{
  "schemaVersion": "1.0",
  "item": {
    "slug": "prompt-request",
    "name": "Prompt Request Pipeline",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ShunsukeHayashi/prompt-request",
    "canonicalUrl": "https://clawhub.ai/ShunsukeHayashi/prompt-request",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/prompt-request",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=prompt-request",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "examples/sample-hook-config.json",
      "SKILL.md",
      "templates/issue-content.md",
      "templates/issue-detailed.md",
      "templates/issue-simple.md",
      "templates/messageTemplate.txt"
    ],
    "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/prompt-request"
    },
    "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/prompt-request",
    "agentPageUrl": "https://openagent3.xyz/skills/prompt-request/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-request/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-request/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": "Prompt Request Pipeline",
        "body": "Issue を書くだけで、自動実装 → PR → レビュー → マージまで全自動で回るパイプライン。"
      },
      {
        "title": "Overview",
        "body": "[auto] Issue 起票\n  → 🚀 実装開始コメント\n  → Phase A: タスク分解（Omega-bridge or Issue本文）\n  → 📋 分析完了コメント\n  → Phase B: 実装 + テスト\n  → ✅ 実装完了コメント\n  → Phase C: commit → push → PR作成\n  → 🔗 PR作成コメント\n  → 自動レビュー → 自動マージ → Issue close"
      },
      {
        "title": "Prerequisites",
        "body": "OpenClaw Gateway running with hooks enabled\nGitHub CLI (gh) authenticated\nGit SSH access to target repository\nGitHub Webhook pointing to OpenClaw hooks endpoint"
      },
      {
        "title": "1. Register GitHub Webhook",
        "body": "On your GitHub repo → Settings → Webhooks → Add webhook:\n\nPayload URL: https://<your-openclaw-endpoint>/hooks/github\nContent type: application/json\nSecret: Your OpenClaw hooks token\nEvents: Select individual events:\n\nIssues\nPull requests\nPull request reviews\nCheck runs\nIssue comments\nPush"
      },
      {
        "title": "2. Configure OpenClaw hooks",
        "body": "Add this to your openclaw.json under hooks.mappings:\n\n{\n  \"match\": { \"path\": \"github\" },\n  \"action\": \"agent\",\n  \"name\": \"GitHub\",\n  \"sessionKey\": \"hook:github:{{repository.name}}:{{headers.x-github-event}}:{{issue.number}}{{pull_request.number}}{{check_run.id}}\",\n  \"messageTemplate\": \"<see templates/messageTemplate.txt>\",\n  \"deliver\": true,\n  \"allowUnsafeExternalContent\": true,\n  \"channel\": \"telegram\",\n  \"to\": \"<your-chat-id>\",\n  \"model\": \"anthropic/claude-opus-4-6\",\n  \"thinking\": \"high\",\n  \"timeoutSeconds\": 900\n}"
      },
      {
        "title": "3. Set working directory",
        "body": "In the messageTemplate, replace the working directory path:\n\nWORKDIR variable: where repositories are cloned (e.g., C:\\Users\\you\\Dev or /home/you/dev)"
      },
      {
        "title": "4. (Optional) Omega-bridge",
        "body": "If you have Miyabi's omega-bridge for SWML-based task decomposition:\n\nSet the path to omega-bridge.ts in the messageTemplate\nIf not available, the pipeline falls back to implementing directly from Issue body"
      },
      {
        "title": "Basic: Create an [auto] Issue",
        "body": "Title: [auto] Add utility function X\n\nBody:\n## Requirements\n- Create scripts/x.sh with function do_x()\n- Add tests in tests/test-x.sh\n\n## Acceptance Criteria\n- Function returns expected output\n- Tests pass"
      },
      {
        "title": "Advanced: With agent personality",
        "body": "Title: [auto] [content] Write article about Y\n\nBody:\nRead agents/content-agent/AGENTS.md and SOUL.md first.\nFollow the rules defined there.\n\n## Topic\n...\n\n## Output\n- File: articles/y.md\n- Word count: 6000"
      },
      {
        "title": "Advanced: With skill reference",
        "body": "Title: [auto] Generate report with weather data\n\nBody:\nRead skills/weather/SKILL.md for API usage.\n\n## Requirements\n..."
      },
      {
        "title": "Issue Events (action=opened)",
        "body": "Early exit check: If action is closed/labeled/etc → 1-line reply, stop\n[auto] check: Title starts with [auto] or body contains <!-- auto-implement -->\nPhase A: Task decomposition (omega-bridge or direct)\nPhase B: Implementation (branch, code, test)\nPhase C: Integration (commit, push, PR)\nProgress comments posted at each phase"
      },
      {
        "title": "PR Events (action=opened/synchronize)",
        "body": "Skip bot senders (loop prevention)\nDiff review for quality/security\nAuto-merge if ALL conditions met:\n\nPR title contains [auto] or branch starts with feature/issue-\nReview is LGTM\nCI checks pass (or empty = pass)\nNo merge conflicts"
      },
      {
        "title": "Safety Rules",
        "body": "Never force push\nNever push directly to main\nNever run permission commands (icacls/chmod/chown)\nMax 3 CI fix retries per PR\nBot sender events are skipped"
      },
      {
        "title": "Configuration Options",
        "body": "OptionDefaultDescriptionmodelclaude-opus-4-6Model for hook sessionsthinkinghighThinking leveltimeoutSeconds900Max execution time (15 min)delivertrueSend results to chatchanneltelegramDelivery channel"
      },
      {
        "title": "Performance (measured)",
        "body": "MetricBefore optimizationAfter optimizationclose/push events8-12 min, ~500 tokens3 sec, ~15 tokens[auto] Issue → merged PRN/A (stuck)~5 minFull pipeline (Issue → merge)N/A~5 min"
      },
      {
        "title": "Tips",
        "body": "Keep Issues small: 1 Issue = 1 clear deliverable, ≤300 lines of diff\nBe specific: The quality of the Issue body directly determines output quality\nUse templates: Create Issue templates for recurring task types\nReference skills: Point the agent to relevant SKILL.md files for domain knowledge\nReference agent definitions: Store AGENTS.md/SOUL.md in the repo for consistent behavior"
      }
    ],
    "body": "Prompt Request Pipeline\n\nIssue を書くだけで、自動実装 → PR → レビュー → マージまで全自動で回るパイプライン。\n\nOverview\n[auto] Issue 起票\n  → 🚀 実装開始コメント\n  → Phase A: タスク分解（Omega-bridge or Issue本文）\n  → 📋 分析完了コメント\n  → Phase B: 実装 + テスト\n  → ✅ 実装完了コメント\n  → Phase C: commit → push → PR作成\n  → 🔗 PR作成コメント\n  → 自動レビュー → 自動マージ → Issue close\n\nPrerequisites\nOpenClaw Gateway running with hooks enabled\nGitHub CLI (gh) authenticated\nGit SSH access to target repository\nGitHub Webhook pointing to OpenClaw hooks endpoint\nSetup\n1. Register GitHub Webhook\n\nOn your GitHub repo → Settings → Webhooks → Add webhook:\n\nPayload URL: https://<your-openclaw-endpoint>/hooks/github\nContent type: application/json\nSecret: Your OpenClaw hooks token\nEvents: Select individual events:\nIssues\nPull requests\nPull request reviews\nCheck runs\nIssue comments\nPush\n2. Configure OpenClaw hooks\n\nAdd this to your openclaw.json under hooks.mappings:\n\n{\n  \"match\": { \"path\": \"github\" },\n  \"action\": \"agent\",\n  \"name\": \"GitHub\",\n  \"sessionKey\": \"hook:github:{{repository.name}}:{{headers.x-github-event}}:{{issue.number}}{{pull_request.number}}{{check_run.id}}\",\n  \"messageTemplate\": \"<see templates/messageTemplate.txt>\",\n  \"deliver\": true,\n  \"allowUnsafeExternalContent\": true,\n  \"channel\": \"telegram\",\n  \"to\": \"<your-chat-id>\",\n  \"model\": \"anthropic/claude-opus-4-6\",\n  \"thinking\": \"high\",\n  \"timeoutSeconds\": 900\n}\n\n3. Set working directory\n\nIn the messageTemplate, replace the working directory path:\n\nWORKDIR variable: where repositories are cloned (e.g., C:\\Users\\you\\Dev or /home/you/dev)\n4. (Optional) Omega-bridge\n\nIf you have Miyabi's omega-bridge for SWML-based task decomposition:\n\nSet the path to omega-bridge.ts in the messageTemplate\nIf not available, the pipeline falls back to implementing directly from Issue body\nUsage\nBasic: Create an [auto] Issue\nTitle: [auto] Add utility function X\n\nBody:\n## Requirements\n- Create scripts/x.sh with function do_x()\n- Add tests in tests/test-x.sh\n\n## Acceptance Criteria\n- Function returns expected output\n- Tests pass\n\nAdvanced: With agent personality\nTitle: [auto] [content] Write article about Y\n\nBody:\nRead agents/content-agent/AGENTS.md and SOUL.md first.\nFollow the rules defined there.\n\n## Topic\n...\n\n## Output\n- File: articles/y.md\n- Word count: 6000\n\nAdvanced: With skill reference\nTitle: [auto] Generate report with weather data\n\nBody:\nRead skills/weather/SKILL.md for API usage.\n\n## Requirements\n...\n\nHow It Works\nIssue Events (action=opened)\nEarly exit check: If action is closed/labeled/etc → 1-line reply, stop\n[auto] check: Title starts with [auto] or body contains <!-- auto-implement -->\nPhase A: Task decomposition (omega-bridge or direct)\nPhase B: Implementation (branch, code, test)\nPhase C: Integration (commit, push, PR)\nProgress comments posted at each phase\nPR Events (action=opened/synchronize)\nSkip bot senders (loop prevention)\nDiff review for quality/security\nAuto-merge if ALL conditions met:\nPR title contains [auto] or branch starts with feature/issue-\nReview is LGTM\nCI checks pass (or empty = pass)\nNo merge conflicts\nSafety Rules\nNever force push\nNever push directly to main\nNever run permission commands (icacls/chmod/chown)\nMax 3 CI fix retries per PR\nBot sender events are skipped\nConfiguration Options\nOption\tDefault\tDescription\nmodel\tclaude-opus-4-6\tModel for hook sessions\nthinking\thigh\tThinking level\ntimeoutSeconds\t900\tMax execution time (15 min)\ndeliver\ttrue\tSend results to chat\nchannel\ttelegram\tDelivery channel\nPerformance (measured)\nMetric\tBefore optimization\tAfter optimization\nclose/push events\t8-12 min, ~500 tokens\t3 sec, ~15 tokens\n[auto] Issue → merged PR\tN/A (stuck)\t~5 min\nFull pipeline (Issue → merge)\tN/A\t~5 min\nTips\nKeep Issues small: 1 Issue = 1 clear deliverable, ≤300 lines of diff\nBe specific: The quality of the Issue body directly determines output quality\nUse templates: Create Issue templates for recurring task types\nReference skills: Point the agent to relevant SKILL.md files for domain knowledge\nReference agent definitions: Store AGENTS.md/SOUL.md in the repo for consistent behavior"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ShunsukeHayashi/prompt-request",
    "publisherUrl": "https://clawhub.ai/ShunsukeHayashi/prompt-request",
    "owner": "ShunsukeHayashi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/prompt-request",
    "downloadUrl": "https://openagent3.xyz/downloads/prompt-request",
    "agentUrl": "https://openagent3.xyz/skills/prompt-request/agent",
    "manifestUrl": "https://openagent3.xyz/skills/prompt-request/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/prompt-request/agent.md"
  }
}