[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DC75EP9JSMRBSKB2JZZKNG":3,"skill-same:01M6DC75EP9JSMRBSKB2JZZKNG":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},"01M6DC75EP9JSMRBSKB2JZZKNG","fresh-context-verify",null,"Use when a value, address, offset, or assumption has become load-bearing and you have relied on it for many steps without an independent check — especially in long reverse-engineering or autonomous-loop work that keeps hitting inconsistencies. Re-derive the value in a FRESH context that cannot inherit your current reasoning, and halt if it disagrees. The structural fix for sunk-cost grinding on a wrong-but-consistent anchor.","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\u002Fagent-self\u002Fskills\u002Ffresh-context-verify\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"fresh context verify","fresh","verify","context","autonomous","structural","anchor","but","cost","use","fix","reasoning","check","work","loop","reverse-engineering","engineering","2026-11-10 10:12:30",false,"---\nname: fresh-context-verify\ndescription: Use when a value, address, offset, or assumption has become load-bearing and you have relied on it for many steps without an independent check — especially in long reverse-engineering or autonomous-loop work that keeps hitting inconsistencies. Re-derive the value in a FRESH context that cannot inherit your current reasoning, and halt if it disagrees. The structural fix for sunk-cost grinding on a wrong-but-consistent anchor.\n---\n\n# Fresh-Context Verify\n\nSame-context self-checking (\"am I sure?\") is proven unreliable — a wrong anchor stays wrong because the reasoning that produced it is still in the window (intrinsic self-correction degrades reasoning; Huang et al., ICLR 2024). The only fix is an EXTERNAL oracle: re-derive the value in a clean context that never saw your assumption.\n\n## When to run\n- A periodic FALSIFY-CHECK prompt told you to (you have made many edits on one assumption).\n- You keep hitting inconsistencies \u002F contradictions and the work is not converging.\n- A single number \u002F address \u002F offset \u002F field is load-bearing for a long chain of work.\n- Before committing days more effort to a path built on one unverified value.\n\n## Protocol\n1. **Name the anchor.** State the exact value or assumption and the ONE claim everything downstream depends on (e.g. \"the date gate is checked at sub_X\" or \"field +Y holds the timestamp\").\n2. **Spawn a clean re-derivation.** Use the `Agent` tool (`Explore` or general-purpose) with a prompt containing ONLY the raw evidence (the binary \u002F file \u002F data + the question) and NOT your reasoning or your current answer: *\"Independently determine X from this evidence. Do not assume any prior value.\"* The fresh agent cannot inherit your wrong anchor.\n3. **Compare.** Match → the anchor survives; continue with higher confidence. Differs, or the fresh agent cannot reproduce it → **STOP.** The anchor is suspect — that is your 2-day-waste early-warning.\n4. **On mismatch:** do not patch around it. Re-derive from the disagreement; if the two derivations still conflict, surface both to the user.\n\n## Why a subagent, not \"re-check yourself\"\nThe subagent runs in a separate context window — it is the *independent sample \u002F fresh reviewer* the evidence demands. Re-reading your own chat is not independent; it re-confirms the bias. Keep the fresh agent's input minimal and bias-free, and never tell it your current answer.\n","# Fresh-Context Verify\n\nSame-context self-checking (\"am I sure?\") is proven unreliable — a wrong anchor stays wrong because the reasoning that produced it is still in the window (intrinsic self-correction degrades reasoning; Huang et al., ICLR 2024). The only fix is an EXTERNAL oracle: re-derive the value in a clean context that never saw your assumption.\n\n## When to run\n- A periodic FALSIFY-CHECK prompt told you to (you have made many edits on one assumption).\n- You keep hitting inconsistencies \u002F contradictions and the work is not converging.\n- A single number \u002F address \u002F offset \u002F field is load-bearing for a long chain of work.\n- Before committing days more effort to a path built on one unverified value.\n\n## Protocol\n1. **Name the anchor.** State the exact value or assumption and the ONE claim everything downstream depends on (e.g. \"the date gate is checked at sub_X\" or \"field +Y holds the timestamp\").\n2. **Spawn a clean re-derivation.** Use the `Agent` tool (`Explore` or general-purpose) with a prompt containing ONLY the raw evidence (the binary \u002F file \u002F data + the question) and NOT your reasoning or your current answer: *\"Independently determine X from this evidence. Do not assume any prior value.\"* The fresh agent cannot inherit your wrong anchor.\n3. **Compare.** Match → the anchor survives; continue with higher confidence. Differs, or the fresh agent cannot reproduce it → **STOP.** The anchor is suspect — that is your 2-day-waste early-warning.\n4. **On mismatch:** do not patch around it. Re-derive from the disagreement; if the two derivations still conflict, surface both to the user.\n\n## Why a subagent, not \"re-check yourself\"\nThe subagent runs in a separate context window — it is the *independent sample \u002F fresh reviewer* the evidence demands. Re-reading your own chat is not independent; it re-confirms the bias. Keep the fresh agent's input minimal and bias-free, and never tell it your current answer.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","agent-self\u002Fskills\u002Ffresh-context-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 fresh-context-verify",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill fresh-context-verify",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill fresh-context-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fagent-self\u002Fskills\u002Ffresh-context-verify\u002FSKILL.md",true,[],[62,82,113,139,153,168],{"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",[],[69,70,71,72,73,74,75,76,77,28,22,78,79,80,81],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","repo","injection","execution","file",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":93,"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",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,28,108,109,110,111,112],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","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":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":123,"categoryName":124,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000008","测试与质量",[126,127,128,129,130,131,132,133,31,134,95,135,136,137,138],"review","visual","visual review","pages","web","false","iteration","take","slides","ui","screenshot","playwright","screenshots",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"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",[],[141,146,147,148,149,150,151,152],"setup","report","project","installation","project setup","issues","state",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"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",[159],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[155,161,74,162,163,164,28,165,32,166,167],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":169,"name":146,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"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",[],[146,148,110,174,150,175],"files","interactive"]