[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSB9ZHPCKMP1KMRWXF17EP":3,"skill-same:01M7CSB9ZHPCKMP1KMRWXF17EP":138},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CSB9ZHPCKMP1KMRWXF17EP","skill-comply",null,"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","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-comply\ndescription: 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\nmetadata:\n  origin: ECC\ntools: Read, Bash\n---\n\n# skill-comply: Automated Compliance Measurement\n\nMeasures whether coding agents actually follow skills, rules, or agent definitions by:\n1. Auto-generating expected behavioral sequences (specs) from any .md file\n2. Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)\n3. Running `claude -p` and capturing tool call traces via stream-json\n4. Classifying tool calls against spec steps using LLM (not regex)\n5. Checking temporal ordering deterministically\n6. Generating self-contained reports with spec, prompts, and timelines\n\n## Supported Targets\n\n- **Skills** (`skills\u002F*\u002FSKILL.md`): Workflow skills like search-first, TDD guides\n- **Rules** (`rules\u002Fcommon\u002F*.md`): Mandatory rules like testing.md, security.md, git-workflow.md\n- **Agent definitions** (`agents\u002F*.md`): Whether an agent gets invoked when expected (internal workflow verification not yet supported)\n\n## When to Activate\n\n- User runs `\u002Fskill-comply \u003Cpath>`\n- User asks \"is this rule actually being followed?\"\n- After adding new rules\u002Fskills, to verify agent compliance\n- Periodically as part of quality maintenance\n\n## Usage\n\n```bash\n# Full run\nuv run python -m scripts.run ~\u002F.claude\u002Frules\u002Fcommon\u002Ftesting.md\n\n# Dry run (no cost, spec + scenarios only)\nuv run python -m scripts.run --dry-run ~\u002F.claude\u002Fskills\u002Fsearch-first\u002FSKILL.md\n\n# Custom models\nuv run python -m scripts.run --gen-model haiku --model sonnet \u003Cpath>\n```\n\n## Key Concept: Prompt Independence\n\nMeasures whether a skill\u002Frule is followed even when the prompt doesn't explicitly support it.\n\n## Report Contents\n\nReports are self-contained and include:\n1. Expected behavioral sequence (auto-generated spec)\n2. Scenario prompts (what was asked at each strictness level)\n3. Compliance scores per scenario\n4. Tool call timelines with LLM classification labels\n\n### Advanced (optional)\n\nFor 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.\n","# skill-comply: Automated Compliance Measurement\n\nMeasures whether coding agents actually follow skills, rules, or agent definitions by:\n1. Auto-generating expected behavioral sequences (specs) from any .md file\n2. Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)\n3. Running `claude -p` and capturing tool call traces via stream-json\n4. Classifying tool calls against spec steps using LLM (not regex)\n5. Checking temporal ordering deterministically\n6. Generating self-contained reports with spec, prompts, and timelines\n\n## Supported Targets\n\n- **Skills** (`skills\u002F*\u002FSKILL.md`): Workflow skills like search-first, TDD guides\n- **Rules** (`rules\u002Fcommon\u002F*.md`): Mandatory rules like testing.md, security.md, git-workflow.md\n- **Agent definitions** (`agents\u002F*.md`): Whether an agent gets invoked when expected (internal workflow verification not yet supported)\n\n## When to Activate\n\n- User runs `\u002Fskill-comply \u003Cpath>`\n- User asks \"is this rule actually being followed?\"\n- After adding new rules\u002Fskills, to verify agent compliance\n- Periodically as part of quality maintenance\n\n## Usage\n\n```bash\n# Full run\nuv run python -m scripts.run ~\u002F.claude\u002Frules\u002Fcommon\u002Ftesting.md\n\n# Dry run (no cost, spec + scenarios only)\nuv run python -m scripts.run --dry-run ~\u002F.claude\u002Fskills\u002Fsearch-first\u002FSKILL.md\n\n# Custom models\nuv run python -m scripts.run --gen-model haiku --model sonnet \u003Cpath>\n```\n\n## Key Concept: Prompt Independence\n\nMeasures whether a skill\u002Frule is followed even when the prompt doesn't explicitly support it.\n\n## Report Contents\n\nReports are self-contained and include:\n1. Expected behavioral sequence (auto-generated spec)\n2. Scenario prompts (what was asked at each strictness level)\n3. Compliance scores per scenario\n4. Tool call timelines with LLM classification labels\n\n### Advanced (optional)\n\nFor 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.\n",{"name":5,"tools":24,"metadata":25,"description":7},"Read, Bash",{"origin":26},"ECC","main","a73152352c0612252131e5cf84e91312a6cf17dc","ai-agents\u002Fskill-comply","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill skill-comply",{"tool":41,"command":42},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill skill-comply",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill skill-comply","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002FSKILL.md",true,[49,55,59,63,69,73,77,81,85,90,94,98,102,106,110,114,118,122,126,130,134],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},".gitignore","OTHER","其他",76,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002F.gitignore",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"fixtures\u002Fcompliant_trace.jsonl",1070,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ffixtures\u002Fcompliant_trace.jsonl",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"fixtures\u002Fnoncompliant_trace.jsonl",629,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ffixtures\u002Fnoncompliant_trace.jsonl",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"fixtures\u002Ftdd_spec.yaml","REFERENCE","参考文档",1266,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ffixtures\u002Ftdd_spec.yaml",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"prompts\u002Fclassifier.md",1064,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fprompts\u002Fclassifier.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"prompts\u002Fscenario_generator.md",1974,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fprompts\u002Fscenario_generator.md",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"prompts\u002Fspec_generator.md",1645,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fprompts\u002Fspec_generator.md",{"path":82,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":83,"sourceHtmlUrl":84},"pyproject.toml",299,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fpyproject.toml",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":14,"sourceHtmlUrl":89},"scripts\u002F__init__.py","SCRIPT","脚本","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002F__init__.py",{"path":91,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Fclassifier.py",2414,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Fclassifier.py",{"path":95,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fgrader.py",4404,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Fgrader.py",{"path":99,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fparser.py",2777,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Fparser.py",{"path":103,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Freport.py",6470,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Freport.py",{"path":107,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Frun.py",4294,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Frun.py",{"path":111,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Frunner.py",7094,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Frunner.py",{"path":115,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Fscenario_generator.py",1835,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Fscenario_generator.py",{"path":119,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fspec_generator.py",2202,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Fspec_generator.py",{"path":123,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Futils.py",411,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Fscripts\u002Futils.py",{"path":127,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":128,"sourceHtmlUrl":129},"tests\u002Ftest_grader.py",8185,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ftests\u002Ftest_grader.py",{"path":131,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":132,"sourceHtmlUrl":133},"tests\u002Ftest_parser.py",3140,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ftests\u002Ftest_parser.py",{"path":135,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":136,"sourceHtmlUrl":137},"tests\u002Ftest_runner.py",6703,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fskill-comply\u002Ftests\u002Ftest_runner.py",[139,146,153,161,168,175],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":157,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]