{"id":"16c754c3-0409-4220-9eb0-a0029abaf7cb","shortId":"jWZ3zd","kind":"skill","title":"verification-before-completion","tagline":"Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Triggers on: \"done\", \"fixed\", \"ready to commit\", \"tests pass\", \"build succeeds\", any success claim. Requires running verification commands and confirming output before making any succe","description":"# 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| 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## Red Flags - STOP\n\n- Using \"should\", \"probably\", \"seems to\"\n- Expressing satisfaction before verification (\"Great!\", \"Perfect!\", \"Done!\", etc.)\n- About to commit/push/PR 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: 34/34 pass] \"All tests pass\"\n❌ \"Should pass now\" / \"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/completion 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/correctness\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\n## Examples\n\n### Example 1: Test Verification\nClaim: \"All tests pass\"\nVerification: Run `npm test`, see output \"34/34 pass\", report with evidence\nWrong: \"Should pass now\" without running tests\n\n### Example 2: Build Verification\nClaim: \"Build succeeds\"\nVerification: Run `npm run build`, see exit code 0, report with evidence\nWrong: \"Linter passed\" (linter ≠ compiler)\n\n### Example 3: Requirements Verification\nClaim: \"All requirements met\"\nVerification: Re-read plan, create checklist, verify each item, report gaps or completion\nWrong: \"Tests pass, phase complete\" (tests ≠ requirements)\n\n## Troubleshooting\n\n### Issue: Tempted to claim success without verification\nSolution: STOP. Run the verification command first. No exceptions.\n\n### Issue: Verification fails but you're tired\nSolution: Exhaustion is not an excuse. Fix the issue and re-verify. Don't commit broken work.\n\n### Issue: Partial verification seems enough\nSolution: Partial proves nothing. Run the FULL verification command. Check exit code and all output.","tags":["verification","before","completion","synapse","deve1993","agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation"],"capabilities":["skill","source-deve1993","skill-verification-before-completion","topic-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workspace","topic-anti-poisoning","topic-auto-learning-ai","topic-automation","topic-claude-code","topic-code-quality","topic-cursor","topic-developer-tools","topic-devops"],"categories":["Synapse"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/deve1993/Synapse/verification-before-completion","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add deve1993/Synapse","source_repo":"https://github.com/deve1993/Synapse","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 7 github stars · SKILL.md body (4,887 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":"2026-05-18T19:14:15.136Z","embedding":null,"createdAt":"2026-05-18T13:21:48.375Z","updatedAt":"2026-05-18T19:14:15.136Z","lastSeenAt":"2026-05-18T19:14:15.136Z","tsv":"'0':182,192,202,394,596 '1':115,556 '2':122,582 '24':441 '3':130,606 '34/34':351,569 '4':139 '5':159 'actual':149,432 'agent':229,235,269,317,421,423,435,516 'alway':65,488 'appli':340,487,518 'assum':216 'believ':451 'bottom':533 'broken':454,674 'bug':208 'build':30,197,199,389,391,395,583,586,592 'cannot':101 'chang':215,234,430 'check':134,195,328,402,426,690 'checklist':244,410,619 'claim':9,34,50,64,84,102,109,121,145,156,164,173,494,546,559,585,609,638 'clean':189 'code':136,214,595,692 'command':38,96,118,127,180,200,349,541,647,689 'commit':17,27,505,673 'commit/push/pr':265 'common':171 'communic':529 'compil':316,403,604 'complet':4,12,48,53,83,129,230,416,420,469,509,626,631 'completion/correctness':531 'confid':305,306 'confirm':40,143 'core':60,476 'correct':360 'count':137 'crash':459 'creat':19,409,618 'creation':507 'cycl':224 'deleg':422,514 'diff':232,428 'differ':334 'dishonesti':57 'doesn':338,400 'done':23,261 'effici':59 'enough':330,680 'error':193 'etc':262 'evid':62,88,152,158,307,573,599 'exact':520 'exampl':554,555,581,605 'except':312,650 'excus':295,326,663 'execut':124 'exhaust':325,659 'exit':135,201,393,594,691 'express':113,255,496 'extrapol':196 'fail':374,653 'failur':138,172,183,442 'fals':468 'featur':464 'first':648 'fix':13,24,209,217,371,664 'flag':248 'fresh':86,128 'full':126,132,687 'function':107,456 'gap':414,624 'gate':106 'good':207 'great':259 'green':223,366,387 'haven':91 'honesti':473 'human':445 'identifi':116 'impli':287 'implic':525 'incomplet':463 'independ':321 'iron':80 'issu':635,651,666,676 'item':622 'key':344 'law':81 'letter':68,343 'lie':168,480 'line':241,243,534 'line-by-lin':240 'linter':188,190,203,313,315,397,399,601,603 'll':482 'log':205 'look':206,359 'm':304,323 'make':43,162 'matter':439 'memori':443 'messag':99 'met':239,612 'miss':460 'move':510 'must':373 'negoti':553 'next':512 'non':552 'non-negoti':551 'noth':333,684 'npm':565,590 'origin':211 'output':41,133,142,181,191,544,568,695 'overview':49 'paraphras':522 'partial':194,274,327,331,677,682 'partner':446 'pass':15,29,104,178,187,204,213,227,246,314,352,355,357,369,377,396,398,418,562,570,576,602,629 'pattern':345 'perfect':260 'phase':419,630 'phrase':521 'plan':408,617 'posit':500 'pr':506 'prevent':294 'previous':184 'principl':61 'probabl':252 'prove':119,332,683 'prs':20 'ration':293 're':406,615,656,669 're-read':405,614 're-verifi':668 'read':131,407,542,616 'readi':25 'realiti':296 'red':222,247,365,386 'red-green':221,364,385 'redirect':470 'regress':218,361,382 'reli':272 'replac':484 'report':236,271,413,424,431,436,571,597,623 'requir':35,174,238,404,461,607,611,633 'restor':375 'result':548 'revert':370 'rework':471 'rule':71,78,337,517 'run':36,93,123,185,291,300,347,368,372,376,390,539,564,579,589,591,644,685 'said':318,447 'satisfact':114,256,498 'see':350,392,567,593 'seem':253,679 'ship':457,462 'shortcut':536 'show':233 'skill' 'skill-verification-before-completion' 'skip':165 'solut':642,658,681 'source-deve1993' 'spirit':75,341 'state':148,155,433,504 'statement':501 'status':111,150 'step':167 'stop':249,643 'succ':45 'succeed':31,198,587 'success':33,237,270,288,319,425,527,639 'success/completion':493 'suffici':176 'suggest':530 'symptom':212 'synonym':524 'task':508,513 'tdd':363 'tempt':636 'test':28,177,179,210,219,226,245,346,348,354,362,383,417,557,561,566,580,628,632 'think':276 'time':465 'tire':280,324,657 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workspace' 'topic-anti-poisoning' 'topic-auto-learning-ai' 'topic-automation' 'topic-claude-code' 'topic-code-quality' 'topic-cursor' 'topic-developer-tools' 'topic-devops' 'trigger':21 'troubleshoot':634 'trust':268,434,453 'undefin':455 'use':5,250 'valu':477 'variat':491 'vcs':231,427 've':379 'verif':2,37,46,55,87,95,258,267,275,292,302,388,538,558,563,584,588,608,613,641,646,652,678,688 'verifi':140,170,225,320,411,429,620,670 'verification-before-complet':1 'violat':66,73,472 'want':282 'wast':466 'without':54,85,266,289,384,578,640 'word':286,335 'work':10,51,220,283,298,503,675 'would':458 'write':367 'written':380 'wrong':574,600,627 'yes':154","prices":[{"id":"ae4f7ab2-06e4-4704-a244-9c6c3e834943","listingId":"16c754c3-0409-4220-9eb0-a0029abaf7cb","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"deve1993","category":"Synapse","install_from":"skills.sh"},"createdAt":"2026-05-18T13:21:48.375Z"}],"sources":[{"listingId":"16c754c3-0409-4220-9eb0-a0029abaf7cb","source":"github","sourceId":"deve1993/Synapse/verification-before-completion","sourceUrl":"https://github.com/deve1993/Synapse/tree/main/skills/verification-before-completion","isPrimary":false,"firstSeenAt":"2026-05-18T13:21:48.375Z","lastSeenAt":"2026-05-18T19:14:15.136Z"}],"details":{"listingId":"16c754c3-0409-4220-9eb0-a0029abaf7cb","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"deve1993","slug":"verification-before-completion","github":{"repo":"deve1993/Synapse","stars":7,"topics":["agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation","claude-code","code-quality","cursor","developer-tools","devops","fullstack-development","multi-agent-systems","nextjs","opencode","persistent-memory","self-improving","telegram-bot"],"license":"other","html_url":"https://github.com/deve1993/Synapse","pushed_at":"2026-05-15T21:34:01Z","description":"Self-improving AI brain for Claude Code & Desktop — 28 MCP tools, 253 skills, collective memory, project tracking, work logs. One server, all your sessions share the same knowledge. Deploy on Coolify in 2 minutes.","skill_md_sha":"3951fef7c3b57d3740f1898dbb8b67e1f43e0f09","skill_md_path":"skills/verification-before-completion/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/deve1993/Synapse/tree/main/skills/verification-before-completion"},"layout":"multi","source":"github","category":"Synapse","frontmatter":{"name":"verification-before-completion","description":"Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Triggers on: \"done\", \"fixed\", \"ready to commit\", \"tests pass\", \"build succeeds\", any success claim. Requires running verification commands and confirming output before making any success claims. Evidence before assertions always."},"skills_sh_url":"https://skills.sh/deve1993/Synapse/verification-before-completion"},"updatedAt":"2026-05-18T19:14:15.136Z"}}