affaan-m/skill-comply
docs/zh-CN/skills/skill-comply/SKILL.md
可视化技能、规则和代理定义是否被实际遵循——自动生成3种提示严格级别的场景，运行代理，分类行为序列，并报告完整工具调用时间线的合规率
$ install --global
skillsauthnpx skillsauth add affaan-m/everything-claude-code skill-complyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 16, 2026, 4:03 AM247.1s1 file scanned
SKILL.md
- name:
- skill-comply
- description:
- 可视化技能、规则和代理定义是否被实际遵循——自动生成3种提示严格级别的场景，运行代理，分类行为序列，并报告完整工具调用时间线的合规率
- origin:
- ECC
- tools:
- Read, Bash
skill-comply：自动化合规性测量
通过以下方式测量编码代理是否实际遵循技能、规则或代理定义：
- 从任意 .md 文件自动生成预期行为序列（规范）
- 自动生成提示严格程度递减的场景（支持性 → 中性 → 竞争性）
- 运行
claude -p并通过 stream-json 捕获工具调用轨迹 - 使用 LLM（而非正则表达式）将工具调用分类到规范步骤
- 确定性检查时间顺序
- 生成包含规范、提示和时间线的自包含报告
支持的目标
- 技能（
skills/*/SKILL.md）：工作流技能，如搜索优先、TDD 指南 - 规则（
rules/common/*.md）：强制性规则，如 testing.md、security.md、git-workflow.md - 代理定义（
agents/*.md）：代理是否在预期时被调用（内部工作流验证尚不支持）
何时激活
- 用户运行
/skill-comply <path> - 用户询问"这条规则是否真的被遵循？"
- 添加新规则/技能后，验证代理合规性
- 作为质量维护的一部分定期执行
使用方法
# 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>
关键概念：提示独立性
测量技能/规则是否在提示未明确支持时仍被遵循。
报告内容
报告是自包含的，包括：
- 预期行为序列（自动生成的规范）
- 场景提示（每个严格程度级别询问的内容）
- 每个场景的合规性评分
- 带有 LLM 分类标签的工具调用时间线
高级（可选）
对于熟悉钩子的用户，报告还包含针对合规性较低的步骤的钩子提升建议。此为参考信息——主要价值在于合规性本身的可见性。
Related Skills
affaan-m/team-agent-orchestration
data-ai
VerifiedTrustedCommunity
Run team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.
208,450SKILL.mdUpdated Jun 6, 2026
affaan-m/dynamic-workflow-mode
data-ai
VerifiedTrustedCommunity
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
207,422SKILL.mdUpdated Jun 5, 2026
affaan-m/react-testing
development
VerifiedTrustedCommunity
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
206,043SKILL.mdUpdated Jun 4, 2026
affaan-m/react-performance
tools
VerifiedTrustedCommunity
React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.
206,043SKILL.mdUpdated Jun 4, 2026