[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCJYX3855PWBCKBNFGFK0T":3,"skill-same:01M6DCJYX3855PWBCKBNFGFK0T":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M6DCJYX3855PWBCKBNFGFK0T","execution-grounded-bon",null,"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\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fexecution-grounded-bon\u002FSKILL.md",[],[18,19],"execution","execution grounded bon","2026-11-10 10:12:30",false,"---\nname: execution-grounded-bon\ndescription: Use when you have SEVERAL candidate patches\u002Fsolutions for the same task — typically from a cross-vendor Codex+Codex worktree fan-out — and must pick the best one WITHOUT trusting an LLM to judge them (JudgeBench shows model-opinion rerank ≈ chance). Synthesize distinguishing inputs where the candidates diverge, execute all candidates on them, cluster by behavior (behavioral-diff), knock out crashers\u002Ftimeouts, and select by EXECUTION-CONSENSUS — where an independent Codex candidate and an independent Codex candidate agree, that agreement is the signal (cross-vendor = independent failures). A BoN-MAV aspect jury ranks within the winning cluster. Distinct from A3 fail-first (validates ONE author's own tests) and diff-blind-test-synth (one patch vs spec-derived tests). Ships SHADOW: observe + log only, never blocks. Evidence: MASTER A4, COUNCIL C3; arXiv 2502.14382 (S*), 2409.08692 (B4), 2503.15223 (PatchDiff), 2207.10397 (CodeT).\n---\n\n# Execution-Grounded Best-of-N + Behavioral-Diff Reranker\n\nWhen N agents produce N candidate patches for the same task, the naive rerank is to ask a model \"which is best?\" — and that is proven near-worthless: an LLM judge over candidate code lands around chance on adversarial selection (JudgeBench), and it is exactly the same-context self-grading the whole Theme-A verification program exists to route around (Goodhart + the intrinsic self-correction ceiling, Huang ICLR'24). The done-signal must be **external and agent-inauthorable**.\n\nExecution is that signal. Instead of an opinion, run every candidate on inputs chosen to make them disagree, watch what they actually *do*, and let their behavior cluster them. Candidates that crash or hang eliminate themselves. Candidates that independently converge on the same behavior — especially across two different vendors — are the ones to trust: two independent samples agreeing is the classic oracle-free consensus signal (CodeT), and cross-vendor agreement makes the two samples' blind spots independent (a Codex bug and a Codex bug are unlikely to be the *same* bug).\n\nGrounded in: **S\\*** (2502.14382, distinguishing-input synthesis for candidate selection), **B4** (2409.08692, Bayesian best-selection over execution results), **PatchDiff** (2503.15223, behavioral patch differencing), **CodeT** (2207.10397, dual-execution agreement without a ground-truth oracle). MASTER A4 \u002F COUNCIL C3 both mandate: gate on executable evidence, **never model opinion**.\n\n### When to run\n### What makes this distinct (do not conflate)\n### The bus this rides (do not rebuild)\n### Protocol\n### The reranker: `rerank.mjs`\n### precomputed: manifest already carries candidates[].observations[]\n### execute: run each candidate's cmd once per probe to build the behavior matrix\n### machine-readable (pure JSON on stdout; terminal marker goes to stderr)\n### prove the logic on this machine (13 embedded assertions)\n### Manifest schema\n### Pipeline (all stages pure & execution-derived — no model opinion)\n### Verdict (excerpt)\n### SHADOW mode (per COUNCIL C5 — always ship observe-only)\n","# Execution-Grounded Best-of-N + Behavioral-Diff Reranker\n\nWhen N agents produce N candidate patches for the same task, the naive rerank is to ask a model \"which is best?\" — and that is proven near-worthless: an LLM judge over candidate code lands around chance on adversarial selection (JudgeBench), and it is exactly the same-context self-grading the whole Theme-A verification program exists to route around (Goodhart + the intrinsic self-correction ceiling, Huang ICLR'24). The done-signal must be **external and agent-inauthorable**.\n\nExecution is that signal. Instead of an opinion, run every candidate on inputs chosen to make them disagree, watch what they actually *do*, and let their behavior cluster them. Candidates that crash or hang eliminate themselves. Candidates that independently converge on the same behavior — especially across two different vendors — are the ones to trust: two independent samples agreeing is the classic oracle-free consensus signal (CodeT), and cross-vendor agreement makes the two samples' blind spots independent (a Codex bug and a Codex bug are unlikely to be the *same* bug).\n\nGrounded in: **S\\*** (2502.14382, distinguishing-input synthesis for candidate selection), **B4** (2409.08692, Bayesian best-selection over execution results), **PatchDiff** (2503.15223, behavioral patch differencing), **CodeT** (2207.10397, dual-execution agreement without a ground-truth oracle). MASTER A4 \u002F COUNCIL C3 both mandate: gate on executable evidence, **never model opinion**.\n\n### When to run\n### What makes this distinct (do not conflate)\n### The bus this rides (do not rebuild)\n### Protocol\n### The reranker: `rerank.mjs`\n### precomputed: manifest already carries candidates[].observations[]\n### execute: run each candidate's cmd once per probe to build the behavior matrix\n### machine-readable (pure JSON on stdout; terminal marker goes to stderr)\n### prove the logic on this machine (13 embedded assertions)\n### Manifest schema\n### Pipeline (all stages pure & execution-derived — no model opinion)\n### Verdict (excerpt)\n### SHADOW mode (per COUNCIL C5 — always ship observe-only)\n",{},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fexecution-grounded-bon","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill execution-grounded-bon",{"tool":37,"command":38},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill execution-grounded-bon",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill execution-grounded-bon","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fexecution-grounded-bon\u002FSKILL.md",true,[],[46,67,98,125,139,155],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":20},"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",[],[53,54,55,56,57,58,59,60,61,62,63,64,65,18,66],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","file",{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":20},"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",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[79,80,81,82,83,84,85,86,87,88,89,90,91,92,62,93,94,95,96,97],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":110,"publishedAt":20},"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",[104,107],{"categoryNo":105,"categoryName":106,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":108,"categoryName":109,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000008","测试与质量",[111,112,113,114,115,116,117,118,119,120,80,121,122,123,124],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":20},"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",[],[127,132,133,134,135,136,137,138],"setup","report","project","installation","project setup","issues","state",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":20},"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",[145],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[141,147,58,148,149,150,62,151,152,153,154],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":156,"name":132,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":20},"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",[],[132,134,95,161,136,162],"files","interactive"]