[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DDSMRPDSFTN65DSJWBZVRY":3,"skill-same:01M6DDSMRPDSFTN65DSJWBZVRY":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":26,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DDSMRPDSFTN65DSJWBZVRY","agent-harness-construction",null,"Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.","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\u002Fagent-harness-construction\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34],"harness","agent harness","agent harness construction","design","ai agent","tool","optimize","formatting","2026-11-10 10:12:30",false,"---\nname: agent-harness-construction\ndescription: Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.\norigin: ECC\n---\n\n# Agent Harness Construction\n\nUse this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.\n\n## Core Model\n\nAgent output quality is constrained by:\n1. Action space quality\n2. Observation quality\n3. Recovery quality\n4. Context budget quality\n\n## Action Space Design\n\n1. Use stable, explicit tool names.\n2. Keep inputs schema-first and narrow.\n3. Return deterministic output shapes.\n4. Avoid catch-all tools unless isolation is impossible.\n\n## Granularity Rules\n\n- Use micro-tools for high-risk operations (deploy, migration, permissions).\n- Use medium tools for common edit\u002Fread\u002Fsearch loops.\n- Use macro-tools only when round-trip overhead is the dominant cost.\n\n## Observation Design\n\nEvery tool response should include:\n- `status`: success|warning|error\n- `summary`: one-line result\n- `next_actions`: actionable follow-ups\n- `artifacts`: file paths \u002F IDs\n\n## Error Recovery Contract\n\nFor every error path, include:\n- root cause hint\n- safe retry instruction\n- explicit stop condition\n\n## Context Budgeting\n\n1. Keep system prompt minimal and invariant.\n2. Move large guidance into skills loaded on demand.\n3. Prefer references to files over inlining long documents.\n4. Compact at phase boundaries, not arbitrary token thresholds.\n\n## Architecture Pattern Guidance\n\n- ReAct: best for exploratory tasks with uncertain path.\n- Function-calling: best for structured deterministic flows.\n- Hybrid (recommended): ReAct planning + typed tool execution.\n\n## Benchmarking\n\nTrack:\n- completion rate\n- retries per task\n- pass@1 and pass@3\n- cost per successful task\n\n## Anti-Patterns\n\n- Too many tools with overlapping semantics.\n- Opaque tool output with no recovery hints.\n- Error-only output without next steps.\n- Context overloading with irrelevant references.\n","# Agent Harness Construction\n\nUse this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.\n\n## Core Model\n\nAgent output quality is constrained by:\n1. Action space quality\n2. Observation quality\n3. Recovery quality\n4. Context budget quality\n\n## Action Space Design\n\n1. Use stable, explicit tool names.\n2. Keep inputs schema-first and narrow.\n3. Return deterministic output shapes.\n4. Avoid catch-all tools unless isolation is impossible.\n\n## Granularity Rules\n\n- Use micro-tools for high-risk operations (deploy, migration, permissions).\n- Use medium tools for common edit\u002Fread\u002Fsearch loops.\n- Use macro-tools only when round-trip overhead is the dominant cost.\n\n## Observation Design\n\nEvery tool response should include:\n- `status`: success|warning|error\n- `summary`: one-line result\n- `next_actions`: actionable follow-ups\n- `artifacts`: file paths \u002F IDs\n\n## Error Recovery Contract\n\nFor every error path, include:\n- root cause hint\n- safe retry instruction\n- explicit stop condition\n\n## Context Budgeting\n\n1. Keep system prompt minimal and invariant.\n2. Move large guidance into skills loaded on demand.\n3. Prefer references to files over inlining long documents.\n4. Compact at phase boundaries, not arbitrary token thresholds.\n\n## Architecture Pattern Guidance\n\n- ReAct: best for exploratory tasks with uncertain path.\n- Function-calling: best for structured deterministic flows.\n- Hybrid (recommended): ReAct planning + typed tool execution.\n\n## Benchmarking\n\nTrack:\n- completion rate\n- retries per task\n- pass@1 and pass@3\n- cost per successful task\n\n## Anti-Patterns\n\n- Too many tools with overlapping semantics.\n- Opaque tool output with no recovery hints.\n- Error-only output without next steps.\n- Context overloading with irrelevant references.\n",{"name":5,"origin":40,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fagent-harness-construction","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-harness-construction",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-harness-construction",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill agent-harness-construction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fagent-harness-construction\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"resources\u002Fimplementation-playbook.md","REFERENCE","参考文档",16197,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de fastapi-templates\u002Fresources\u002Fimplementation-playbook.md",[68,90,116,143,157,173],{"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":35},"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",[],[75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":97,"publishedAt":35},"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",[96],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[98,99,100,101,102,103,32,104,105,106,107,108,109,110,84,111,112,113,114,115],"openmm md","how","decision","pick","linux","analyze","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":128,"publishedAt":35},"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",[122,125],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[129,130,131,132,133,134,135,136,137,138,99,139,140,141,142],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":149,"publishedAt":35},"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",[],[145,150,151,152,153,154,155,156],"setup","report","project","installation","project setup","issues","state",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":35},"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",[163],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[159,165,80,166,167,168,84,169,170,171,172],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":174,"name":150,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":35},"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",[],[150,152,113,179,154,180],"files","interactive"]