[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF2EK6P4FPD5AE5B1CBZKC":3,"skill-same:01M6DF2EK6P4FPD5AE5B1CBZKC":57},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DF2EK6P4FPD5AE5B1CBZKC","verification-before-completion",null,"Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","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\u002Fverification-before-completion\u002FSKILL.md",[],[19,20,21,22,23,24,25],"verification","verification before completion","work","use","evidence","claim","commands","2026-11-10 10:12:30",false,"---\nname: verification-before-completion\ndescription: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always\n---\n\n# Verification Before Completion\n\n## Overview\n\nClaiming work is complete without verification is dishonesty, not efficiency.\n\n**Core principle:** Evidence before claims, always.\n\n**Violating the letter of this rule is violating the spirit of this rule.**\n\n## The Iron Law\n\n```\nNO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE\n```\n\nIf you haven't run the verification command in this message, you cannot claim it passes.\n\n## The Gate Function\n\n```\nBEFORE claiming any status or expressing satisfaction:\n\n1. IDENTIFY: What command proves this claim?\n2. RUN: Execute the FULL command (fresh, complete)\n3. READ: Full output, check exit code, count failures\n4. VERIFY: Does output confirm the claim?\n   - If NO: State actual status with evidence\n   - If YES: State claim WITH evidence\n5. ONLY THEN: Make the claim\n\nSkip any step = lying, not verifying\n```\n\n## Common Failures\n\n| Claim | Requires | Not Sufficient |\n|-------|----------|----------------|\n| Tests pass | Test command output: 0 failures | Previous run, \"should pass\" |\n| Commit is green | Suite run from a FRESH CLONE of that commit: exit 0 | Working-tree green |\n| Linter clean | Linter output: 0 errors | Partial check, extrapolation |\n| Build succeeds | Build command: exit 0 | Linter passing, logs look good |\n| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |\n| Regression test works | Red-green cycle verified | Test passes once |\n| Agent completed | VCS diff shows changes | Agent reports \"success\" |\n| Requirements met | Line-by-line checklist | Tests passing |\n\n## Working-Tree Green Is Not Clone Green\n\nYour working tree is not what CI checks out, so a green run there is evidence\nabout YOUR disk -- not about the commit.\n\n- **Untracked and uncommitted files leak in.** A suite reporting **3,910 passed**\n  in the working tree produced **31 collection errors** from a FRESH CLONE of the\n  SAME commit (measured 2026-08-10). The tree was green on files git never saw.\n- **On Windows, CRLF flips formatter verdicts.** The working tree is CRLF, the\n  stored blob is LF, and a formatter can decide differently on the two bodies.\n  A local `ruff format --check` green is NOT a CI green.\n\nVerify against the STORED BLOB, not the file on disk:\n\n```\ngit ls-files -s -- \u003Cpath>     # the blob sha you are about to commit\ngit cat-file -p \u003Cblob-sha>    # the exact bytes CI checks out\n```\n\n**Do NOT reach for `git archive` here.** Measured 2026-08-14 on a CRLF-tracked\nmarkdown file in this repo, one file through three routes: `git archive` + `tar -x`\nreturned CRLF-converted bytes (139 CRLF) -- `git archive` applies export-time EOL\nconversion -- while `git cat-file -p` and `git show \u003Crev>:\u003Cpath>` each returned the\nblob (0 CRLF). All three are identical after LF-normalisation, so the only delta is\nthe line endings -- which is exactly the delta that flips the formatter.\n\n## Red Flags - STOP\n\n- Using \"should\", \"probably\", \"seems to\"\n- Expressing satisfaction before verification (\"Great!\", \"Perfect!\", \"Done!\", etc.)\n- About to commit\u002Fpush\u002FPR without verification\n- Trusting agent success reports\n- Relying on partial verification\n- Thinking \"just this once\"\n- Tired and wanting work over\n- **ANY wording implying success without having run verification**\n\n## Rationalization Prevention\n\n| Excuse | Reality |\n|--------|---------|\n| \"Should work now\" | RUN the verification |\n| \"I'm confident\" | Confidence ≠ evidence |\n| \"Just this once\" | No exceptions |\n| \"Linter passed\" | Linter ≠ compiler |\n| \"Agent said success\" | Verify independently |\n| \"I'm tired\" | Exhaustion ≠ excuse |\n| \"Partial check is enough\" | Partial proves nothing |\n| \"Different words so rule doesn't apply\" | Spirit over letter |\n\n## Key Patterns\n\n**Tests:**\n```\n [Run test command] [See: 34\u002F34 pass] \"All tests pass\"\n \"Should pass now\" \u002F \"Looks correct\"\n```\n\n**Regression tests (TDD Red-Green):**\n```\n Write -> Run (pass) -> Revert fix -> Run (MUST FAIL) -> Restore -> Run (pass)\n \"I've written a regression test\" (without red-green verification)\n```\n\n**Build:**\n```\n [Run build] [See: exit 0] \"Build passes\"\n \"Linter passed\" (linter doesn't check compilation)\n```\n\n**Requirements:**\n```\n Re-read plan -> Create checklist -> Verify each -> Report gaps or completion\n \"Tests pass, phase complete\"\n```\n\n**Agent delegation:**\n```\n Agent reports success -> Check VCS diff -> Verify changes -> Report actual state\n Trust agent report\n```\n\n## Why This Matters\n\nFrom 24 failure memories:\n- your human partner said \"I don't believe you\" - trust broken\n- Undefined functions shipped - would crash\n- Missing requirements shipped - incomplete features\n- Time wasted on false completion -> redirect -> rework\n- Violates: \"Honesty is a core value. If you lie, you'll be replaced.\"\n\n## When To Apply\n\n**ALWAYS before:**\n- ANY variation of success\u002Fcompletion claims\n- ANY expression of satisfaction\n- ANY positive statement about work state\n- Committing, PR creation, task completion\n- Moving to next task\n- Delegating to agents\n\n**Rule applies to:**\n- Exact phrases\n- Paraphrases and synonyms\n- Implications of success\n- ANY communication suggesting completion\u002Fcorrectness\n\n## Checkpoint Provenance: disk-verified vs agent-claimed (Wave C, 2026-08-27)\n\nFail-closed completion doctrine (canonical text: `~\\AGENTS.md` \"Verification doctrine\"):\n**a budget-aborted gate is never green; completion claims require disk artifacts.**\n\n- Every checkpoint \u002F execution-state entry you write (`.beads\\context\\execution-state.md`,\n  wave execution logs, resume files) carries a provenance tag:\n  - **`disk-verified`** — you re-read the artifact\u002Fpath the entry claims, in this message.\n  - **`agent-claimed`** — asserted by an agent (including yourself, earlier) and not yet re-read.\n- On resume, treat `agent-claimed` entries as UNVERIFIED: re-check the artifact before building\n  on them. An absent artifact downgrades the claim to false — but only after a **grace window**\n  (~60s re-check) because artifact writes lag under RAM pressure on this box (transcript-flush\n  lag); an honest completion must not be marked false by a slow flush.\n- A gate that was killed by budget (time\u002Ftokens\u002FRAM) reports **FAILED-TO-RUN**, never PASS and\n  never silently green. Enforcement hooks for this are deliberately NOT built yet — gated on\n  Wave B's observe-mode evidence.\n\n## The Bottom Line\n\n**No shortcuts for verification.**\n\nRun the command. Read the output. THEN claim the result.\n\nThis is non-negotiable.\n","# Verification Before Completion\n\n## Overview\n\nClaiming work is complete without verification is dishonesty, not efficiency.\n\n**Core principle:** Evidence before claims, always.\n\n**Violating the letter of this rule is violating the spirit of this rule.**\n\n## The Iron Law\n\n```\nNO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE\n```\n\nIf you haven't run the verification command in this message, you cannot claim it passes.\n\n## The Gate Function\n\n```\nBEFORE claiming any status or expressing satisfaction:\n\n1. IDENTIFY: What command proves this claim?\n2. RUN: Execute the FULL command (fresh, complete)\n3. READ: Full output, check exit code, count failures\n4. VERIFY: Does output confirm the claim?\n   - If NO: State actual status with evidence\n   - If YES: State claim WITH evidence\n5. ONLY THEN: Make the claim\n\nSkip any step = lying, not verifying\n```\n\n## Common Failures\n\n| Claim | Requires | Not Sufficient |\n|-------|----------|----------------|\n| Tests pass | Test command output: 0 failures | Previous run, \"should pass\" |\n| Commit is green | Suite run from a FRESH CLONE of that commit: exit 0 | Working-tree green |\n| Linter clean | Linter output: 0 errors | Partial check, extrapolation |\n| Build succeeds | Build command: exit 0 | Linter passing, logs look good |\n| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |\n| Regression test works | Red-green cycle verified | Test passes once |\n| Agent completed | VCS diff shows changes | Agent reports \"success\" |\n| Requirements met | Line-by-line checklist | Tests passing |\n\n## Working-Tree Green Is Not Clone Green\n\nYour working tree is not what CI checks out, so a green run there is evidence\nabout YOUR disk -- not about the commit.\n\n- **Untracked and uncommitted files leak in.** A suite reporting **3,910 passed**\n  in the working tree produced **31 collection errors** from a FRESH CLONE of the\n  SAME commit (measured 2026-08-10). The tree was green on files git never saw.\n- **On Windows, CRLF flips formatter verdicts.** The working tree is CRLF, the\n  stored blob is LF, and a formatter can decide differently on the two bodies.\n  A local `ruff format --check` green is NOT a CI green.\n\nVerify against the STORED BLOB, not the file on disk:\n\n```\ngit ls-files -s -- \u003Cpath>     # the blob sha you are about to commit\ngit cat-file -p \u003Cblob-sha>    # the exact bytes CI checks out\n```\n\n**Do NOT reach for `git archive` here.** Measured 2026-08-14 on a CRLF-tracked\nmarkdown file in this repo, one file through three routes: `git archive` + `tar -x`\nreturned CRLF-converted bytes (139 CRLF) -- `git archive` applies export-time EOL\nconversion -- while `git cat-file -p` and `git show \u003Crev>:\u003Cpath>` each returned the\nblob (0 CRLF). All three are identical after LF-normalisation, so the only delta is\nthe line endings -- which is exactly the delta that flips the formatter.\n\n## Red Flags - STOP\n\n- Using \"should\", \"probably\", \"seems to\"\n- Expressing satisfaction before verification (\"Great!\", \"Perfect!\", \"Done!\", etc.)\n- About to commit\u002Fpush\u002FPR without verification\n- Trusting agent success reports\n- Relying on partial verification\n- Thinking \"just this once\"\n- Tired and wanting work over\n- **ANY wording implying success without having run verification**\n\n## Rationalization Prevention\n\n| Excuse | Reality |\n|--------|---------|\n| \"Should work now\" | RUN the verification |\n| \"I'm confident\" | Confidence ≠ evidence |\n| \"Just this once\" | No exceptions |\n| \"Linter passed\" | Linter ≠ compiler |\n| \"Agent said success\" | Verify independently |\n| \"I'm tired\" | Exhaustion ≠ excuse |\n| \"Partial check is enough\" | Partial proves nothing |\n| \"Different words so rule doesn't apply\" | Spirit over letter |\n\n## Key Patterns\n\n**Tests:**\n```\n [Run test command] [See: 34\u002F34 pass] \"All tests pass\"\n \"Should pass now\" \u002F \"Looks correct\"\n```\n\n**Regression tests (TDD Red-Green):**\n```\n Write -> Run (pass) -> Revert fix -> Run (MUST FAIL) -> Restore -> Run (pass)\n \"I've written a regression test\" (without red-green verification)\n```\n\n**Build:**\n```\n [Run build] [See: exit 0] \"Build passes\"\n \"Linter passed\" (linter doesn't check compilation)\n```\n\n**Requirements:**\n```\n Re-read plan -> Create checklist -> Verify each -> Report gaps or completion\n \"Tests pass, phase complete\"\n```\n\n**Agent delegation:**\n```\n Agent reports success -> Check VCS diff -> Verify changes -> Report actual state\n Trust agent report\n```\n\n## Why This Matters\n\nFrom 24 failure memories:\n- your human partner said \"I don't believe you\" - trust broken\n- Undefined functions shipped - would crash\n- Missing requirements shipped - incomplete features\n- Time wasted on false completion -> redirect -> rework\n- Violates: \"Honesty is a core value. If you lie, you'll be replaced.\"\n\n## When To Apply\n\n**ALWAYS before:**\n- ANY variation of success\u002Fcompletion claims\n- ANY expression of satisfaction\n- ANY positive statement about work state\n- Committing, PR creation, task completion\n- Moving to next task\n- Delegating to agents\n\n**Rule applies to:**\n- Exact phrases\n- Paraphrases and synonyms\n- Implications of success\n- ANY communication suggesting completion\u002Fcorrectness\n\n## Checkpoint Provenance: disk-verified vs agent-claimed (Wave C, 2026-08-27)\n\nFail-closed completion doctrine (canonical text: `~\\AGENTS.md` \"Verification doctrine\"):\n**a budget-aborted gate is never green; completion claims require disk artifacts.**\n\n- Every checkpoint \u002F execution-state entry you write (`.beads\\context\\execution-state.md`,\n  wave execution logs, resume files) carries a provenance tag:\n  - **`disk-verified`** — you re-read the artifact\u002Fpath the entry claims, in this message.\n  - **`agent-claimed`** — asserted by an agent (including yourself, earlier) and not yet re-read.\n- On resume, treat `agent-claimed` entries as UNVERIFIED: re-check the artifact before building\n  on them. An absent artifact downgrades the claim to false — but only after a **grace window**\n  (~60s re-check) because artifact writes lag under RAM pressure on this box (transcript-flush\n  lag); an honest completion must not be marked false by a slow flush.\n- A gate that was killed by budget (time\u002Ftokens\u002FRAM) reports **FAILED-TO-RUN**, never PASS and\n  never silently green. Enforcement hooks for this are deliberately NOT built yet — gated on\n  Wave B's observe-mode evidence.\n\n## The Bottom Line\n\n**No shortcuts for verification.**\n\nRun the command. Read the output. THEN claim the result.\n\nThis is non-negotiable.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fverification-before-completion","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill verification-before-completion",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill verification-before-completion",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill verification-before-completion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"agents\u002Fopenai.yaml","REFERENCE","参考文档",203,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002Fagents\u002Fopenai.yaml",[58,79,110,137,151,166],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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",[],[65,66,67,68,69,70,71,72,73,22,74,75,76,77,78],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,94,95,96,97,98,99,100,101,102,103,104,22,105,106,107,108,109],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":122,"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",[116,119],{"categoryNo":117,"categoryName":118,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":120,"categoryName":121,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000008","测试与质量",[123,124,125,126,127,128,129,130,131,132,92,133,134,135,136],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"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",[],[139,144,145,146,147,148,149,150],"setup","report","project","installation","project setup","issues","state",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"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",[157],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[153,159,70,160,161,162,22,163,21,164,165],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":167,"name":144,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"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",[],[144,146,107,172,148,173],"files","interactive"]