[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P5EJY76F2ASFM1FYP7WNED":3,"skill-same:01M6P5EJY76F2ASFM1FYP7WNED":101},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":80,"commitSha":81,"skillDirectory":82,"forksCount":83,"repositoryHtmlUrl":84,"repositoryHomepageUrl":6,"ownerHtmlUrl":85,"ownerBlogUrl":86,"ownerDescription":6,"updatedAt":87,"install":88,"resources":100},"01M6P5EJY76F2ASFM1FYP7WNED","tldr-code-analysis",null,"5-layer code analysis (AST, Call Graph, CFG, DFG, PDG) that yields 95% token savings over raw file reads. Use when: 'systematically understand an unfamiliar codebase', 'analyze code structure with minimal tokens', 'map call graphs and data flow', 'find dead code and architectural layers', 'trace variable definitions across files'.","DojoGenesis\u002Fgateway","DojoGenesis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273886418?v=4","01M6P54RXMD3TZ2082Z3Z4JMQP","Cruz Morales (TresPies)","01M6P54S269YR0ZZZ96WGQM439",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fcontinuous-learning\u002Fskills\u002Ftldr-code-analysis\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"code","tldr code analysis","tldr code","code analysis","tldr","analysis","analyze","ast","call graph","only","files","structure","map","across","deep","false","l2","data flow","CFG","directory","2026-11-10 10:12:30",false,"---\nname: tldr-code-analysis\nmodel: opus\ndescription: \"5-layer code analysis (AST, Call Graph, CFG, DFG, PDG) that yields 95% token savings over raw file reads. Use when: 'systematically understand an unfamiliar codebase', 'analyze code structure with minimal tokens', 'map call graphs and data flow', 'find dead code and architectural layers', 'trace variable definitions across files'.\"\ncategory: continuous-learning\ntriggers:\n  - \"systematically understand an unfamiliar codebase\"\n  - \"analyze code structure with minimal tokens\"\n  - \"map call graphs and data flow\"\n  - \"find dead code and architectural layers\"\n  - \"trace variable definitions across files\"\ntier: 1\nagents:\n  - \"primary\"\ntool_dependencies:\n  - \"file_system\"\n\ninputs:\n  - name: repo_path\n    type: string\n    description: Path to the repository or directory to analyze\n    required: true\n  - name: analysis_depth\n    type: string\n    description: \"Depth of analysis: 'overview' (L1-L2 only), 'deep' (L1-L4), or 'full' (all 5 layers including PDG)\"\n    required: false\noutputs:\n  - name: analysis_report\n    type: ref\n    format: cas-ref\n    description: Structured analysis report covering requested layers with token-efficient code summaries\n---\n# TLDR Code Analysis\n\n**Purpose:** Systematically analyze unfamiliar codebases using a 5-layer analysis stack that reduces token consumption by 95% compared to raw file reads, while surfacing architecture, call graphs, control flow, data flow, and program dependencies.\n\n---\n\n## I. When to Use\n\n- Onboarding to an unfamiliar codebase and need structural understanding fast\n- Preparing for a refactor by mapping cross-file call graphs and data flow\n- Hunting a bug that spans multiple files and need to trace variable definitions\n- Auditing code quality: dead code detection, cyclomatic complexity, architectural layers\n- Any codebase exploration where reading raw files would blow the context budget\n\n---\n\n## II. The 5-Layer Stack\n\n```\nLayer 1: AST         ~500 tokens   Function signatures, imports, class outlines\nLayer 2: Call Graph  +440 tokens   What calls what (cross-file edges)\nLayer 3: CFG         +110 tokens   Cyclomatic complexity, branches, loops\nLayer 4: DFG         +130 tokens   Variable definitions, reads, modifications\nLayer 5: PDG         +150 tokens   Program dependencies, slicing\n---------------------------------------------------------------------------\nTotal:              ~1,200 tokens  vs 23,000 raw = 95% savings\n```\n\n### Depth Modes\n\n| Mode | Layers | Token Budget | Best For |\n|------|--------|-------------|----------|\n| overview | L1-L2 | ~940 tokens | Quick orientation, \"what does this repo do?\" |\n| deep | L1-L4 | ~1,180 tokens | Refactor prep, bug tracing |\n| full | L1-L5 | ~1,330 tokens | Full program slicing, dependency analysis |\n\n---\n\n## III. Workflow\n\n### Step 1: Structural Scan (Layer 1 - AST)\n\nExtract file tree, function signatures, imports, and class outlines.\n\n```bash\ntldr tree [repo_path]\ntldr structure [repo_path] --lang [detected_language]\ntldr imports [key_file]\n```\n\nProduces a codemap: the skeleton of every file without reading bodies.\n\n### Step 2: Call Graph Construction (Layer 2)\n\nBuild cross-file call graph to understand what calls what.\n\n```bash\ntldr calls [repo_path]\ntldr impact [function_name] [repo_path]    # Reverse: who calls this?\ntldr importers [module_name] [repo_path]   # Reverse import lookup\n```\n\nThis layer reveals the actual dependency structure that import lists alone miss.\n\n### Step 3: Control Flow Analysis (Layer 3 - CFG)\n\nFor functions of interest, analyze branching complexity.\n\n```bash\ntldr cfg [file] [function]\n# Returns: cyclomatic complexity, block count, branch points, loop nesting\n```\n\nSkip this layer for overview depth. Use it when refactoring or assessing complexity.\n\n### Step 4: Data Flow Analysis (Layer 4 - DFG)\n\nTrack where variables are defined, read, and modified.\n\n```bash\ntldr dfg [file] [function]\n# Returns: definition sites, use sites, modification chains\n```\n\nCritical for bug tracing: \"where does this value come from and where does it go?\"\n\n### Step 5: Program Dependency Graph (Layer 5 - PDG)\n\nFull dependency analysis and program slicing.\n\n```bash\ntldr slice [file] [function] [line_number]\ntldr slice [file] [function] [line] --direction forward\ntldr slice [file] [function] [line] --var [variable_name]\n```\n\nAnswers: \"what code affects line X?\" and \"what does line X affect?\" Use for surgical changes where you need to know the full blast radius.\n\n### Step 6: Synthesis\n\nCombine layer outputs into a structured analysis report:\n1. Architecture overview (entry points, layers, circular deps)\n2. Hot paths (most-called functions, highest complexity)\n3. Risk areas (dead code, high cyclomatic complexity, deep nesting)\n4. Actionable findings (specific files and functions to investigate)\n\n```bash\ntldr arch [repo_path]    # Architectural layer detection\ntldr dead [repo_path]    # Dead\u002Funreachable code\n```\n\n---\n\n## IV. Language Support\n\n| Language | AST | Call Graph | CFG | DFG | PDG |\n|----------|-----|------------|-----|-----|-----|\n| Python | Yes | Yes | Yes | Yes | Yes |\n| TypeScript | Yes | Yes | Yes | Yes | Yes |\n| JavaScript | Yes | Yes | Yes | Yes | Yes |\n| Go | Yes | Yes | Yes | Yes | Yes |\n| Rust | Yes | Yes | Yes | Yes | Yes |\n| Java | Yes | Yes | - | - | - |\n| C\u002FC++ | Yes | Yes | - | - | - |\n\n---\n\n## V. Output\n\n- A structured analysis report saved to the project directory\n- Sections: Architecture Map, Call Graph Summary, Complexity Hotspots, Data Flow Findings, Dead Code Report, Actionable Recommendations\n- Token budget: ~1,200 tokens for full 5-layer analysis vs ~23,000 for raw reads\n\n---\n\n## VI. Examples\n\n**Scenario 1:** \"Help me understand this Go microservice repo\" with depth=overview --> AST scan (52 files, 340 functions), call graph (entry points: main->server->handlers, 3 architectural layers detected), report in ~940 tokens identifying 4 handler packages and the dependency flow between them.\n\n**Scenario 2:** \"Trace why user_id is None at line 87 in processor.py\" with depth=full --> DFG traces variable from 3 definition sites, PDG slice reveals that one branch path skips assignment, call graph shows 2 callers that trigger the None path. Fix: add guard clause at line 71.\n\n**Scenario 3:** \"Audit this TypeScript monorepo before refactoring\" with depth=deep --> AST finds 1,200 exports across 89 files, call graph reveals 47 are never imported (dead exports), CFG flags 3 functions with cyclomatic complexity >15, DFG finds 2 variables shadowed across module boundaries.\n\n---\n\n## VII. Edge Cases\n\n- Repository uses multiple languages: run AST scan per language, then merge call graphs at the FFI\u002FAPI boundary layer\n- Very large monorepo (10,000+ files): use `--max` flag to cap file count per scan; analyze by package\u002Fdirectory rather than whole repo\n- Language not in full support table (Java, C++): L1-L2 analysis only; note the limitation in the report and recommend manual inspection for flow analysis\n- No entry point discoverable: use `tldr dead` with explicit entry point hints (`--entry main cli test_`)\n\n---\n\n## VIII. Anti-Patterns\n\n- Reading raw files first and then running TLDR -- the whole point is to avoid reading raw files; navigate with TLDR, then read only the 2-4 files that matter\n- Running full depth on every file -- use overview to find the interesting files, then deep\u002Ffull on those specific files\n- Treating TLDR output as the final answer for bug fixes -- TLDR navigates to the right code, but you still need to read the actual implementation to write the fix\n- Skipping the call graph (L2) and jumping to CFG\u002FDFG -- without knowing what calls what, flow analysis on individual functions misses cross-file interactions\n","# TLDR Code Analysis\n\n**Purpose:** Systematically analyze unfamiliar codebases using a 5-layer analysis stack that reduces token consumption by 95% compared to raw file reads, while surfacing architecture, call graphs, control flow, data flow, and program dependencies.\n\n---\n\n## I. When to Use\n\n- Onboarding to an unfamiliar codebase and need structural understanding fast\n- Preparing for a refactor by mapping cross-file call graphs and data flow\n- Hunting a bug that spans multiple files and need to trace variable definitions\n- Auditing code quality: dead code detection, cyclomatic complexity, architectural layers\n- Any codebase exploration where reading raw files would blow the context budget\n\n---\n\n## II. The 5-Layer Stack\n\n```\nLayer 1: AST         ~500 tokens   Function signatures, imports, class outlines\nLayer 2: Call Graph  +440 tokens   What calls what (cross-file edges)\nLayer 3: CFG         +110 tokens   Cyclomatic complexity, branches, loops\nLayer 4: DFG         +130 tokens   Variable definitions, reads, modifications\nLayer 5: PDG         +150 tokens   Program dependencies, slicing\n---------------------------------------------------------------------------\nTotal:              ~1,200 tokens  vs 23,000 raw = 95% savings\n```\n\n### Depth Modes\n\n| Mode | Layers | Token Budget | Best For |\n|------|--------|-------------|----------|\n| overview | L1-L2 | ~940 tokens | Quick orientation, \"what does this repo do?\" |\n| deep | L1-L4 | ~1,180 tokens | Refactor prep, bug tracing |\n| full | L1-L5 | ~1,330 tokens | Full program slicing, dependency analysis |\n\n---\n\n## III. Workflow\n\n### Step 1: Structural Scan (Layer 1 - AST)\n\nExtract file tree, function signatures, imports, and class outlines.\n\n```bash\ntldr tree [repo_path]\ntldr structure [repo_path] --lang [detected_language]\ntldr imports [key_file]\n```\n\nProduces a codemap: the skeleton of every file without reading bodies.\n\n### Step 2: Call Graph Construction (Layer 2)\n\nBuild cross-file call graph to understand what calls what.\n\n```bash\ntldr calls [repo_path]\ntldr impact [function_name] [repo_path]    # Reverse: who calls this?\ntldr importers [module_name] [repo_path]   # Reverse import lookup\n```\n\nThis layer reveals the actual dependency structure that import lists alone miss.\n\n### Step 3: Control Flow Analysis (Layer 3 - CFG)\n\nFor functions of interest, analyze branching complexity.\n\n```bash\ntldr cfg [file] [function]\n# Returns: cyclomatic complexity, block count, branch points, loop nesting\n```\n\nSkip this layer for overview depth. Use it when refactoring or assessing complexity.\n\n### Step 4: Data Flow Analysis (Layer 4 - DFG)\n\nTrack where variables are defined, read, and modified.\n\n```bash\ntldr dfg [file] [function]\n# Returns: definition sites, use sites, modification chains\n```\n\nCritical for bug tracing: \"where does this value come from and where does it go?\"\n\n### Step 5: Program Dependency Graph (Layer 5 - PDG)\n\nFull dependency analysis and program slicing.\n\n```bash\ntldr slice [file] [function] [line_number]\ntldr slice [file] [function] [line] --direction forward\ntldr slice [file] [function] [line] --var [variable_name]\n```\n\nAnswers: \"what code affects line X?\" and \"what does line X affect?\" Use for surgical changes where you need to know the full blast radius.\n\n### Step 6: Synthesis\n\nCombine layer outputs into a structured analysis report:\n1. Architecture overview (entry points, layers, circular deps)\n2. Hot paths (most-called functions, highest complexity)\n3. Risk areas (dead code, high cyclomatic complexity, deep nesting)\n4. Actionable findings (specific files and functions to investigate)\n\n```bash\ntldr arch [repo_path]    # Architectural layer detection\ntldr dead [repo_path]    # Dead\u002Funreachable code\n```\n\n---\n\n## IV. Language Support\n\n| Language | AST | Call Graph | CFG | DFG | PDG |\n|----------|-----|------------|-----|-----|-----|\n| Python | Yes | Yes | Yes | Yes | Yes |\n| TypeScript | Yes | Yes | Yes | Yes | Yes |\n| JavaScript | Yes | Yes | Yes | Yes | Yes |\n| Go | Yes | Yes | Yes | Yes | Yes |\n| Rust | Yes | Yes | Yes | Yes | Yes |\n| Java | Yes | Yes | - | - | - |\n| C\u002FC++ | Yes | Yes | - | - | - |\n\n---\n\n## V. Output\n\n- A structured analysis report saved to the project directory\n- Sections: Architecture Map, Call Graph Summary, Complexity Hotspots, Data Flow Findings, Dead Code Report, Actionable Recommendations\n- Token budget: ~1,200 tokens for full 5-layer analysis vs ~23,000 for raw reads\n\n---\n\n## VI. Examples\n\n**Scenario 1:** \"Help me understand this Go microservice repo\" with depth=overview --> AST scan (52 files, 340 functions), call graph (entry points: main->server->handlers, 3 architectural layers detected), report in ~940 tokens identifying 4 handler packages and the dependency flow between them.\n\n**Scenario 2:** \"Trace why user_id is None at line 87 in processor.py\" with depth=full --> DFG traces variable from 3 definition sites, PDG slice reveals that one branch path skips assignment, call graph shows 2 callers that trigger the None path. Fix: add guard clause at line 71.\n\n**Scenario 3:** \"Audit this TypeScript monorepo before refactoring\" with depth=deep --> AST finds 1,200 exports across 89 files, call graph reveals 47 are never imported (dead exports), CFG flags 3 functions with cyclomatic complexity >15, DFG finds 2 variables shadowed across module boundaries.\n\n---\n\n## VII. Edge Cases\n\n- Repository uses multiple languages: run AST scan per language, then merge call graphs at the FFI\u002FAPI boundary layer\n- Very large monorepo (10,000+ files): use `--max` flag to cap file count per scan; analyze by package\u002Fdirectory rather than whole repo\n- Language not in full support table (Java, C++): L1-L2 analysis only; note the limitation in the report and recommend manual inspection for flow analysis\n- No entry point discoverable: use `tldr dead` with explicit entry point hints (`--entry main cli test_`)\n\n---\n\n## VIII. Anti-Patterns\n\n- Reading raw files first and then running TLDR -- the whole point is to avoid reading raw files; navigate with TLDR, then read only the 2-4 files that matter\n- Running full depth on every file -- use overview to find the interesting files, then deep\u002Ffull on those specific files\n- Treating TLDR output as the final answer for bug fixes -- TLDR navigates to the right code, but you still need to read the actual implementation to write the fix\n- Skipping the call graph (L2) and jumping to CFG\u002FDFG -- without knowing what calls what, flow analysis on individual functions misses cross-file interactions\n",{"name":5,"tier":52,"model":53,"agents":54,"inputs":56,"outputs":65,"category":71,"triggers":72,"description":7,"tool_dependencies":78},1,"opus",[55],"primary",[57,62],{"name":58,"type":59,"required":60,"description":61},"repo_path","string",true,"Path to the repository or directory to analyze",{"name":63,"type":59,"required":48,"description":64},"analysis_depth","Depth of analysis: 'overview' (L1-L2 only), 'deep' (L1-L4), or 'full' (all 5 layers including PDG)",[66],{"name":67,"type":68,"format":69,"description":70},"analysis_report","ref","cas-ref","Structured analysis report covering requested layers with token-efficient code summaries","continuous-learning",[73,74,75,76,77],"systematically understand an unfamiliar codebase","analyze code structure with minimal tokens","map call graphs and data flow","find dead code and architectural layers","trace variable definitions across files",[79],"file_system","main","ff07df5fd8f75762c2a131e6e26d297e8ae403ee","plugins\u002Fcontinuous-learning\u002Fskills\u002Ftldr-code-analysis",0,"https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway","https:\u002F\u002Fgithub.com\u002FDojoGenesis","dojogenesis.com","2026-10-25 22:59:58",{"source":8,"skillName":5,"commands":89,"prompt":99,"zipAvailable":60},[90,93,96],{"tool":91,"command":92},"npx","npx skills add DojoGenesis\u002Fgateway --skill tldr-code-analysis",{"tool":94,"command":95},"bunx","bunx skills add DojoGenesis\u002Fgateway --skill tldr-code-analysis",{"tool":97,"command":98},"pnpm","pnpm dlx skills add DojoGenesis\u002Fgateway --skill tldr-code-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fcontinuous-learning\u002Fskills\u002Ftldr-code-analysis\u002FSKILL.md",[],[102,123,136,144,181,206],{"skillNo":103,"name":104,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":112,"publishedAt":47},"01M6P6J0WYSD1MTGA3ZX6MGGZ5","kata-test-echo","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-test-echo\u002FSKILL.md",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[113,114,115,116,117,118,119,120,121,122],"kata test echo","Echo","test","json","v1","output","input","structured","contracts","schema",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":47},"01M6P6HQJNGG4WPZW0DEWMAY2N","kata-plain","An ordinary prose skill; not dispatchable.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-plain\u002FSKILL.md",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000023","Skill与智能体开发",[133,134,135],"kata plain","prose skill","prose",{"skillNo":137,"name":138,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":47},"01M6P6HH6Y7K8K6606MF7VZ1HB","kata-broken","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-broken\u002FSKILL.md",[],[142,143,120,121,114,122,116,115,119,117,118],"kata broken","broken",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":162,"publishedAt":47},"01M6P6GW520QJ03A6K7Y5PWJ52","voice-before-structure","Read the project's design language and philosophy before writing structural artifacts. Ground manifests, READMEs, and descriptions in the project's voice, not boilerplate. Use when creating manifests or READMEs for established projects, writing ecosystem-level documentation, building plugin descriptions or marketplace metadata, or authoring metadata that carries a project's identity. Trigger phrases: 'write the manifest', 'create a README', 'describe this plugin', 'ground yourself in the philosophy', 'ecosystem-level work'.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fvoice-before-structure\u002FSKILL.md",[150,153,156,159],{"categoryNo":151,"categoryName":152,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":154,"categoryName":155,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",{"categoryNo":160,"categoryName":161,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[163,38,164,165,166,42,167,168,169,170,171,172,173,174,175,176,177,178,179,180],"voice before structure","voice","manifests","ecosystem","authoring","structural","project","artifact","philosophy","design","writing","identity","documentation","create","projects","work","read","write",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":47},"01M6P6GMNA4HJ4D5RRM3BQZ73M","system-prompt-archaeology","Produces a named ADA disposition preset (YAML) and a layered behavioral analysis (structural decomposition + evidence-cited classifications) from a system prompt. Use when: \"analyze this system prompt\", \"extract disposition from prompt\", \"reverse-engineer agent behavior\", \"what patterns does this prompt use\", \"build a preset from this prompt\".","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsystem-prompt-archaeology\u002FSKILL.md",[187],{"categoryNo":130,"categoryName":131,"taxonomyType":110,"taxonomyTypeDesc":111},[189,190,191,192,193,194,168,195,196,197,198,199,200,201,33,32,202,203,204,205],"system prompt archaeology","system prompt","prompt","system","behavioral","classify","decomposition","wisdom","patterns","engineer","decompose","evidence","ada","STRING","sonnet","true","reverse",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":47},"01M6P6G2D70T9R00HX6K154X5Y","session-lifecycle-automation","Designs and configures all three loops of solo-operator session automation — session bookends, background maintenance agents, and a delegation flywheel. Use when setting up a new workspace, recovering from the 44% zero-artifact session leak, or preparing to scale delegation across multiple concurrent agents.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsession-lifecycle-automation\u002FSKILL.md",[212],{"categoryNo":130,"categoryName":131,"taxonomyType":110,"taxonomyTypeDesc":111},[214,215,216,217,218,219,220,46,221,222,223,224,37,170,225,40,226,227,228,229],"automation","session lifecycle automation","session lifecycle","lifecycle","session","markdown","configure","config","delegation","audit","SET","solo","scheduled","loops","up","template"]