{
  "schemaVersion": "1.0",
  "item": {
    "slug": "task-finish-contract",
    "name": "Task Finish Contract",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Dalomeve/task-finish-contract",
    "canonicalUrl": "https://clawhub.ai/Dalomeve/task-finish-contract",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/task-finish-contract",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=task-finish-contract",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/privacy-checklist.md",
      "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/task-finish-contract"
    },
    "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/task-finish-contract",
    "agentPageUrl": "https://openagent3.xyz/skills/task-finish-contract/agent",
    "manifestUrl": "https://openagent3.xyz/skills/task-finish-contract/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/task-finish-contract/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": "Task Finish Contract",
        "body": "Prevent mid-task stalls. Every task must finish with explicit state and evidence."
      },
      {
        "title": "Problem",
        "body": "Agents often:\n\nStop mid-task without explanation\nOutput plans without execution\nLack clear completion criteria\nMissing evidence artifacts"
      },
      {
        "title": "1. State Output (Each Substantial Step)",
        "body": "**Goal**: What finished looks like\n**Progress**: What has been done\n**Next**: One concrete action executing now"
      },
      {
        "title": "2. Completion Proof Format",
        "body": "For tasks with 2+ steps, include:\n\n**DONE_CHECKLIST**:\n- [ ] Item 1 completed\n- [ ] Item 2 completed\n\n**EVIDENCE**:\n- Executed: command/action summary\n- Artifact: path/URL/id\n- Verified: check command result\n\n**NEXT_AUTONOMOUS_STEP**:\n- One follow-up that runs without user input"
      },
      {
        "title": "3. Anti-Stall Rule",
        "body": "Planning-only replies: max 1\nNext reply MUST contain execution evidence\nNever end with \"I will now...\" without tool result"
      },
      {
        "title": "Executable Completion Criteria",
        "body": "CriteriaVerificationGoal statedSelect-String \"Goal\" memory/{date}.md matchesProgress trackedSelect-String \"Progress\" memory/{date}.md matchesNext action definedSelect-String \"Next\" memory/{date}.md matchesEvidence presentArtifact path/URL existsNo unresolved markers`Select-String \"TODO"
      },
      {
        "title": "Privacy/Safety",
        "body": "No sensitive data in completion evidence\nArtifact paths use relative or workspace paths\nNo credentials in task logs"
      },
      {
        "title": "Self-Use Trigger",
        "body": "Use when:\n\nStarting any multi-step task\nResuming after interruption\nHandoff to another agent\n\nFinish what you start. Prove it with evidence."
      }
    ],
    "body": "Task Finish Contract\n\nPrevent mid-task stalls. Every task must finish with explicit state and evidence.\n\nProblem\n\nAgents often:\n\nStop mid-task without explanation\nOutput plans without execution\nLack clear completion criteria\nMissing evidence artifacts\nWorkflow\n1. State Output (Each Substantial Step)\n**Goal**: What finished looks like\n**Progress**: What has been done\n**Next**: One concrete action executing now\n\n2. Completion Proof Format\n\nFor tasks with 2+ steps, include:\n\n**DONE_CHECKLIST**:\n- [ ] Item 1 completed\n- [ ] Item 2 completed\n\n**EVIDENCE**:\n- Executed: command/action summary\n- Artifact: path/URL/id\n- Verified: check command result\n\n**NEXT_AUTONOMOUS_STEP**:\n- One follow-up that runs without user input\n\n3. Anti-Stall Rule\nPlanning-only replies: max 1\nNext reply MUST contain execution evidence\nNever end with \"I will now...\" without tool result\nExecutable Completion Criteria\nCriteria\tVerification\nGoal stated\tSelect-String \"Goal\" memory/{date}.md matches\nProgress tracked\tSelect-String \"Progress\" memory/{date}.md matches\nNext action defined\tSelect-String \"Next\" memory/{date}.md matches\nEvidence present\tArtifact path/URL exists\nNo unresolved markers\t`Select-String \"TODO\nPrivacy/Safety\nNo sensitive data in completion evidence\nArtifact paths use relative or workspace paths\nNo credentials in task logs\nSelf-Use Trigger\n\nUse when:\n\nStarting any multi-step task\nResuming after interruption\nHandoff to another agent\n\nFinish what you start. Prove it with evidence."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Dalomeve/task-finish-contract",
    "publisherUrl": "https://clawhub.ai/Dalomeve/task-finish-contract",
    "owner": "Dalomeve",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/task-finish-contract",
    "downloadUrl": "https://openagent3.xyz/downloads/task-finish-contract",
    "agentUrl": "https://openagent3.xyz/skills/task-finish-contract/agent",
    "manifestUrl": "https://openagent3.xyz/skills/task-finish-contract/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/task-finish-contract/agent.md"
  }
}