ]
}

SKILL.md

tile.json