[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DE4DBCWSCBJTY0TQ2DBK2K":3,"skill-same:01M6DE4DBCWSCBJTY0TQ2DBK2K":61},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DE4DBCWSCBJTY0TQ2DBK2K","delegated-build-verify",null,"Use when delegating a large build to a generator (Codex fan-out, subagents, or a Workflow) and you must independently verify the result - the \"agent builds X, then you evaluate\" pattern. Turns a converged plan\u002Fgrill into an authoritative build-spec that doubles as the evaluation rubric, fans out the generator, then verifies with an active fabrication hunt. Triggers: \"build X then evaluate\".","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\u002Fdelegated-build-verify\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"delegated build verify","verify","build","use","as","triggers","pattern","active","hunt","grill","spec","subagents","rubric","plan","Evaluation","workflow","codex","2026-11-10 10:12:30",false,"---\nname: delegated-build-verify\ndescription: \"Use when delegating a large build to a generator (Codex fan-out, subagents, or a Workflow) and you must independently verify the result - the \\\"agent builds X, then you evaluate\\\" pattern. Turns a converged plan\u002Fgrill into an authoritative build-spec that doubles as the evaluation rubric, fans out the generator, then verifies with an active fabrication hunt. Triggers: \\\"build X then evaluate\\\".\"\n---\n# Delegated Build + Verify\n\nGenerator–verifier delegation for big builds. The generator (Codex threads \u002F a Workflow \u002F\nsubagents) writes the code or data; **YOU are the independent verifier**. Never let the\ngenerator grade its own homework — self-reported completion and coverage are gameable proxies.\n\n## When to use\n- The user says \"build X, then evaluate it\" \u002F \"fan out Codex to build this, then check it.\"\n- A large multi-part build you will delegate but must not ship on the generator's say-so.\n- Downstream of `grill-me-extensive`, once the scope has converged into decisions.\n\n## The pattern (in order — do not skip step 1)\n1. **Write the BUILD SPEC first — it IS the eval rubric.** Before any generation, author an\n   authoritative spec with: (a) **prime directives** (the non-negotiables — never-fabricate,\n   provenance, security\u002Fprivacy boundaries); (b) the data\u002FAPI contract + schema; (c) per-part\n   sourcing; (d) an explicit **§ Acceptance Criteria** that enumerates *every* gate. It must be\n   precise enough that a fresh reviewer can grade against it. Save it: the generator builds to\n   it, you evaluate against it. No spec → you have no rubric → don't generate yet.\n2. **Encode boundaries as STRUCTURAL gates, not per-item discipline.** e.g. a provenance \u002F\n   lawful-basis gate that auto-routes ungated data to a private\u002Fabsent state; a first-class\n   node so a forbidden attachment is impossible *by construction*. Invariants scale to 100k+\n   records; reminders don't.\n3. **Fan out the generator.** Codex threads \u002F a Workflow \u002F subagents, each carrying a scoped\n   slice of the spec **plus the prime directives embedded in its prompt**. Sequence hard\n   dependencies (schema before data). Worktree-isolate parallel writers so they don't collide.\n4. **VERIFY independently — with an ACTIVE FABRICATION HUNT.** Do NOT trust the generator's\n   self-reported completion\u002Fcoverage. Re-run the gates yourself; spot-hunt for fabricated,\n   unprovenanced, or derived-as-authoritative cells; read the actual test *summary* line, not\n   the exit code. Report: **completion** (done \u002F partial \u002F absent per part), **honest coverage\n   %**, and each **gate** pass\u002Ffail. **Fabrication or coverage-theater = automatic FAIL for\n   that slice**, however \"done\" it looks. Incomplete-but-honest beats complete-but-fabricated.\n\n## Red flags (STOP)\n| Thought | Reality |\n|---|---|\n| \"The generator said it's 100% covered.\" | Verify it yourself; self-reported coverage is a gameable proxy. |\n| \"No build-spec yet, I'll just start generating.\" | You have no rubric — write the spec first. |\n| \"I'll delegate without repeating the non-negotiables.\" | Drift + fabrication. Embed them in every slice. |\n| \"It looks complete, ship it.\" | Run the fabrication hunt before believing \"complete.\" |\n\n## Related\n- Upstream scope: `grill-me-extensive`. Verify discipline: `verification-before-completion`.\n- Anti-reward-hacking rationale: basic-memory `agentic-repair-reliability`,\n  `verified-green-read-summary-not-coverage`.\n","# Delegated Build + Verify\n\nGenerator–verifier delegation for big builds. The generator (Codex threads \u002F a Workflow \u002F\nsubagents) writes the code or data; **YOU are the independent verifier**. Never let the\ngenerator grade its own homework — self-reported completion and coverage are gameable proxies.\n\n## When to use\n- The user says \"build X, then evaluate it\" \u002F \"fan out Codex to build this, then check it.\"\n- A large multi-part build you will delegate but must not ship on the generator's say-so.\n- Downstream of `grill-me-extensive`, once the scope has converged into decisions.\n\n## The pattern (in order — do not skip step 1)\n1. **Write the BUILD SPEC first — it IS the eval rubric.** Before any generation, author an\n   authoritative spec with: (a) **prime directives** (the non-negotiables — never-fabricate,\n   provenance, security\u002Fprivacy boundaries); (b) the data\u002FAPI contract + schema; (c) per-part\n   sourcing; (d) an explicit **§ Acceptance Criteria** that enumerates *every* gate. It must be\n   precise enough that a fresh reviewer can grade against it. Save it: the generator builds to\n   it, you evaluate against it. No spec → you have no rubric → don't generate yet.\n2. **Encode boundaries as STRUCTURAL gates, not per-item discipline.** e.g. a provenance \u002F\n   lawful-basis gate that auto-routes ungated data to a private\u002Fabsent state; a first-class\n   node so a forbidden attachment is impossible *by construction*. Invariants scale to 100k+\n   records; reminders don't.\n3. **Fan out the generator.** Codex threads \u002F a Workflow \u002F subagents, each carrying a scoped\n   slice of the spec **plus the prime directives embedded in its prompt**. Sequence hard\n   dependencies (schema before data). Worktree-isolate parallel writers so they don't collide.\n4. **VERIFY independently — with an ACTIVE FABRICATION HUNT.** Do NOT trust the generator's\n   self-reported completion\u002Fcoverage. Re-run the gates yourself; spot-hunt for fabricated,\n   unprovenanced, or derived-as-authoritative cells; read the actual test *summary* line, not\n   the exit code. Report: **completion** (done \u002F partial \u002F absent per part), **honest coverage\n   %**, and each **gate** pass\u002Ffail. **Fabrication or coverage-theater = automatic FAIL for\n   that slice**, however \"done\" it looks. Incomplete-but-honest beats complete-but-fabricated.\n\n## Red flags (STOP)\n| Thought | Reality |\n|---|---|\n| \"The generator said it's 100% covered.\" | Verify it yourself; self-reported coverage is a gameable proxy. |\n| \"No build-spec yet, I'll just start generating.\" | You have no rubric — write the spec first. |\n| \"I'll delegate without repeating the non-negotiables.\" | Drift + fabrication. Embed them in every slice. |\n| \"It looks complete, ship it.\" | Run the fabrication hunt before believing \"complete.\" |\n\n## Related\n- Upstream scope: `grill-me-extensive`. Verify discipline: `verification-before-completion`.\n- Anti-reward-hacking rationale: basic-memory `agentic-repair-reliability`,\n  `verified-green-read-summary-not-coverage`.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fdelegated-build-verify","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 delegated-build-verify",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill delegated-build-verify",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill delegated-build-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fdelegated-build-verify\u002FSKILL.md",true,[],[62,83,113,140,154,170],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":36},"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",[],[69,70,71,72,73,74,75,76,77,22,78,79,80,81,82],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":94,"publishedAt":36},"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",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[95,96,97,98,99,100,101,102,103,104,105,106,34,107,22,108,109,110,111,112],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","windows","free","molecular dynamics","local","do","MCP",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":36},"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",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":123,"categoryName":124,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量",[126,127,128,129,130,131,132,133,134,135,96,136,137,138,139],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":36},"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",[],[142,147,148,149,150,151,152,153],"setup","report","project","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":36},"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":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[156,162,74,163,164,165,22,166,167,168,169],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":171,"name":147,"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":36},"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",[],[147,149,110,176,151,177],"files","interactive"]