{"id":"df6a9fdb-8f9e-4380-b171-e469f69a3b0b","shortId":"9mVtwy","kind":"skill","title":"verification-before-completion","tagline":"Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.","description":"# Verification Before Completion\n\n> **NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE**\n\n## Core Protocol\n\nEvidence before claims, always. If you haven't run the verification command in this message, you cannot claim it passes.\n\n```\nBEFORE any completion claim:\n1. IDENTIFY: What verification 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   - NO → State actual status with evidence\n   - YES → State claim WITH evidence\n5. ONLY THEN: Make the claim\n```\n\n### Command Selection\n\nWhen multiple verification options exist (mono-repo, multiple suites):\n- Run the **most specific** command that covers the changed code\n- When uncertain, run the **broadest** command (full test suite > single file)\n- Lint ≠ build ≠ test — each verifies different claims\n\n### Evidence Format\n\n```\n✅ Ran: npm test\n   Exit: 0\n   Result: 47 passed, 0 failed\n   \"All tests pass.\"\n\n❌ \"Tests should pass now\" (no command output)\n```\n\n## Verification Requirements by Claim Type\n\n| Claim | Required Evidence | Insufficient |\n|-------|-------------------|--------------|\n| Tests pass | Test output: 0 failures | Previous run, \"should pass\" |\n| Linter clean | Linter output: 0 errors | Partial check, extrapolation |\n| Build succeeds | Build exit code: 0 | Linter passing |\n| Bug fixed | Original symptom test passes | Code changed |\n| Regression test | Red-green cycle verified | Single green |\n| Agent completed | VCS diff shows changes | Agent \"success\" report |\n| Requirements met | Line-by-line checklist | Tests passing |\n\n## Red Flags — STOP\n\n- Words: \"should\", \"probably\", \"seems to\"\n- Satisfaction before verification: \"Great!\", \"Perfect!\", \"Done!\"\n- About to commit/push/PR without verification\n- Trusting agent success reports\n- Partial verification\n- **ANY wording implying success without verification output**\n\n## Rationalization Prevention\n\n| Excuse | Response |\n|--------|----------|\n| \"Should work now\" | Run the verification |\n| \"I'm confident\" | Confidence ≠ evidence |\n| \"Just this once\" | No exceptions |\n| \"Linter passed\" | Linter ≠ build |\n| \"Agent said success\" | Verify independently |\n| \"Partial check enough\" | Partial proves nothing |\n\n## Key Patterns\n\n**Tests:**\n```\n✅ [Run test] → [See: 34/34 pass] → \"All tests pass\"\n❌ \"Should pass now\"\n```\n\n**Regression (TDD):**\n```\n✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)\n❌ \"Wrote regression test\" (no red-green)\n```\n\n**Requirements:**\n```\n✅ Re-read plan → Checklist each item → Report gaps or completion\n❌ \"Tests pass, phase complete\"\n```\n\n**Agent delegation:**\n```\n✅ Agent reports → Check VCS diff → Verify changes → Report actual state\n❌ Trust agent report\n```","tags":["verification","before","completion","agent","skills","library","codingcossack","agent-framework","agent-skills","agent-system","agent-workflow","agentic-workflow"],"capabilities":["skill","source-codingcossack","skill-verification-before-completion","topic-agent-framework","topic-agent-skills","topic-agent-system","topic-agent-workflow","topic-agentic-workflow","topic-ai-agents","topic-anthropic","topic-claude","topic-claude-code","topic-claude-skills","topic-claude-skills-hub","topic-claude-skills-libary"],"categories":["agent-skills-library"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/CodingCossack/agent-skills-library/verification-before-completion","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add CodingCossack/agent-skills-library","source_repo":"https://github.com/CodingCossack/agent-skills-library","install_from":"skills.sh"}},"qualityScore":"0.458","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 17 github stars · SKILL.md body (2,768 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-23T01:02:08.325Z","embedding":null,"createdAt":"2026-04-18T23:06:42.847Z","updatedAt":"2026-04-23T01:02:08.325Z","lastSeenAt":"2026-04-23T01:02:08.325Z","tsv":"'0':165,169,194,204,214 '1':70 '2':78 '3':86 '34/34':325 '4':95 '47':167 '5':113 'actual':104,379 'agent':234,240,272,308,369,371,382 'alway':49 'assert':14 'broadest':145 'bug':217 'build':153,209,211,307 'cannot':62 'chang':139,224,239,377 'check':90,207,314,373 'checklist':249,358 'claim':9,16,39,48,63,69,77,101,110,118,158,184,186 'clean':201 'code':92,140,213,223 'command':57,74,83,119,135,146,179 'commit':26 'commit/push/pr':268 'complet':4,8,20,36,38,68,85,235,364,368 'confid':296,297 'confirm':99 'core':44 'count':93 'cover':137 'cycl':230 'deleg':370 'diff':237,375 'differ':157 'disciplin':6 'done':265 'enforc':29 'enough':315 'error':205 'evid':31,43,46,107,112,159,188,298 'evidence-first':30 'except':303 'excus':286 'execut':80 'exist':125 'exit':91,164,212 'extrapol':208 'fail':170,342 'failur':94,195 'file':151 'first':32 'fix':18,218,339 'flag':253 'format':160 'fresh':41,84 'full':82,88,147 'gap':362 'great':263 'green':229,233,352 'haven':52 'identifi':71 'impli':279 'independ':312 'insuffici':189 'item':360 'key':319 'line':246,248 'line-by-lin':245 'lint':152 'linter':200,202,215,304,306 'm':295 'make':116 'messag':60 'met':244 'mono':127 'mono-repo':126 'multipl':122,129 'must':341 'noth':318 'npm':162 'option':124 'origin':219 'output':89,98,180,193,203,283 'partial':206,275,313,316 'pass':23,65,168,173,176,191,199,216,222,251,305,326,329,331,337,345,366 'pattern':320 'perfect':264 'phase':367 'plan':357 'prevent':285 'previous':196 'probabl':257 'protocol':45 'prove':75,317 'prs':28 'ran':161 'ration':284 're':355 're-read':354 'read':87,356 'red':228,252,351 'red-green':227,350 'regress':225,333,347 'repo':128 'report':21,242,274,361,372,378,383 'requir':182,187,243,353 'respons':287 'restor':343 'result':166 'revert':338 'run':54,79,131,143,197,291,322,336,340,344 'said':309 'satisfact':260 'see':324 'seem':258 'select':120 'show':238 'singl':150,232 'skill' 'skill-verification-before-completion' 'source-codingcossack' 'specif':134 'state':103,109,380 'status':105 'stop':254 'succeed':210 'success':15,241,273,280,310 'suit':130,149 'symptom':220 'tdd':334 'test':22,148,154,163,172,174,190,192,221,226,250,321,323,328,348,365 'topic-agent-framework' 'topic-agent-skills' 'topic-agent-system' 'topic-agent-workflow' 'topic-agentic-workflow' 'topic-ai-agents' 'topic-anthropic' 'topic-claude' 'topic-claude-code' 'topic-claude-skills' 'topic-claude-skills-hub' 'topic-claude-skills-libary' 'trust':271,381 'type':185 'uncertain':142 'use':10 'vcs':236,374 'verif':2,5,34,42,56,73,123,181,262,270,276,282,293 'verifi':96,156,231,311,376 'verification-before-complet':1 'without':40,269,281 'word':255,278 'work':289 'workflow':33 'write':335 'wrote':346 'yes':108","prices":[{"id":"90e1a169-4f66-4fd9-b0ee-b811a6a9282e","listingId":"df6a9fdb-8f9e-4380-b171-e469f69a3b0b","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"CodingCossack","category":"agent-skills-library","install_from":"skills.sh"},"createdAt":"2026-04-18T23:06:42.847Z"}],"sources":[{"listingId":"df6a9fdb-8f9e-4380-b171-e469f69a3b0b","source":"github","sourceId":"CodingCossack/agent-skills-library/verification-before-completion","sourceUrl":"https://github.com/CodingCossack/agent-skills-library/tree/main/skills/verification-before-completion","isPrimary":false,"firstSeenAt":"2026-04-18T23:06:42.847Z","lastSeenAt":"2026-04-23T01:02:08.325Z"}],"details":{"listingId":"df6a9fdb-8f9e-4380-b171-e469f69a3b0b","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"CodingCossack","slug":"verification-before-completion","github":{"repo":"CodingCossack/agent-skills-library","stars":17,"topics":["agent-framework","agent-skills","agent-system","agent-workflow","agentic-workflow","ai-agents","anthropic","claude","claude-code","claude-skills","claude-skills-hub","claude-skills-libary","code-review","codex","context-engineering","debugging","developer-workflow"],"license":null,"html_url":"https://github.com/CodingCossack/agent-skills-library","pushed_at":"2026-01-03T20:02:38Z","description":"Coding agent skills library for programming workflows | Claude Skills, Codex Skills | Forked from obra/superpower","skill_md_sha":"d61a7c7c14770c92c4406290024fe1cfbff0d6cd","skill_md_path":"skills/verification-before-completion/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/CodingCossack/agent-skills-library/tree/main/skills/verification-before-completion"},"layout":"multi","source":"github","category":"agent-skills-library","frontmatter":{"name":"verification-before-completion","description":"Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow."},"skills_sh_url":"https://skills.sh/CodingCossack/agent-skills-library/verification-before-completion"},"updatedAt":"2026-04-23T01:02:08.325Z"}}