Skill

skill-comply

Measures coding agent compliance with skills/rules/agents by generating specs/scenarios at 3 strictness levels, running agents, classifying tool calls, and reporting timelines with scores.

Python

Bash

testing

developer-tools

From everything-claude-code

Install

Run in your terminal

npx claudepluginhub memorialmkua-lab/aiclaude

Tool Access

This skill uses the workspace's default tool permissions.

Supporting Assets

View in Repository

fixtures/compliant_trace.jsonl

fixtures/noncompliant_trace.jsonl

fixtures/tdd_spec.yaml

prompts/classifier.md

prompts/scenario_generator.md

prompts/spec_generator.md

pyproject.toml

scripts/__init__.py

scripts/classifier.py

scripts/grader.py

scripts/parser.py

scripts/report.py

scripts/run.py

scripts/runner.py

scripts/scenario_generator.py

scripts/spec_generator.py

scripts/utils.py

tests/test_grader.py

tests/test_parser.py

Skill Content

Similar Skills

agent-harness-construction

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

ecc

140.3k

benchmark

Benchmarks web page Core Web Vitals/bundle sizes, API latency under load, build times; detects regressions via before/after PR comparisons.

ecc

140.3k

agent-eval

Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.

ecc

140.3k

Stats

Stars0

Forks0

Last CommitMar 23, 2026

Actions

View Source View Plugin View on GitHub View README

skill-comply: Automated Compliance Measurement

Measures whether coding agents actually follow skills, rules, or agent definitions by:

Auto-generating expected behavioral sequences (specs) from any .md file
Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)
Running claude -p and capturing tool call traces via stream-json
Classifying tool calls against spec steps using LLM (not regex)
Checking temporal ordering deterministically
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

# 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:

Expected behavioral sequence (auto-generated spec)
Scenario prompts (what was asked at each strictness level)
Compliance scores per scenario
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.