[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEWGRW8ZFCEE67AN8AH54Y":3,"skill-same:01M6DEWGRW8ZFCEE67AN8AH54Y":49},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M6DEWGRW8ZFCEE67AN8AH54Y","source-command-evolve",null,"Analyze instincts and suggest or generate evolved structures","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsource-command-evolve\u002FSKILL.md",[],[19,20,21,22,23],"evolve","command","source command evolve","generate","analyze","2026-11-10 10:12:30",false,"---\nname: \"source-command-evolve\"\ndescription: \"Analyze instincts and suggest or generate evolved structures\"\n---\n\n# source-command-evolve\n\nUse this skill when the user asks to run the migrated source command `evolve`.\n\n## Command Template\n\n# Evolve Command\n\n## Implementation\n\nRun the instinct CLI using the plugin root path:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcontinuous-learning-v2\u002Fscripts\u002Finstinct-cli.py\" evolve [--generate]\n```\n\nOr if `CLAUDE_PLUGIN_ROOT` is not set (manual installation):\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fscripts\u002Finstinct-cli.py evolve [--generate]\n```\n\nAnalyzes instincts and clusters related ones into higher-level structures:\n- **Commands**: When instincts describe user-invoked actions\n- **Skills**: When instincts describe auto-triggered behaviors\n- **Agents**: When instincts describe complex, multi-step processes\n\n## Usage\n\n```\n\u002Fevolve                    # Analyze all instincts and suggest evolutions\n\u002Fevolve --generate         # Also generate files under evolved\u002F{skills,commands,agents}\n```\n\n## Evolution Rules\n\n### → Command (User-Invoked)\nWhen instincts describe actions a user would explicitly request:\n- Multiple instincts about \"when user asks to...\"\n- Instincts with triggers like \"when creating a new X\"\n- Instincts that follow a repeatable sequence\n\nExample:\n- `new-table-step1`: \"when adding a database table, create migration\"\n- `new-table-step2`: \"when adding a database table, update schema\"\n- `new-table-step3`: \"when adding a database table, regenerate types\"\n\n→ Creates: **new-table** command\n\n### → Skill (Auto-Triggered)\nWhen instincts describe behaviors that should happen automatically:\n- Pattern-matching triggers\n- Error handling responses\n- Code style enforcement\n\nExample:\n- `prefer-functional`: \"when writing functions, prefer functional style\"\n- `use-immutable`: \"when modifying state, use immutable patterns\"\n- `avoid-classes`: \"when designing modules, avoid class-based design\"\n\n→ Creates: `functional-patterns` skill\n\n### → Agent (Needs Depth\u002FIsolation)\nWhen instincts describe complex, multi-step processes that benefit from isolation:\n- Debugging workflows\n- Refactoring sequences\n- Research tasks\n\nExample:\n- `debug-step1`: \"when debugging, first check logs\"\n- `debug-step2`: \"when debugging, isolate the failing component\"\n- `debug-step3`: \"when debugging, create minimal reproduction\"\n- `debug-step4`: \"when debugging, verify fix with test\"\n\n→ Creates: **debugger** agent\n\n## What to Do\n\n1. Detect current project context\n2. Read project + global instincts (project takes precedence on ID conflicts)\n3. Group instincts by trigger\u002Fdomain patterns\n4. Identify:\n   - Skill candidates (trigger clusters with 2+ instincts)\n   - Command candidates (high-confidence workflow instincts)\n   - Agent candidates (larger, high-confidence clusters)\n5. Show promotion candidates (project -> global) when applicable\n6. If `--generate` is passed, write files to:\n   - Project scope: `~\u002F.claude\u002Fhomunculus\u002Fprojects\u002F\u003Cproject-id>\u002Fevolved\u002F`\n   - Global fallback: `~\u002F.claude\u002Fhomunculus\u002Fevolved\u002F`\n\n## Output Format\n\n```\n============================================================\n  EVOLVE ANALYSIS - 12 instincts\n  Project: my-app (a1b2c3d4e5f6)\n  Project-scoped: 8 | Global: 4\n============================================================\n\nHigh confidence instincts (>=80%): 5\n\n## SKILL CANDIDATES\n1. Cluster: \"adding tests\"\n   Instincts: 3\n   Avg confidence: 82%\n   Domains: testing\n   Scopes: project\n\n## COMMAND CANDIDATES (2)\n  \u002Fadding-tests\n    From: test-first-workflow [project]\n    Confidence: 84%\n\n## AGENT CANDIDATES (1)\n  adding-tests-agent\n    Covers 3 instincts\n    Avg confidence: 82%\n```\n\n## Flags\n\n- `--generate`: Generate evolved files in addition to analysis output\n\n## Generated File Format\n\n### Command\n```markdown\n---\nname: new-table\ndescription: Create a new database table with migration, schema update, and type generation\ncommand: \u002Fnew-table\nevolved_from:\n  - new-table-migration\n  - update-schema\n  - regenerate-types\n---\n\n# New Table Command\n\n[Generated content based on clustered instincts]\n\n## Steps\n1. ...\n2. ...\n```\n\n### Skill\n```markdown\n---\nname: functional-patterns\ndescription: Enforce functional programming patterns\nevolved_from:\n  - prefer-functional\n  - use-immutable\n  - avoid-classes\n---\n\n# Functional Patterns Skill\n\n[Generated content based on clustered instincts]\n```\n\n### Agent\n```markdown\n---\nname: debugger\ndescription: Systematic debugging agent\nmodel: sonnet\nevolved_from:\n  - debug-check-logs\n  - debug-isolate\n  - debug-reproduce\n---\n\n# Debugger Agent\n\n[Generated content based on clustered instincts]\n```\n","# source-command-evolve\n\nUse this skill when the user asks to run the migrated source command `evolve`.\n\n## Command Template\n\n# Evolve Command\n\n## Implementation\n\nRun the instinct CLI using the plugin root path:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcontinuous-learning-v2\u002Fscripts\u002Finstinct-cli.py\" evolve [--generate]\n```\n\nOr if `CLAUDE_PLUGIN_ROOT` is not set (manual installation):\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fscripts\u002Finstinct-cli.py evolve [--generate]\n```\n\nAnalyzes instincts and clusters related ones into higher-level structures:\n- **Commands**: When instincts describe user-invoked actions\n- **Skills**: When instincts describe auto-triggered behaviors\n- **Agents**: When instincts describe complex, multi-step processes\n\n## Usage\n\n```\n\u002Fevolve                    # Analyze all instincts and suggest evolutions\n\u002Fevolve --generate         # Also generate files under evolved\u002F{skills,commands,agents}\n```\n\n## Evolution Rules\n\n### → Command (User-Invoked)\nWhen instincts describe actions a user would explicitly request:\n- Multiple instincts about \"when user asks to...\"\n- Instincts with triggers like \"when creating a new X\"\n- Instincts that follow a repeatable sequence\n\nExample:\n- `new-table-step1`: \"when adding a database table, create migration\"\n- `new-table-step2`: \"when adding a database table, update schema\"\n- `new-table-step3`: \"when adding a database table, regenerate types\"\n\n→ Creates: **new-table** command\n\n### → Skill (Auto-Triggered)\nWhen instincts describe behaviors that should happen automatically:\n- Pattern-matching triggers\n- Error handling responses\n- Code style enforcement\n\nExample:\n- `prefer-functional`: \"when writing functions, prefer functional style\"\n- `use-immutable`: \"when modifying state, use immutable patterns\"\n- `avoid-classes`: \"when designing modules, avoid class-based design\"\n\n→ Creates: `functional-patterns` skill\n\n### → Agent (Needs Depth\u002FIsolation)\nWhen instincts describe complex, multi-step processes that benefit from isolation:\n- Debugging workflows\n- Refactoring sequences\n- Research tasks\n\nExample:\n- `debug-step1`: \"when debugging, first check logs\"\n- `debug-step2`: \"when debugging, isolate the failing component\"\n- `debug-step3`: \"when debugging, create minimal reproduction\"\n- `debug-step4`: \"when debugging, verify fix with test\"\n\n→ Creates: **debugger** agent\n\n## What to Do\n\n1. Detect current project context\n2. Read project + global instincts (project takes precedence on ID conflicts)\n3. Group instincts by trigger\u002Fdomain patterns\n4. Identify:\n   - Skill candidates (trigger clusters with 2+ instincts)\n   - Command candidates (high-confidence workflow instincts)\n   - Agent candidates (larger, high-confidence clusters)\n5. Show promotion candidates (project -> global) when applicable\n6. If `--generate` is passed, write files to:\n   - Project scope: `~\u002F.claude\u002Fhomunculus\u002Fprojects\u002F\u003Cproject-id>\u002Fevolved\u002F`\n   - Global fallback: `~\u002F.claude\u002Fhomunculus\u002Fevolved\u002F`\n\n## Output Format\n\n```\n============================================================\n  EVOLVE ANALYSIS - 12 instincts\n  Project: my-app (a1b2c3d4e5f6)\n  Project-scoped: 8 | Global: 4\n============================================================\n\nHigh confidence instincts (>=80%): 5\n\n## SKILL CANDIDATES\n1. Cluster: \"adding tests\"\n   Instincts: 3\n   Avg confidence: 82%\n   Domains: testing\n   Scopes: project\n\n## COMMAND CANDIDATES (2)\n  \u002Fadding-tests\n    From: test-first-workflow [project]\n    Confidence: 84%\n\n## AGENT CANDIDATES (1)\n  adding-tests-agent\n    Covers 3 instincts\n    Avg confidence: 82%\n```\n\n## Flags\n\n- `--generate`: Generate evolved files in addition to analysis output\n\n## Generated File Format\n\n### Command\n```markdown\n---\nname: new-table\ndescription: Create a new database table with migration, schema update, and type generation\ncommand: \u002Fnew-table\nevolved_from:\n  - new-table-migration\n  - update-schema\n  - regenerate-types\n---\n\n# New Table Command\n\n[Generated content based on clustered instincts]\n\n## Steps\n1. ...\n2. ...\n```\n\n### Skill\n```markdown\n---\nname: functional-patterns\ndescription: Enforce functional programming patterns\nevolved_from:\n  - prefer-functional\n  - use-immutable\n  - avoid-classes\n---\n\n# Functional Patterns Skill\n\n[Generated content based on clustered instincts]\n```\n\n### Agent\n```markdown\n---\nname: debugger\ndescription: Systematic debugging agent\nmodel: sonnet\nevolved_from:\n  - debug-check-logs\n  - debug-isolate\n  - debug-reproduce\n---\n\n# Debugger Agent\n\n[Generated content based on clustered instincts]\n```\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fsource-command-evolve","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-evolve",{"tool":41,"command":42},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-evolve",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-evolve","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsource-command-evolve\u002FSKILL.md",true,[],[50,72,102,129,143,159],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":24},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[57,58,59,60,61,62,63,64,65,66,67,68,69,70,71],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":83,"publishedAt":24},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[84,85,86,87,88,23,89,90,91,92,93,94,95,96,66,97,98,99,100,101],"openmm md","how","decision","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":114,"publishedAt":24},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[108,111],{"categoryNo":109,"categoryName":110,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":112,"categoryName":113,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000008","测试与质量",[115,116,117,118,119,120,121,122,123,124,85,125,126,127,128],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":24},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[131,136,137,138,139,140,141,142],"setup","report","project","installation","project setup","issues","state",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":150,"publishedAt":24},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[149],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[145,151,62,152,153,154,66,155,156,157,158],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":160,"name":136,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":24},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[136,138,99,165,140,166],"files","interactive"]