{
  "schemaVersion": "1.0",
  "item": {
    "slug": "verification-before-completion",
    "name": "Verification Before Completion",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/zlc000190/verification-before-completion",
    "canonicalUrl": "https://clawhub.ai/zlc000190/verification-before-completion",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/verification-before-completion",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=verification-before-completion",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/verification-before-completion"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/verification-before-completion",
    "agentPageUrl": "https://openagent3.xyz/skills/verification-before-completion/agent",
    "manifestUrl": "https://openagent3.xyz/skills/verification-before-completion/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/verification-before-completion/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Overview",
        "body": "Claiming work is complete without verification is dishonesty, not efficiency.\n\nCore principle: Evidence before claims, always.\n\nViolating the letter of this rule is violating the spirit of this rule."
      },
      {
        "title": "The Iron Law",
        "body": "NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE\n\nIf you haven't run the verification command in this message, you cannot claim it passes."
      },
      {
        "title": "The Gate Function",
        "body": "BEFORE 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"
      },
      {
        "title": "Common Failures",
        "body": "ClaimRequiresNot SufficientTests passTest command output: 0 failuresPrevious run, \"should pass\"Linter cleanLinter output: 0 errorsPartial check, extrapolationBuild succeedsBuild command: exit 0Linter passing, logs look goodBug fixedTest original symptom: passesCode changed, assumed fixedRegression test worksRed-green cycle verifiedTest passes onceAgent completedVCS diff shows changesAgent reports \"success\"Requirements metLine-by-line checklistTests passing"
      },
      {
        "title": "Red Flags - STOP",
        "body": "Using \"should\", \"probably\", \"seems to\"\nExpressing satisfaction before verification (\"Great!\", \"Perfect!\", \"Done!\", etc.)\nAbout to commit/push/PR without verification\nTrusting agent success reports\nRelying on partial verification\nThinking \"just this once\"\nTired and wanting work over\nANY wording implying success without having run verification"
      },
      {
        "title": "Rationalization Prevention",
        "body": "ExcuseReality\"Should work now\"RUN the verification\"I'm confident\"Confidence ≠ evidence\"Just this once\"No exceptions\"Linter passed\"Linter ≠ compiler\"Agent said success\"Verify independently\"I'm tired\"Exhaustion ≠ excuse\"Partial check is enough\"Partial proves nothing\"Different words so rule doesn't apply\"Spirit over letter"
      },
      {
        "title": "Key Patterns",
        "body": "Tests:\n\n✅ [Run test command] [See: 34/34 pass] \"All tests pass\"\n❌ \"Should pass now\" / \"Looks correct\"\n\nRegression 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\nBuild:\n\n✅ [Run build] [See: exit 0] \"Build passes\"\n❌ \"Linter passed\" (linter doesn't check compilation)\n\nRequirements:\n\n✅ Re-read plan → Create checklist → Verify each → Report gaps or completion\n❌ \"Tests pass, phase complete\"\n\nAgent delegation:\n\n✅ Agent reports success → Check VCS diff → Verify changes → Report actual state\n❌ Trust agent report"
      },
      {
        "title": "Why This Matters",
        "body": "From 24 failure memories:\n\nyour human partner said \"I don't believe you\" - trust broken\nUndefined functions shipped - would crash\nMissing requirements shipped - incomplete features\nTime wasted on false completion → redirect → rework\nViolates: \"Honesty is a core value. If you lie, you'll be replaced.\""
      },
      {
        "title": "When To Apply",
        "body": "ALWAYS before:\n\nANY variation of success/completion claims\nANY expression of satisfaction\nANY positive statement about work state\nCommitting, PR creation, task completion\nMoving to next task\nDelegating to agents\n\nRule applies to:\n\nExact phrases\nParaphrases and synonyms\nImplications of success\nANY communication suggesting completion/correctness"
      },
      {
        "title": "The Bottom Line",
        "body": "No shortcuts for verification.\n\nRun the command. Read the output. THEN claim the result.\n\nThis is non-negotiable."
      }
    ],
    "body": "Verification Before Completion\nOverview\n\nClaiming work is complete without verification is dishonesty, not efficiency.\n\nCore principle: Evidence before claims, always.\n\nViolating the letter of this rule is violating the spirit of this rule.\n\nThe Iron Law\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\nThe Gate Function\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\nCommon Failures\nClaim\tRequires\tNot Sufficient\nTests pass\tTest command output: 0 failures\tPrevious run, \"should pass\"\nLinter clean\tLinter output: 0 errors\tPartial check, extrapolation\nBuild succeeds\tBuild command: exit 0\tLinter passing, logs look good\nBug fixed\tTest original symptom: passes\tCode changed, assumed fixed\nRegression test works\tRed-green cycle verified\tTest passes once\nAgent completed\tVCS diff shows changes\tAgent reports \"success\"\nRequirements met\tLine-by-line checklist\tTests passing\nRed Flags - STOP\nUsing \"should\", \"probably\", \"seems to\"\nExpressing satisfaction before verification (\"Great!\", \"Perfect!\", \"Done!\", etc.)\nAbout to commit/push/PR without verification\nTrusting agent success reports\nRelying on partial verification\nThinking \"just this once\"\nTired and wanting work over\nANY wording implying success without having run verification\nRationalization Prevention\nExcuse\tReality\n\"Should work now\"\tRUN the verification\n\"I'm confident\"\tConfidence ≠ evidence\n\"Just this once\"\tNo exceptions\n\"Linter passed\"\tLinter ≠ compiler\n\"Agent said success\"\tVerify independently\n\"I'm tired\"\tExhaustion ≠ excuse\n\"Partial check is enough\"\tPartial proves nothing\n\"Different words so rule doesn't apply\"\tSpirit over letter\nKey Patterns\n\nTests:\n\n✅ [Run test command] [See: 34/34 pass] \"All tests pass\"\n❌ \"Should pass now\" / \"Looks correct\"\n\n\nRegression 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\nBuild:\n\n✅ [Run build] [See: exit 0] \"Build passes\"\n❌ \"Linter passed\" (linter doesn't check compilation)\n\n\nRequirements:\n\n✅ Re-read plan → Create checklist → Verify each → Report gaps or completion\n❌ \"Tests pass, phase complete\"\n\n\nAgent delegation:\n\n✅ Agent reports success → Check VCS diff → Verify changes → Report actual state\n❌ Trust agent report\n\nWhy This Matters\n\nFrom 24 failure memories:\n\nyour human partner said \"I don't believe you\" - trust broken\nUndefined functions shipped - would crash\nMissing requirements shipped - incomplete features\nTime wasted on false completion → redirect → rework\nViolates: \"Honesty is a core value. If you lie, you'll be replaced.\"\nWhen To Apply\n\nALWAYS before:\n\nANY variation of success/completion claims\nANY expression of satisfaction\nANY positive statement about work state\nCommitting, PR creation, task completion\nMoving to next task\nDelegating to agents\n\nRule applies to:\n\nExact phrases\nParaphrases and synonyms\nImplications of success\nANY communication suggesting completion/correctness\nThe Bottom Line\n\nNo shortcuts for verification.\n\nRun the command. Read the output. THEN claim the result.\n\nThis is non-negotiable."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/zlc000190/verification-before-completion",
    "publisherUrl": "https://clawhub.ai/zlc000190/verification-before-completion",
    "owner": "zlc000190",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/verification-before-completion",
    "downloadUrl": "https://openagent3.xyz/downloads/verification-before-completion",
    "agentUrl": "https://openagent3.xyz/skills/verification-before-completion/agent",
    "manifestUrl": "https://openagent3.xyz/skills/verification-before-completion/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/verification-before-completion/agent.md"
  }
}