[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCJ1RCKCQFMSB2PZNBZ7GQ":3,"skill-same:01M6DCJ1RCKCQFMSB2PZNBZ7GQ":51},{"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":22,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":13,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DCJ1RCKCQFMSB2PZNBZ7GQ","diff-blind-test-synth",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\u002Fdiff-blind-test-synth\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[23,24,25],"test","diff","diff blind test synth","2026-11-10 10:12:30",false,"---\nname: diff-blind-test-synth\ndescription: Use when you want an INDEPENDENT external check that a patch\u002FPR actually satisfies the spec — synthesize executable tests from ONLY the spec + public API (never the diff), then run them against the pre-patch tree (expect FAIL) and the patched tree (expect PASS). A divergence from that expected pattern flags a spec-miss (patch does not implement the requirement) or an over\u002Funder-fitted patch. Distinct from fail-first\u002Fred-proof (which validates the author's OWN changed tests) and execution-consensus rerank (which picks among candidate patches). Runs in SHADOW mode: observe + log only, never blocks. Evidence: UTBoost (2506.09289), MASTER A-Tier2.\n---\n\n# Diff-Blind Adversarial Test Synthesis\n\nThe fixing agent authored the patch AND (usually) the tests that prove it — so \"tests pass\" only proves the patch is self-consistent, not that it meets the requirement. The one signal the author cannot fabricate is a test written by someone who **never saw the diff**. This skill produces that signal: a fresh Opus, given only the spec and the public API surface, writes executable tests; their PASS\u002FFAIL pattern across the pre-patch and post-patch trees is an external oracle on whether the patch does what the spec asked.\n\nGrounded in UTBoost (arXiv 2506.09289): LLM-synthesized, ground-truth-blind tests materially raise the bug-detection power of a patch benchmark by catching patches that pass the shipped suite yet miss the actual fix.\n\n## When to run\n- Reviewing a fleet\u002FCodex\u002Fsubagent patch or PR where the author wrote both code and tests.\n- A bugfix task where you want proof the fix addresses the REQUIREMENT, not just the author's chosen test.\n- Before adopting a \"green-tested\" change you did not write, when the spec is concrete enough to author tests from.\n- NOT for: pure refactors with no behavioral spec; changes whose spec is only visible in the diff itself.\n\n## What makes this distinct (do not conflate)\n- **vs A3 fail-first \u002F red-proof gate:** that gate takes the AUTHOR's changed tests and proves they fail on the merge-base. Here the tests are authored **blind to the diff** by a fresh context — it catches the case where the author's own tests are tautological or under-specify the requirement.\n\n### Diff-blindness is the whole point — enforce the isolation\n### Protocol\n### SHADOW mode (per council C5 — always ship observe-only)\n### Anti-flake \u002F anti-overfit guards\n### Inline runner (shadow-mode, write on demand — no separate skill file)\n### $BASE = merge-base, $TESTFILE = diff-blind synthesized test, $PKG = importable package\n","# Diff-Blind Adversarial Test Synthesis\n\nThe fixing agent authored the patch AND (usually) the tests that prove it — so \"tests pass\" only proves the patch is self-consistent, not that it meets the requirement. The one signal the author cannot fabricate is a test written by someone who **never saw the diff**. This skill produces that signal: a fresh Opus, given only the spec and the public API surface, writes executable tests; their PASS\u002FFAIL pattern across the pre-patch and post-patch trees is an external oracle on whether the patch does what the spec asked.\n\nGrounded in UTBoost (arXiv 2506.09289): LLM-synthesized, ground-truth-blind tests materially raise the bug-detection power of a patch benchmark by catching patches that pass the shipped suite yet miss the actual fix.\n\n## When to run\n- Reviewing a fleet\u002FCodex\u002Fsubagent patch or PR where the author wrote both code and tests.\n- A bugfix task where you want proof the fix addresses the REQUIREMENT, not just the author's chosen test.\n- Before adopting a \"green-tested\" change you did not write, when the spec is concrete enough to author tests from.\n- NOT for: pure refactors with no behavioral spec; changes whose spec is only visible in the diff itself.\n\n## What makes this distinct (do not conflate)\n- **vs A3 fail-first \u002F red-proof gate:** that gate takes the AUTHOR's changed tests and proves they fail on the merge-base. Here the tests are authored **blind to the diff** by a fresh context — it catches the case where the author's own tests are tautological or under-specify the requirement.\n\n### Diff-blindness is the whole point — enforce the isolation\n### Protocol\n### SHADOW mode (per council C5 — always ship observe-only)\n### Anti-flake \u002F anti-overfit guards\n### Inline runner (shadow-mode, write on demand — no separate skill file)\n### $BASE = merge-base, $TESTFILE = diff-blind synthesized test, $PKG = importable package\n",{},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fdiff-blind-test-synth","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":7,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth","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\u002Fdiff-blind-test-synth\u002FSKILL.md",true,[],[52,74,103,128,142,158],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":26},"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",[],[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":83,"publishedAt":26},"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",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[84,85,86,87,88,89,90,91,92,93,94,95,96,97,68,98,99,100,101,102],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":113,"publishedAt":26},"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",[109,112],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[114,115,116,117,118,119,120,121,122,123,85,124,125,126,127],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":26},"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",[],[130,135,136,137,138,139,140,141],"setup","report","project","installation","project setup","issues","state",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":26},"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",[148],{"categoryNo":81,"categoryName":82,"taxonomyType":20,"taxonomyTypeDesc":21},[144,150,64,151,152,153,68,154,155,156,157],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":159,"name":135,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":26},"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",[],[135,137,100,164,139,165],"files","interactive"]