[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF7D7478R55P46REYH4QAC":3,"skill-same:01M6DF7D7478R55P46REYH4QAC":59},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements",null,"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.","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\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"clarify","requirements","clarify requirements","file","execution","injection","risk","repo","context","use","scanning","goal","prompts","task","options","2026-11-10 10:12:30",false,"---\nname: clarify-requirements\ndescription: 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.\n---\n\n# clarify-requirements\n\nInvoked when the inquisitiveness guard (or the agent itself) detects a prompt that could be interpreted in meaningfully different ways before file edits begin.\n\n## Procedure\n\n1. **Cheap repo scan (1-2 reads).** Identify the most likely files\u002Fmodules relevant to the user's request. Look for names, recent modifications, or patterns that suggest intent. This bounds the question space so questions are grounded, not open-ended.\n\n2. **List interpretations.** Generate 2-6 concrete, mutually exclusive interpretations of the request. Label them A, B, C... For each note the implied scope (which files\u002Fbehaviors change) and the outcome difference.\n\n3. **EVPI gate.** Only proceed to ask if the interpretations lead to meaningfully different implementations. If one interpretation is clearly dominant from context (imports, recent commits, task name), pick it, state your assumption, and skip asking.\n\n4. **Ask via AskUserQuestion — 1-3 questions, max.** Questions must be:\n   - Grounded (reference actual file\u002Fmodule names or concrete options found in step 1-2).\n   - Mutually exclusive (each question resolves a distinct axis of ambiguity).\n   - Short (one sentence + options where applicable).\n   - Never asking about things inferrable from the codebase.\n\n5. **Proceed.** Once the user answers (or you confirm no material ambiguity), proceed with implementation. Do not loop back into this skill.\n\n## Scope exclusions\n\n- Do NOT invoke mid-task; clarification mid-execution amplifies prompt-injection risk 15-16x.\n- Do NOT ask when the prompt names a specific file, error, URL, or code reference — those are already concrete.\n- Do NOT generate more than 6 interpretations; if there are more, the problem is too broad — ask one framing question first.\n","# clarify-requirements\n\nInvoked when the inquisitiveness guard (or the agent itself) detects a prompt that could be interpreted in meaningfully different ways before file edits begin.\n\n## Procedure\n\n1. **Cheap repo scan (1-2 reads).** Identify the most likely files\u002Fmodules relevant to the user's request. Look for names, recent modifications, or patterns that suggest intent. This bounds the question space so questions are grounded, not open-ended.\n\n2. **List interpretations.** Generate 2-6 concrete, mutually exclusive interpretations of the request. Label them A, B, C... For each note the implied scope (which files\u002Fbehaviors change) and the outcome difference.\n\n3. **EVPI gate.** Only proceed to ask if the interpretations lead to meaningfully different implementations. If one interpretation is clearly dominant from context (imports, recent commits, task name), pick it, state your assumption, and skip asking.\n\n4. **Ask via AskUserQuestion — 1-3 questions, max.** Questions must be:\n   - Grounded (reference actual file\u002Fmodule names or concrete options found in step 1-2).\n   - Mutually exclusive (each question resolves a distinct axis of ambiguity).\n   - Short (one sentence + options where applicable).\n   - Never asking about things inferrable from the codebase.\n\n5. **Proceed.** Once the user answers (or you confirm no material ambiguity), proceed with implementation. Do not loop back into this skill.\n\n## Scope exclusions\n\n- Do NOT invoke mid-task; clarification mid-execution amplifies prompt-injection risk 15-16x.\n- Do NOT ask when the prompt names a specific file, error, URL, or code reference — those are already concrete.\n- Do NOT generate more than 6 interpretations; if there are more, the problem is too broad — ask one framing question first.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","tools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill clarify-requirements",{"tool":51,"command":52},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill clarify-requirements",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill clarify-requirements","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",true,[],[60,91,118,132,148,156],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":71,"publishedAt":34},"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",[66],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,28,87,88,89,90],"openmm md","MCP","linux","workflow","windows","license","gpu","NVIDIA","open","how","stack","tool","analyze","pick","decision","do","local","molecular dynamics","free",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":103,"publishedAt":34},"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",[97,100],{"categoryNo":98,"categoryName":99,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":101,"categoryName":102,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000008","测试与质量",[104,105,106,107,108,109,110,111,112,81,113,114,115,116,117],"review","visual review","visual","slides","check","take","iteration","pages","false","ui","screenshots","playwright","web","screenshot",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":34},"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",[],[120,125,126,127,128,129,130,131],"setup","report","state","issues","project setup","installation","project",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":34},"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",[138],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},[134,32,140,141,142,143,144,28,145,146,147],"development","work on","start issue","work","user","work on issue","ready","issue",{"skillNo":149,"name":125,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":34},"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",[],[125,154,129,155,88,131],"interactive","files",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":34},"01M6DF6M1P5KAJ13YQJ28T7XDE","pr-shepherd","Monitor a PR through to merge — handle CI failures, review comments, and thread resolution automatically until all checks pass","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fpr-shepherd\u002FSKILL.md",[],[163,164,165,166,167,168,169,104],"shepherd","pr","pr shepherd","monitor","merge","resolution","ci"]