pantheon-org/skill-quality-auditor

Skill Quality Auditor

Navigation hub for evaluating, maintaining, and improving skill quality with 9-dimension framework scoring.

Prerequisites

This skill drives the pantheon-skill-auditor CLI and is distributed by it (pantheon-skill-auditor skill install). Every audit command below requires that binary on PATH. Confirm it is available:

pantheon-skill-auditor --version

If it is missing, build or install it first (see Quick Start). There is no self-contained fallback for these commands.

Quick Start

Build once, then audit:

Build once:

bun run build:skill-auditor

Run audits:

# Single skill
pantheon-skill-auditor evaluate <domain>/<skill-name> --json --store

# Batch with grade gate
pantheon-skill-auditor batch <skill1> <skill2> --fail-below B --store

When to Use

• Evaluate skills before merge or publication using 9-dimension scoring
• Generate remediation plans, detect duplication (>20% threshold), or enforce CI quality gates
• Validate eval scenario coverage and artifact conventions

When Not to Use

• Write the skill first — do not audit an unfinished draft
• Avoid using this as a substitute for peer review of logic or domain accuracy

Workflow

1. Run pantheon-skill-auditor evaluate <skill> --json --store
2. Check artifacts and eval coverage using deterministic criteria
3. Generate a remediation plan with T-shirt sizing and score delta estimates
4. Run the auditor again to verify improvement; if score is below target, check remediation-plan.md and focus on the lowest-scoring dimension

Mindset

• Use scores as directional signals, not absolute truth.
• Apply deterministic, reproducible checks over manual review.
• Use threshold-based evaluation rather than relative comparisons.
• Keep audit rules strict for safety and consistency; stay flexible elsewhere.

Anti-Patterns (Summary)

• NEVER skip baseline comparison in recurring audits — WHY: score regressions go undetected without a prior audit.json
• NEVER ignore Knowledge Delta below 15/20 — WHY: low D1 means the skill adds no value over LLM baseline
• NEVER apply subjective scoring — WHY: scores drift between evaluators and cannot be automated in CI
• NEVER create kitchen-sink skills covering unrelated tasks — WHY: broad scope kills D7 and prevents correct triggering
• NEVER use harness-specific paths in skill content — WHY: absolute paths break when installed in a different repo
• NEVER list references without "When to Use" conditions — WHY: unconditional loading bloats context and penalises D5

Ensure you review Detailed Anti-Patterns for all WHY/BAD/GOOD failure modes including agent name references and D4 heading rules.

Examples

Remediation workflow:

pantheon-skill-auditor evaluate documentation/markdown-authoring --json --store
# Score: 98/140 (C+) -> review remediation-plan.md -> fix -> re-audit -> 128/140 (A)

PR-scoped triage:

skills=$(git diff --name-only origin/main | grep "skills/.*/SKILL.md" | sed 's|skills/||;s|/SKILL.md||' | tr '\n' ' ')
pantheon-skill-auditor batch $skills --fail-below B --store

Audit all skills:

pantheon-skill-auditor batch $(find skills -name "SKILL.md" | sed 's|skills/||;s|/SKILL.md||' | tr '\n' ' ')

See Audit Workflow Examples for input/output pairs and CI quality gate examples.

Self-Audit

pantheon-skill-auditor evaluate agentic-harness/skill-quality-auditor --json
# Expected: A grade, total >= 126/140

References

Framework

| Topic | Reference | When to Use | | --- | --- | --- | | Per-dimension criteria and bonus rules | Dimensions | Evaluating any dimension or understanding the rubric | | Score thresholds and grade bands | Scoring Rubric | Calculating a total score or assigning a grade | | A-grade checklist and red flags | Quality Standards | Targeting A-grade or reviewing blockers | | Trigger pattern density and keyword analysis | Pattern Recognition | Scoring D7 or improving description keywords | | Canonical SKILL.md structure and References table standard | SKILL Template | Authoring or refactoring a skill |

Operations

| Topic | Reference | When to Use | | --- | --- | --- | | CI gate configuration and batch pass/fail logic | Quality Thresholds | Setting up CI quality gates | | NEVER/WHY/BAD/GOOD failure modes per dimension | Anti-Patterns | Explaining low scores or writing remediation guidance | | T-shirt sizing and remediation roadmaps | Remediation Planning | Writing a remediation plan for a C/D-grade skill | | Deduplication workflow and aggregation guidance | Duplication Detection | Detecting skill overlap or planning aggregations | | pantheon-skill-auditor evaluate/batch usage and output formats | Scripts Workflow | Running audits from the command line | | Registry publication gates and tessl compliance checks | Tessl Compliance | Preparing a skill for public registry submission |