[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CC0KQ3CGS6GD9M10P3RE92":3,"skill-same:01M6CC0KQ3CGS6GD9M10P3RE92":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6CC0KQ3CGS6GD9M10P3RE92","llm-artifacts-detection",null,"Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.","ray-manaloto\u002Fmacos-development-environment","ray-manaloto","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227192835?v=4","01M6CBR7J13ZA01X5YB1A1QRJP","01M6CBR7P0S3NS8ZV81JYNST14",1,"MIT","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30,31],"artifacts","detection","llm artifacts detection","coding agent","test","code","issues","dead code","coding","quality","common","generated","use","up","2026-11-10 10:12:30",false,"---\nname: llm-artifacts-detection\ndescription: Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.\n---\n\n# LLM Artifacts Detection\n\nDetect and flag common patterns introduced by LLM coding agents that reduce code quality.\n\n## Detection Categories\n\n| Category | Reference | Key Issues |\n|----------|-----------|------------|\n| Tests | [references\u002Ftests-criteria.md](references\u002Ftests-criteria.md) | DRY violations, library testing, mock boundaries |\n| Dead Code | [references\u002Fdead-code-criteria.md](references\u002Fdead-code-criteria.md) | Unused code, TODO\u002FFIXME, backwards compat cruft |\n| Abstraction | [references\u002Fabstraction-criteria.md](references\u002Fabstraction-criteria.md) | Over-abstraction, copy-paste drift, over-configuration |\n| Style | [references\u002Fstyle-criteria.md](references\u002Fstyle-criteria.md) | Obvious comments, defensive overkill, unnecessary types |\n\n## Agent Prompts\n\nUse these prompts to spawn focused detection agents:\n\n### Tests Agent\n\n```\nAnalyze the test files for LLM-introduced test quality issues:\n\n1. **DRY Violations**: Look for setup\u002Fteardown code repeated across multiple test functions instead of using fixtures or shared helpers. Flag patterns like:\n   - Identical object creation in multiple tests\n   - Repeated mock configurations\n   - Copy-pasted database setup\n\n2. **Library Testing**: Identify tests that validate standard library or framework behavior rather than application code. Signs:\n   - No imports from the application codebase\n   - Testing built-in functions or third-party library methods\n   - Assertions about stdlib behavior\n\n3. **Mock Boundaries**: Flag mocking that's too deep or too shallow:\n   - Too deep: Mocking internal implementation details, private methods\n   - Too shallow: Mocking at the wrong layer, missing integration points\n   - Wrong level: Unit test mocks in integration tests or vice versa\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Dead Code Agent\n\n```\nScan the codebase for dead code and cleanup opportunities:\n\n1. **Unused Code**: Find functions, classes, and variables with no references:\n   - Functions never called\n   - Classes never instantiated\n   - Module-level variables never read\n   - Unreachable code after returns\n\n2. **TODO\u002FFIXME Comments**: Flag all TODO, FIXME, HACK, XXX comments that indicate incomplete work\n\n3. **Backwards Compat Cruft**: Look for patterns suggesting removed features:\n   - Variables renamed with _unused, _old, _deprecated suffixes\n   - Re-exports only for backwards compatibility\n   - Comments like \"# removed\", \"# legacy\", \"# deprecated\"\n   - Empty functions\u002Fclasses kept \"for compatibility\"\n\n4. **Orphaned Tests**: Tests for code that no longer exists:\n   - Test files with no corresponding source\n   - Test functions testing deleted features\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Abstraction Agent\n\n```\nReview the codebase for over-engineering introduced by LLM agents:\n\n1. **Over-Abstraction**: Identify unnecessary abstraction layers:\n   - Wrapper classes that just delegate to one method\n   - Interfaces\u002Fprotocols with only one implementation\n   - Abstract base classes with single concrete class\n   - Factory functions that always return the same type\n\n2. **Copy-Paste Drift**: Find 3+ similar code blocks that should be parameterized:\n   - Nearly identical functions with minor variations\n   - Repeated patterns that could be a single function with parameters\n   - Similar class methods across multiple classes\n\n3. **Over-Configuration**: Flag configuration for non-configurable things:\n   - Feature flags that are never toggled\n   - Environment variables always set to one value\n   - Config options with no production variation\n   - Overly generic code for single use case\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Style Agent\n\n```\nCheck for verbose LLM-style patterns that reduce code clarity:\n\n1. **Obvious Comments**: Comments that restate what the code clearly does:\n   - \"# increment counter\" above counter += 1\n   - \"# return the result\" above return result\n   - Docstrings that repeat the function name\n\n2. **Over-Documentation**: Excessive documentation on trivial code:\n   - Full docstrings on simple getters\u002Fsetters\n   - Parameter descriptions for obvious args\n   - Return value docs for self-evident returns\n\n3. **Defensive Overkill**: Unnecessary defensive programming:\n   - try\u002Fexcept around code that cannot fail\n   - Null checks on values that can't be null\n   - Type checks after type hints guarantee the type\n   - Validation of already-validated inputs\n\n4. **Unnecessary Type Hints**: Type hints that add no value:\n   - Type hints on obvious literal assignments\n   - Redundant hints on variables immediately clear from context\n   - Over-annotated internal\u002Flocal variables\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n## Usage\n\n1. Load this skill when reviewing AI-generated code\n2. Spawn agents for specific detection categories as needed\n3. Use reference files for detailed criteria and examples\n4. Report issues in format: `[FILE:LINE] ISSUE_TITLE`\n\n## When to Apply\n\n- Cleaning up code written by AI coding agents\n- Post-generation code review\n- Reducing code bloat from iterative AI generation\n- Identifying patterns that reduce maintainability\n","# LLM Artifacts Detection\n\nDetect and flag common patterns introduced by LLM coding agents that reduce code quality.\n\n## Detection Categories\n\n| Category | Reference | Key Issues |\n|----------|-----------|------------|\n| Tests | [references\u002Ftests-criteria.md](references\u002Ftests-criteria.md) | DRY violations, library testing, mock boundaries |\n| Dead Code | [references\u002Fdead-code-criteria.md](references\u002Fdead-code-criteria.md) | Unused code, TODO\u002FFIXME, backwards compat cruft |\n| Abstraction | [references\u002Fabstraction-criteria.md](references\u002Fabstraction-criteria.md) | Over-abstraction, copy-paste drift, over-configuration |\n| Style | [references\u002Fstyle-criteria.md](references\u002Fstyle-criteria.md) | Obvious comments, defensive overkill, unnecessary types |\n\n## Agent Prompts\n\nUse these prompts to spawn focused detection agents:\n\n### Tests Agent\n\n```\nAnalyze the test files for LLM-introduced test quality issues:\n\n1. **DRY Violations**: Look for setup\u002Fteardown code repeated across multiple test functions instead of using fixtures or shared helpers. Flag patterns like:\n   - Identical object creation in multiple tests\n   - Repeated mock configurations\n   - Copy-pasted database setup\n\n2. **Library Testing**: Identify tests that validate standard library or framework behavior rather than application code. Signs:\n   - No imports from the application codebase\n   - Testing built-in functions or third-party library methods\n   - Assertions about stdlib behavior\n\n3. **Mock Boundaries**: Flag mocking that's too deep or too shallow:\n   - Too deep: Mocking internal implementation details, private methods\n   - Too shallow: Mocking at the wrong layer, missing integration points\n   - Wrong level: Unit test mocks in integration tests or vice versa\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Dead Code Agent\n\n```\nScan the codebase for dead code and cleanup opportunities:\n\n1. **Unused Code**: Find functions, classes, and variables with no references:\n   - Functions never called\n   - Classes never instantiated\n   - Module-level variables never read\n   - Unreachable code after returns\n\n2. **TODO\u002FFIXME Comments**: Flag all TODO, FIXME, HACK, XXX comments that indicate incomplete work\n\n3. **Backwards Compat Cruft**: Look for patterns suggesting removed features:\n   - Variables renamed with _unused, _old, _deprecated suffixes\n   - Re-exports only for backwards compatibility\n   - Comments like \"# removed\", \"# legacy\", \"# deprecated\"\n   - Empty functions\u002Fclasses kept \"for compatibility\"\n\n4. **Orphaned Tests**: Tests for code that no longer exists:\n   - Test files with no corresponding source\n   - Test functions testing deleted features\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Abstraction Agent\n\n```\nReview the codebase for over-engineering introduced by LLM agents:\n\n1. **Over-Abstraction**: Identify unnecessary abstraction layers:\n   - Wrapper classes that just delegate to one method\n   - Interfaces\u002Fprotocols with only one implementation\n   - Abstract base classes with single concrete class\n   - Factory functions that always return the same type\n\n2. **Copy-Paste Drift**: Find 3+ similar code blocks that should be parameterized:\n   - Nearly identical functions with minor variations\n   - Repeated patterns that could be a single function with parameters\n   - Similar class methods across multiple classes\n\n3. **Over-Configuration**: Flag configuration for non-configurable things:\n   - Feature flags that are never toggled\n   - Environment variables always set to one value\n   - Config options with no production variation\n   - Overly generic code for single use case\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n### Style Agent\n\n```\nCheck for verbose LLM-style patterns that reduce code clarity:\n\n1. **Obvious Comments**: Comments that restate what the code clearly does:\n   - \"# increment counter\" above counter += 1\n   - \"# return the result\" above return result\n   - Docstrings that repeat the function name\n\n2. **Over-Documentation**: Excessive documentation on trivial code:\n   - Full docstrings on simple getters\u002Fsetters\n   - Parameter descriptions for obvious args\n   - Return value docs for self-evident returns\n\n3. **Defensive Overkill**: Unnecessary defensive programming:\n   - try\u002Fexcept around code that cannot fail\n   - Null checks on values that can't be null\n   - Type checks after type hints guarantee the type\n   - Validation of already-validated inputs\n\n4. **Unnecessary Type Hints**: Type hints that add no value:\n   - Type hints on obvious literal assignments\n   - Redundant hints on variables immediately clear from context\n   - Over-annotated internal\u002Flocal variables\n\nFor each issue found, report: [FILE:LINE] ISSUE_TITLE\n```\n\n## Usage\n\n1. Load this skill when reviewing AI-generated code\n2. Spawn agents for specific detection categories as needed\n3. Use reference files for detailed criteria and examples\n4. Report issues in format: `[FILE:LINE] ISSUE_TITLE`\n\n## When to Apply\n\n- Cleaning up code written by AI coding agents\n- Post-generation code review\n- Reducing code bloat from iterative AI generation\n- Identifying patterns that reduce maintainability\n",{"name":5,"description":7},"main","716b17df3ef6719d88aeac180015008b7ddfff6f",".claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection",0,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment","https:\u002F\u002Fgithub.com\u002Fray-manaloto","2026-08-03 16:55:50",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add ray-manaloto\u002Fmacos-development-environment --skill llm-artifacts-detection",{"tool":50,"command":51},"bunx","bunx skills add ray-manaloto\u002Fmacos-development-environment --skill llm-artifacts-detection",{"tool":53,"command":54},"pnpm","pnpm dlx skills add ray-manaloto\u002Fmacos-development-environment --skill llm-artifacts-detection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002FSKILL.md",true,[58,64,68,72],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fabstraction-criteria.md","REFERENCE","参考文档",7717,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002Freferences\u002Fabstraction-criteria.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fdead-code-criteria.md",5450,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002Freferences\u002Fdead-code-criteria.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fstyle-criteria.md",6512,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002Freferences\u002Fstyle-criteria.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Ftests-criteria.md",5998,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Fllm-artifacts-detection\u002Freferences\u002Ftests-criteria.md",[77,98,116,134,153,167],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":32},"01M6CC8DXNJ39YWERYTWCGGCGG","next-workflow-step","Use this skill when the user wants to transition to the next workflow step, wrap up a session cleanly, prepare a handoff, or says things like \"next step\", \"continue the workflow\", \"wrap up\", \"hand off\", \"move to the next phase\", \"what's next in embrace\", or \"prepare for \u002Fclear\". Also triggers when the current octo:embrace phase appears complete and no explicit next action is set.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fworkflow-toolkit\u002Fskills\u002Fnext-workflow-step\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[89,90,31,30,91,92,93,94,95,96,97],"next workflow step","workflow","session","user","wrap up","continue","handoff","prepare","SET",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":32},"01M6CC8BRZBQHEBXGMKPDM422P","source-discovery","This skill should be used when the user asks to \"find sources\", \"discover URLs\", \"catalog a source\", \"classify a URL\", \"search for libraries\", \"check what exists\", or mentions source discovery, URL cataloging, source classification, or research source management.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fsource-discovery\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,92,114,115],"discovery","source discovery","research","libraries","search","classification","find","check","management","catalog","find sources",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":32},"01M6CC89CGJP69A0PS22G2H1FV","review-synthesis","This skill should be used when the user asks to \"summarize review findings\", \"prioritize fixes\", \"rank review issues\", \"combine reviewer feedback\", \"create action items from review\", or mentions review synthesis, finding prioritization, severity ranking, or review result summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Freview-synthesis\u002FSKILL.md",[],[123,124,125,126,127,128,129,92,130,131,132,24,133],"review","review synthesis","Synthesis","prioritize","create action","feedback","reviewer","summarize","prioritization","create","severity",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":143,"publishedAt":32},"01M6CC872EZ9GRJY0HRCG0RT2M","research-scoring","This skill should be used when the user asks to \"score research\", \"check research quality\", \"evaluate coverage\", \"measure improvement\", \"assess research completeness\", or mentions research scoring, quality metrics, coverage gaps, improvement baseline, or research pipeline status.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fresearch-scoring\u002FSKILL.md",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000021","资料检索与研究",[144,107,145,146,147,148,149,27,112,92,150,151,152],"research scoring","status","coverage gaps","metrics","pipeline","baseline","coverage","pipeline status","research quality",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":32},"01M6CC852HSDS1FE4EJAT0RHGR","notebooklm-integration","This skill should be used when the user asks to \"ingest into NotebookLM\", \"query NotebookLM\", \"add sources to notebook\", \"cross-source synthesis\", \"check stale sources\", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fnotebooklm-integration\u002FSKILL.md",[],[160,161,162,163,112,92,164,165,166,125],"notebooklm integration","notebooklm","integration","knowledge","ingestion","ingest","stale",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":174,"publishedAt":32},"01M6CC82Z4V3205KCJWQZPS2VG","evidence-synthesis","This skill should be used when the user asks to \"synthesize findings\", \"combine research\", \"cross-reference sources\", \"summarize evidence\", \"write a deep review\", or mentions evidence synthesis, finding consolidation, cross-source analysis, or research summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fevidence-synthesis\u002FSKILL.md",[173],{"categoryNo":141,"categoryName":142,"taxonomyType":86,"taxonomyTypeDesc":87},[175,125,176,130,107,177,178,179,92,180,123],"evidence synthesis","evidence","deep review","analysis","write","reference"]