[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DB0VDENHZPYXGW8WNFPNDF":3,"skill-same:01M6DB0VDENHZPYXGW8WNFPNDF":67},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M6DB0VDENHZPYXGW8WNFPNDF","agent-sort",null,"Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.","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\u002F.agents\u002Fskills\u002Fagent-sort\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"agent sort","evidence","bundle","full","commands","project","build","daily","hooks","review","use","install","repo","Rules","parallel","plan","library","2026-11-10 10:12:30",false,"---\nname: agent-sort\ndescription: Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.\norigin: ECC\n---\n\n# Agent Sort\n\nUse this skill when a repo needs a project-specific ECC surface instead of the default full install.\n\nThe goal is not to guess what \"feels useful.\" The goal is to classify ECC components with evidence from the actual codebase.\n\n## When to Use\n\n- A project only needs a subset of ECC and full installs are too noisy\n- The repo stack is clear, but nobody wants to hand-curate skills one by one\n- A team wants a repeatable install decision backed by grep evidence instead of opinion\n- You need to separate always-loaded daily workflow surfaces from searchable library\u002Freference surfaces\n- A repo has drifted into the wrong language, rule, or hook set and needs cleanup\n\n## Non-Negotiable Rules\n\n- Use the current repository as the source of truth, not generic preferences\n- Every DAILY decision must cite concrete repo evidence\n- LIBRARY does not mean \"delete\"; it means \"keep accessible without loading by default\"\n- Do not install hooks, rules, or scripts that the current repo cannot use\n- Prefer ECC-native surfaces; do not introduce a second install system\n\n## Outputs\n\nProduce these artifacts in order:\n\n1. DAILY inventory\n2. LIBRARY inventory\n3. install plan\n4. verification report\n5. optional `skill-library` router if the project wants one\n\n## Classification Model\n\nUse two buckets only:\n\n- `DAILY`\n  - should load every session for this repo\n  - strongly matched to the repo's language, framework, workflow, or operator surface\n- `LIBRARY`\n  - useful to retain, but not worth loading by default\n  - should remain reachable through search, router skill, or selective manual use\n\n## Evidence Sources\n\nUse repo-local evidence before making any classification:\n\n- file extensions\n- package managers and lockfiles\n- framework configs\n- CI and hook configs\n- build\u002Ftest scripts\n- imports and dependency manifests\n- repo docs that explicitly describe the stack\n\nUseful commands include:\n\n```bash\nrg --files\nrg -n \"typescript|react|next|supabase|django|spring|flutter|swift\"\ncat package.json\ncat pyproject.toml\ncat Cargo.toml\ncat pubspec.yaml\ncat go.mod\n```\n\n## Parallel Review Passes\n\nIf parallel subagents are available, split the review into these passes:\n\n1. Agents\n   - classify `agents\u002F*`\n2. Skills\n   - classify `skills\u002F*`\n3. Commands\n   - classify `commands\u002F*`\n4. Rules\n   - classify `rules\u002F*`\n5. Hooks and scripts\n   - classify hook surfaces, MCP health checks, helper scripts, and OS compatibility\n6. Extras\n   - classify contexts, examples, MCP configs, templates, and guidance docs\n\nIf subagents are not available, run the same passes sequentially.\n\n## Core Workflow\n\n### 1. Read the repo\n\nEstablish the real stack before classifying anything:\n\n- languages in use\n- frameworks in use\n- primary package manager\n- test stack\n- lint\u002Fformat stack\n- deployment\u002Fruntime surface\n- operator integrations already present\n\n### 2. Build the evidence table\n\nFor every candidate surface, record:\n\n- component path\n- component type\n- proposed bucket\n- repo evidence\n- short justification\n\nUse this format:\n\n```text\nskills\u002Ffrontend-patterns | skill | DAILY | 84 .tsx files, next.config.ts present | core frontend stack\nskills\u002Fdjango-patterns   | skill | LIBRARY | no .py files, no pyproject.toml       | not active in this repo\nrules\u002Ftypescript\u002F*       | rules | DAILY | package.json + tsconfig.json            | active TS repo\nrules\u002Fpython\u002F*           | rules | LIBRARY | zero Python source files             | keep accessible only\n```\n\n### 3. Decide DAILY vs LIBRARY\n\nPromote to `DAILY` when:\n\n- the repo clearly uses the matching stack\n- the component is general enough to help every session\n- the repo already depends on the corresponding runtime or workflow\n\nDemote to `LIBRARY` when:\n\n- the component is off-stack\n- the repo might need it later, but not every day\n- it adds context overhead without immediate relevance\n\n### 4. Build the install plan\n\nTranslate the classification into action:\n\n- DAILY skills -> install or keep in `.claude\u002Fskills\u002F`\n- DAILY commands -> keep as explicit shims only if still useful\n- DAILY rules -> install only matching language sets\n- DAILY hooks\u002Fscripts -> keep only compatible ones\n- LIBRARY surfaces -> keep accessible through search or `skill-library`\n\nIf the repo already uses selective installs, update that plan instead of creating another system.\n\n### 5. Create the optional library router\n\nIf the project wants a searchable library surface, create:\n\n- `.claude\u002Fskills\u002Fskill-library\u002FSKILL.md`\n\nThat router should contain:\n\n- a short explanation of DAILY vs LIBRARY\n- grouped trigger keywords\n- where the library references live\n\nDo not duplicate every skill body inside the router.\n\n### 6. Verify the result\n\nAfter the plan is applied, verify:\n\n- every DAILY file exists where expected\n- stale language rules were not left active\n- incompatible hooks were not installed\n- the resulting install actually matches the repo stack\n\nReturn a compact report with:\n\n- DAILY count\n- LIBRARY count\n- removed stale surfaces\n- open questions\n\n## Handoffs\n\nIf the next step is interactive installation or repair, hand off to:\n\n- `configure-ecc`\n\nIf the next step is overlap cleanup or catalog review, hand off to:\n\n- `skill-stocktake`\n\nIf the next step is broader context trimming, hand off to:\n\n- `strategic-compact`\n\n## Output Format\n\nReturn the result in this order:\n\n```text\nSTACK\n- language\u002Fframework\u002Fruntime summary\n\nDAILY\n- always-loaded items with evidence\n\nLIBRARY\n- searchable\u002Freference items with evidence\n\nINSTALL PLAN\n- what should be installed, removed, or routed\n\nVERIFICATION\n- checks run and remaining gaps\n```\n","# Agent Sort\n\nUse this skill when a repo needs a project-specific ECC surface instead of the default full install.\n\nThe goal is not to guess what \"feels useful.\" The goal is to classify ECC components with evidence from the actual codebase.\n\n## When to Use\n\n- A project only needs a subset of ECC and full installs are too noisy\n- The repo stack is clear, but nobody wants to hand-curate skills one by one\n- A team wants a repeatable install decision backed by grep evidence instead of opinion\n- You need to separate always-loaded daily workflow surfaces from searchable library\u002Freference surfaces\n- A repo has drifted into the wrong language, rule, or hook set and needs cleanup\n\n## Non-Negotiable Rules\n\n- Use the current repository as the source of truth, not generic preferences\n- Every DAILY decision must cite concrete repo evidence\n- LIBRARY does not mean \"delete\"; it means \"keep accessible without loading by default\"\n- Do not install hooks, rules, or scripts that the current repo cannot use\n- Prefer ECC-native surfaces; do not introduce a second install system\n\n## Outputs\n\nProduce these artifacts in order:\n\n1. DAILY inventory\n2. LIBRARY inventory\n3. install plan\n4. verification report\n5. optional `skill-library` router if the project wants one\n\n## Classification Model\n\nUse two buckets only:\n\n- `DAILY`\n  - should load every session for this repo\n  - strongly matched to the repo's language, framework, workflow, or operator surface\n- `LIBRARY`\n  - useful to retain, but not worth loading by default\n  - should remain reachable through search, router skill, or selective manual use\n\n## Evidence Sources\n\nUse repo-local evidence before making any classification:\n\n- file extensions\n- package managers and lockfiles\n- framework configs\n- CI and hook configs\n- build\u002Ftest scripts\n- imports and dependency manifests\n- repo docs that explicitly describe the stack\n\nUseful commands include:\n\n```bash\nrg --files\nrg -n \"typescript|react|next|supabase|django|spring|flutter|swift\"\ncat package.json\ncat pyproject.toml\ncat Cargo.toml\ncat pubspec.yaml\ncat go.mod\n```\n\n## Parallel Review Passes\n\nIf parallel subagents are available, split the review into these passes:\n\n1. Agents\n   - classify `agents\u002F*`\n2. Skills\n   - classify `skills\u002F*`\n3. Commands\n   - classify `commands\u002F*`\n4. Rules\n   - classify `rules\u002F*`\n5. Hooks and scripts\n   - classify hook surfaces, MCP health checks, helper scripts, and OS compatibility\n6. Extras\n   - classify contexts, examples, MCP configs, templates, and guidance docs\n\nIf subagents are not available, run the same passes sequentially.\n\n## Core Workflow\n\n### 1. Read the repo\n\nEstablish the real stack before classifying anything:\n\n- languages in use\n- frameworks in use\n- primary package manager\n- test stack\n- lint\u002Fformat stack\n- deployment\u002Fruntime surface\n- operator integrations already present\n\n### 2. Build the evidence table\n\nFor every candidate surface, record:\n\n- component path\n- component type\n- proposed bucket\n- repo evidence\n- short justification\n\nUse this format:\n\n```text\nskills\u002Ffrontend-patterns | skill | DAILY | 84 .tsx files, next.config.ts present | core frontend stack\nskills\u002Fdjango-patterns   | skill | LIBRARY | no .py files, no pyproject.toml       | not active in this repo\nrules\u002Ftypescript\u002F*       | rules | DAILY | package.json + tsconfig.json            | active TS repo\nrules\u002Fpython\u002F*           | rules | LIBRARY | zero Python source files             | keep accessible only\n```\n\n### 3. Decide DAILY vs LIBRARY\n\nPromote to `DAILY` when:\n\n- the repo clearly uses the matching stack\n- the component is general enough to help every session\n- the repo already depends on the corresponding runtime or workflow\n\nDemote to `LIBRARY` when:\n\n- the component is off-stack\n- the repo might need it later, but not every day\n- it adds context overhead without immediate relevance\n\n### 4. Build the install plan\n\nTranslate the classification into action:\n\n- DAILY skills -> install or keep in `.claude\u002Fskills\u002F`\n- DAILY commands -> keep as explicit shims only if still useful\n- DAILY rules -> install only matching language sets\n- DAILY hooks\u002Fscripts -> keep only compatible ones\n- LIBRARY surfaces -> keep accessible through search or `skill-library`\n\nIf the repo already uses selective installs, update that plan instead of creating another system.\n\n### 5. Create the optional library router\n\nIf the project wants a searchable library surface, create:\n\n- `.claude\u002Fskills\u002Fskill-library\u002FSKILL.md`\n\nThat router should contain:\n\n- a short explanation of DAILY vs LIBRARY\n- grouped trigger keywords\n- where the library references live\n\nDo not duplicate every skill body inside the router.\n\n### 6. Verify the result\n\nAfter the plan is applied, verify:\n\n- every DAILY file exists where expected\n- stale language rules were not left active\n- incompatible hooks were not installed\n- the resulting install actually matches the repo stack\n\nReturn a compact report with:\n\n- DAILY count\n- LIBRARY count\n- removed stale surfaces\n- open questions\n\n## Handoffs\n\nIf the next step is interactive installation or repair, hand off to:\n\n- `configure-ecc`\n\nIf the next step is overlap cleanup or catalog review, hand off to:\n\n- `skill-stocktake`\n\nIf the next step is broader context trimming, hand off to:\n\n- `strategic-compact`\n\n## Output Format\n\nReturn the result in this order:\n\n```text\nSTACK\n- language\u002Fframework\u002Fruntime summary\n\nDAILY\n- always-loaded items with evidence\n\nLIBRARY\n- searchable\u002Freference items with evidence\n\nINSTALL PLAN\n- what should be installed, removed, or routed\n\nVERIFICATION\n- checks run and remaining gaps\n```\n",{"name":5,"origin":46,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fagent-sort","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-sort",{"tool":59,"command":60},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-sort",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-sort","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-sort\u002FSKILL.md",true,[],[68,88,115,141,154,170],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":41},"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",[],[75,76,77,78,79,80,81,82,83,34,84,36,85,86,87],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","injection","execution","file",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":95,"publishedAt":41},"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",[94],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[96,97,98,99,100,101,102,103,104,105,106,107,108,109,34,110,111,112,113,114],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":127,"publishedAt":41},"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",[121,124],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[33,128,129,130,131,132,133,134,135,136,97,137,138,139,140],"visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":41},"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",[],[143,148,149,29,150,151,152,153],"setup","report","installation","project setup","issues","state",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":41},"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",[160],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[156,162,80,163,164,165,34,166,167,168,169],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":171,"name":148,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":41},"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",[],[148,29,112,176,151,177],"files","interactive"]