skillhub

skill-comply✓ Pass

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

80out of 100
188.6k
★ stars
7
↓ downloads
28
◉ views

// Install Skill

Install Skill

Skills are third-party code from public GitHub repositories. SkillHub scans for known malicious patterns but cannot guarantee safety. Review the source code before installing.

Install globally (user-level):

npx skillhub install affaan-m/everything-claude-code/skill-comply

Install in current project:

npx skillhub install affaan-m/everything-claude-code/skill-comply --project

Suggested path: ~/.claude/skills/skill-comply/

AI Review

80
out of 100
Instruction Quality80
Description Precision80
Usefulness81
Technical Soundness75

Exceptional meta-skill — the only automated compliance testing tool for Claude Code skills reviewed so far. Prompt independence measurement (testing without explicit trigger support) is a novel concept. LLM-based classification is more reliable than regex.

betacomplexClaude Code developers and tool authors who ship skills and want to verify they're followed.Verifying skill adoption after deployment; regression testing rules; measuring agent definition compliance; periodic quality audits.
Reviewed by claude-code on 4/13/2026

SKILL.md Content

---
name: skill-comply
description: Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
origin: ECC
tools: Read, Bash
---

# skill-comply: Automated Compliance Measurement

Measures whether coding agents actually follow skills, rules, or agent definitions by:
1. Auto-generating expected behavioral sequences (specs) from any .md file
2. Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)
3. Running `claude -p` and capturing tool call traces via stream-json
4. Classifying tool calls against spec steps using LLM (not regex)
5. Checking temporal ordering deterministically
6. Generating self-contained reports with spec, prompts, and timelines

## Supported Targets

- **Skills** (`skills/*/SKILL.md`): Workflow skills like search-first, TDD guides
- **Rules** (`rules/common/*.md`): Mandatory rules like testing.md, security.md, git-workflow.md
- **Agent definitions** (`agents/*.md`): Whether an agent gets invoked when expected (internal workflow verification not yet supported)

## When to Activate

- User runs `/skill-comply <path>`
- User asks "is this rule actually being followed?"
- After adding new rules/skills, to verify agent compliance
- Periodically as part of quality maintenance

## Usage

```bash
# Full run
uv run python -m scripts.run ~/.claude/rules/common/testing.md

# Dry run (no cost, spec + scenarios only)
uv run python -m scripts.run --dry-run ~/.claude/skills/search-first/SKILL.md

# Custom models
uv run python -m scripts.run --gen-model haiku --model sonnet <path>
```

## Key Concept: Prompt Independence

Measures whether a skill/rule is followed even when the prompt doesn't explicitly support it.

## Report Contents

Reports are self-contained and include:
1. Expected behavioral sequence (auto-generated spec)
2. Scenario prompts (what was asked at each strictness level)
3. Compliance scores per scenario
4. Tool call timelines with LLM classification labels

### Advanced (optional)

For users familiar with hooks, reports also include hook promotion recommendations for steps with low compliance. This is informational — the main value is the compliance visibility itself.