{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-reviewer-pro",
    "name": "Skill Reviewer Pro",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/YKaiXu/skill-reviewer-pro",
    "canonicalUrl": "https://clawhub.ai/YKaiXu/skill-reviewer-pro",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skill-reviewer-pro",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-reviewer-pro",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json"
    ],
    "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/skill-reviewer-pro"
    },
    "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/skill-reviewer-pro",
    "agentPageUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/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": "Skill Reviewer Pro",
        "body": "Comprehensive skill review and validation for OpenClaw skills with scoring rubric, defect checklists, functional verification, optimization recommendations, and workflow validation."
      },
      {
        "title": "Language Adaptation",
        "body": "IMPORTANT: Always respond in the same language as the user's request.\n\nIf user asks in Chinese → respond in Chinese\nIf user asks in English → respond in English\nIf user asks in other languages → respond in that language\n\nAuto-adapt to the user's language to ensure clear communication and better user experience."
      },
      {
        "title": "Level 1: Format Validation ✅",
        "body": "package_skill.py validation passed\nYAML frontmatter valid\nFile structure correct"
      },
      {
        "title": "Level 2: Writing Quality Assessment",
        "body": "Structure: ✅ Good (6/6)\n\nClear frontmatter with name and description\nWell-organized body with workflow sections\nProgressive disclosure pattern used\n\nDescription: ✅ Strong (8/8)\n\nStarts with what skill does: \"Build high-performing OpenClaw agents end-to-end.\"\nIncludes trigger: \"Use when you want to design a new agent...\"\nSpecific scope: mentions SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md\nReasonable length\nContains searchable keywords\n\nExample Density: ⚠️ Low (1/3)\n\nSKILL.md has few code blocks\nCould benefit from more concrete examples\n\nOrganization: ✅ Good (6/6)\n\nOrganized by workflow (Phase 1 → Phase 2 → Phase 3 → Phase 4)\nLogical flow from interview to generation to validation\nSections are self-contained\n\nActionability: ✅ Good (10/10)\n\nInstructions are imperative\nSteps are ordered logically\nGuardrails checklist provided\nAcceptance tests included"
      },
      {
        "title": "Level 3: Functional Verification ❌ CRITICAL (0/20)",
        "body": "Problem: Generated AGENTS.md template does not match OpenClaw specifications\n\nMissing from templates.md AGENTS.md:\n\nSession startup requirements (Read SOUL.md, USER.md, memory files)\nMemory workflow details (daily notes vs long-term)\nGroup chat behavior guidelines (when to speak, when to stay silent)\nHeartbeat mechanism details (heartbeat vs cron, what to check)\nTool usage guidelines (Skills provide tools, Voice storytelling, Platform formatting)\n\nImpact: Skills created with agent-builder-plus will be missing critical OpenClaw agent behaviors."
      },
      {
        "title": "Level 4: Best Practices Check ✅ Good (15/15)",
        "body": "Progressive Disclosure: ✅ Good (5/5)\n\nSKILL.md is concise\nDetailed information in references/\nReferences properly linked\n\nResource Organization: ✅ Good (5/5)\n\nOnly necessary directories created\nNo extraneous files\n\nTriggering Accuracy: ✅ Good (5/5)\n\nDescription clearly states when to use\nNo \"When to Use This Skill\" in body"
      },
      {
        "title": "Level 5: Optimization Recommendations",
        "body": "🔴 Critical (Must Fix)\n\n1. Fix AGENTS.md Template Functional Mismatch\nUpdate references/templates.md to include all required sections from actual OpenClaw AGENTS.md.\n\n🟡 Major (Should Fix)\n\n2. Add More Concrete Examples\nAdd 3-5 concrete code examples in workflow sections.\n\n3. Add Quick Start Section\nAdd a \"Quick Start\" section at the beginning of SKILL.md."
      },
      {
        "title": "Level 6: Workflow Validation ❌ CRITICAL (0/20)",
        "body": "Note: This level applies to workflow tools (skills that guide users through multi-step processes).\n\nWorkflow Completeness Check\n\nWORKFLOW COMPLETENESS CHECK:\n\n[ ] Each phase has clear operational steps\n[ ] Correct CLI commands are used\n[ ] Error handling is documented\n[ ] Backup and recovery mechanisms exist\n[ ] Verification steps are included\n[ ] Configuration management is documented\n[ ] Failure recovery strategies exist\n\nagent-builder-plus Analysis:\n\nCheckStatusIssueEach phase has clear operational steps⚠️ PartialPhase 2 only lists files, not creation commandsCorrect CLI commands are used❌ MissingNo openclaw agents add commandError handling is documented❌ MissingNo error handling in any phaseBackup and recovery mechanisms exist❌ MissingNo backup before config changesVerification steps are included❌ MissingNo verification after agent registrationConfiguration management is documented❌ MissingNo auth-profiles.json documentationFailure recovery strategies exist❌ MissingNo recovery strategies for any phase\n\nDetailed Issues\n\nIssue 1: Missing BOOTSTRAP.md in file list\n\nPhase: Phase 2\nProblem: BOOTSTRAP.md is mentioned in AGENTS.md specs but not in file list\nImpact: New agents lack first-run guidance\nFix: Add BOOTSTRAP.md to Phase 2 file list\n\nIssue 2: No agent registration logic\n\nPhase: Missing\nProblem: No openclaw agents add command documented\nImpact: Users must manually configure openclaw.json\nFix: Add Phase 2.5 with openclaw agents add command\n\nIssue 3: No auth-profiles.json documentation\n\nPhase: Missing\nProblem: No authentication configuration documentation\nImpact: Agents cannot access external services (e.g., Feishu)\nFix: Add authentication section after Phase 2.5\n\nIssue 4: No backup mechanism\n\nPhase: Missing\nProblem: No backup before modifying openclaw.json\nImpact: Config errors can break entire OpenClaw system\nFix: Add backup step before Phase 2.5\n\nIssue 5: No configuration verification\n\nPhase: Missing\nProblem: No verification after agent registration\nImpact: Agent may not start correctly\nFix: Add Phase 2.6 with verification steps\n\nIssue 6: No directory creation robustness\n\nPhase: Phase 2\nProblem: No error handling for directory creation\nImpact: File writes fail silently if directory creation fails\nFix: Add mkdir -p with error checking\n\nIssue 7: No automated testing (Phase 8)\n\nPhase: Missing\nProblem: Only Phase 4 (acceptance tests), no automated testing\nImpact: No complete testing workflow\nFix: Add Phase 8 with automated test commands\n\nIssue 8: No failure recovery strategies\n\nPhase: All phases\nProblem: No recovery strategies for any phase\nImpact: Users don't know how to recover from failures\nFix: Add failure recovery section to each phase\n\nIssue 9: Unclear Feishu binding method\n\nPhase: Phase 1\nProblem: Question 2 asks \"Which channels?\" but doesn't clarify Feishu binding\nImpact: Users unclear about channel binding vs /agentname command\nFix: Clarify Feishu binding options in Phase 1\n\nIssue 10: Optional systemd heartbeat\n\nPhase: Optional\nProblem: No systemd service configuration option\nImpact: Cannot run agent as systemd service\nFix: Add optional systemd service configuration"
      },
      {
        "title": "Score Summary",
        "body": "SKILL REVIEW SCORECARD\n═══════════════════════════════════════\nSkill: agent-builder-plus\nReviewer: 大鱼\nDate: 2026-02-27\n\nCategory              Score    Max\n─────────────────────────────────────\nLevel 1: Format       10       10  ✅\nLevel 2: Writing\n  - Structure          6        6  ✅\n  - Description        8        8  ✅\n  - Example density    1        3  ⚠️\n  - Organization       6        6  ✅\n  - Actionability     10       10  ✅\nLevel 3: Functional    0       20  ❌ CRITICAL\nLevel 4: Best Practices\n  - Progressive       5        5  ✅\n  - Resources         5        5  ✅\n  - Triggering        5        5  ✅\nLevel 5: Optimization  0       10  (recommendations provided)\n)\nLevel 6: Workflow      0       20  ❌ CRITICAL\n─────────────────────────────────────\nTOTAL                 56       116\n\nRATING: 56/116 = Fair — significant gaps to address\nVERDICT: REWORK (functional and workflow verification failed)"
      },
      {
        "title": "Top Defects",
        "body": "1. Functional Mismatch: AGENTS.md template missing critical OpenClaw specifications.\n\n2. Workflow Incomplete: Missing agent registration, configuration verification, backup mechanisms, error handling, and failure recovery strategies."
      },
      {
        "title": "Recommendation",
        "body": "Update references/templates.md AGENTS.md template with all required sections\nAdd Phase 2.5 (agent registration with openclaw agents add)\nAdd Phase 2.6 (configuration verification)\nAdd backup mechanism before config changes\nAdd failure recovery strategies to each phase\nAdd directory creation error handling\nAdd Phase 8 (automated testing)\nClarify Feishu binding options in Phase 1\nAdd optional systemd service configuration"
      },
      {
        "title": "Level 1: Format Validation",
        "body": "Run automatic validation using package_skill.py:\n\npython3 /home/yupeng/.npm-global/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py <skill-path>"
      },
      {
        "title": "Level 2: Writing Quality Assessment",
        "body": "Check structure, description, examples, organization, and actionability."
      },
      {
        "title": "Level 3: Functional Verification",
        "body": "For OpenClaw skills, compare generated templates with actual specifications."
      },
      {
        "title": "Level 4: Best Practices Check",
        "body": "Verify progressive disclosure, resource organization, and triggering accuracy."
      },
      {
        "title": "Level 5: Optimization Recommendations",
        "body": "Provide prioritized recommendations (Critical/Major/Minor)."
      },
      {
        "title": "Level 6: Workflow Validation (For Workflow Tools)",
        "body": "Workflow Completeness Check\n\nWORKFLOW COMPLETENESS CHECK:\n\n[ ] Each phase has clear operational steps\n[ ] Correct CLI commands are used\n[ ] Error handling is documented\n[ ] Backup and recovery mechanisms exist\n[ ] Verification steps are included\n[ ] Configuration management is documented\n[ ] Failure recovery strategies exist\n\nPhase-by-Phase Validation\n\nFor each phase in the workflow:\n\nPHASE VALIDATION CHECKLIST:\n\nPhase: [phase name]\n\nOperational Steps:\n[ ] Clear, step-by-step instructions provided\n[ ] Commands are accurate and complete\n[ ] Required parameters are specified\n\nError Handling:\n[ ] Common errors are documented\n[ ] Recovery steps are provided\n[ ] Error messages are explained\n\nVerification:\n[ ] Success criteria are defined\n[ ] Verification steps are included\n[ ] How to confirm completion is explained\n\nDependencies:\n[ ] Prerequisites are listed\n[ ] Order dependencies are clear\n[ ] Previous phase completion is verified\n\nCLI Command Validation\n\nFor workflow tools that use OpenClaw CLI commands:\n\nCLI COMMAND VALIDATION:\n\n[ ] Commands are verified with `openclaw <command> --help`\n[ ] Command syntax is correct\n[ ] Required options are documented\n[ ] Default values are explained\n[ ] Example commands are runnable\n\nConfiguration Management\n\nFor tools that modify OpenClaw configuration:\n\nCONFIGURATION MANAGEMENT CHECK:\n\n[ ] Files being modified are listed\n[ ] Backup mechanism is provided\n[ ] Rollback steps are documented\n[ ] Configuration validation is included\n[ ] Authentication requirements are explained"
      },
      {
        "title": "Critical",
        "body": "Invalid frontmatter\nBroken code examples\nMisleading description\nFunctional mismatch (OpenClaw skills)\nWorkflow incomplete (missing phases, no CLI commands)\nNo backup before config changes"
      },
      {
        "title": "Major",
        "body": "No \"When to Use\" information\nText walls without examples\nExamples missing language tags\nAbstract organization\nDuplication between SKILL.md and references\nNo error handling\nNo verification steps\nNo failure recovery strategies"
      },
      {
        "title": "Minor",
        "body": "Placeholder values\nInconsistent formatting\nExtraneous files\nMissing cross-references\nNo quick start guide"
      },
      {
        "title": "Language Adaptation Guidelines",
        "body": "CRITICAL: Always respond in the same language as the user's request."
      },
      {
        "title": "Detection Rules",
        "body": "Detect user language from the request message\n\nCheck the language of the user's input message\nUse the same language for all responses\n\n\n\nLanguage mapping\n\nChinese (中文/汉语) → Respond in Chinese\nEnglish → Respond in English\nJapanese (日本語) → Respond in Japanese\nKorean (한국어) → Respond in Korean\nOther languages → Respond in the detected language\n\n\n\nConsistency\n\nOnce language is detected, use it for the entire review\nAll section headers, descriptions, and feedback should be in the same language\nTechnical terms (like \"Level 1\", \"Level 2\") can remain in English if they are standard terminology"
      },
      {
        "title": "Example Scenarios",
        "body": "Scenario 1: User asks in Chinese\n\nUser: 请审查一下 agent-builder-plus 这个 skill\nAI: (responds in Chinese)\n## 审查结果：agent-builder-plus\n...\n\nScenario 2: User asks in English\n\nUser: Please review the agent-builder-plus skill\nAI: (responds in English)\n## Review Results: agent-builder-plus\n...\n\nScenario 3: User asks in mixed language\n\nUser: 请审查 agent-builder-plus skill\nAI: (responds in Chinese, as the primary language is Chinese)\n## 审查结果：agent-builder-plus\n..."
      },
      {
        "title": "Implementation Notes",
        "body": "Language detection should be done at the start of the review\nUse simple language detection (check for Chinese characters, etc.)\nIf language cannot be detected, default to the language of the previous interaction\nMaintain language consistency throughout the entire review process"
      },
      {
        "title": "Technical Terms",
        "body": "Keep technical terms in English when appropriate:\n\nSkill names (e.g., \"agent-builder-plus\")\nFile names (e.g., \"SKILL.md\", \"IDENTITY.md\")\nCLI commands (e.g., \"openclaw agents add\")\nTechnical concepts (e.g., \"workspace\", \"agent\", \"channel\")\n\nBut translate descriptions, feedback, and explanations to the user's language."
      }
    ],
    "body": "Skill Reviewer Pro\n\nComprehensive skill review and validation for OpenClaw skills with scoring rubric, defect checklists, functional verification, optimization recommendations, and workflow validation.\n\nLanguage Adaptation\n\nIMPORTANT: Always respond in the same language as the user's request.\n\nIf user asks in Chinese → respond in Chinese\nIf user asks in English → respond in English\nIf user asks in other languages → respond in that language\n\nAuto-adapt to the user's language to ensure clear communication and better user experience.\n\nReview: agent-builder-plus (Example)\nLevel 1: Format Validation ✅\npackage_skill.py validation passed\nYAML frontmatter valid\nFile structure correct\nLevel 2: Writing Quality Assessment\n\nStructure: ✅ Good (6/6)\n\nClear frontmatter with name and description\nWell-organized body with workflow sections\nProgressive disclosure pattern used\n\nDescription: ✅ Strong (8/8)\n\nStarts with what skill does: \"Build high-performing OpenClaw agents end-to-end.\"\nIncludes trigger: \"Use when you want to design a new agent...\"\nSpecific scope: mentions SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md\nReasonable length\nContains searchable keywords\n\nExample Density: ⚠️ Low (1/3)\n\nSKILL.md has few code blocks\nCould benefit from more concrete examples\n\nOrganization: ✅ Good (6/6)\n\nOrganized by workflow (Phase 1 → Phase 2 → Phase 3 → Phase 4)\nLogical flow from interview to generation to validation\nSections are self-contained\n\nActionability: ✅ Good (10/10)\n\nInstructions are imperative\nSteps are ordered logically\nGuardrails checklist provided\nAcceptance tests included\nLevel 3: Functional Verification ❌ CRITICAL (0/20)\n\nProblem: Generated AGENTS.md template does not match OpenClaw specifications\n\nMissing from templates.md AGENTS.md:\n\nSession startup requirements (Read SOUL.md, USER.md, memory files)\nMemory workflow details (daily notes vs long-term)\nGroup chat behavior guidelines (when to speak, when to stay silent)\nHeartbeat mechanism details (heartbeat vs cron, what to check)\nTool usage guidelines (Skills provide tools, Voice storytelling, Platform formatting)\n\nImpact: Skills created with agent-builder-plus will be missing critical OpenClaw agent behaviors.\n\nLevel 4: Best Practices Check ✅ Good (15/15)\n\nProgressive Disclosure: ✅ Good (5/5)\n\nSKILL.md is concise\nDetailed information in references/\nReferences properly linked\n\nResource Organization: ✅ Good (5/5)\n\nOnly necessary directories created\nNo extraneous files\n\nTriggering Accuracy: ✅ Good (5/5)\n\nDescription clearly states when to use\nNo \"When to Use This Skill\" in body\nLevel 5: Optimization Recommendations\n🔴 Critical (Must Fix)\n\n1. Fix AGENTS.md Template Functional Mismatch Update references/templates.md to include all required sections from actual OpenClaw AGENTS.md.\n\n🟡 Major (Should Fix)\n\n2. Add More Concrete Examples Add 3-5 concrete code examples in workflow sections.\n\n3. Add Quick Start Section Add a \"Quick Start\" section at the beginning of SKILL.md.\n\nLevel 6: Workflow Validation ❌ CRITICAL (0/20)\n\nNote: This level applies to workflow tools (skills that guide users through multi-step processes).\n\nWorkflow Completeness Check\nWORKFLOW COMPLETENESS CHECK:\n\n[ ] Each phase has clear operational steps\n[ ] Correct CLI commands are used\n[ ] Error handling is documented\n[ ] Backup and recovery mechanisms exist\n[ ] Verification steps are included\n[ ] Configuration management is documented\n[ ] Failure recovery strategies exist\n\n\nagent-builder-plus Analysis:\n\nCheck\tStatus\tIssue\nEach phase has clear operational steps\t⚠️ Partial\tPhase 2 only lists files, not creation commands\nCorrect CLI commands are used\t❌ Missing\tNo openclaw agents add command\nError handling is documented\t❌ Missing\tNo error handling in any phase\nBackup and recovery mechanisms exist\t❌ Missing\tNo backup before config changes\nVerification steps are included\t❌ Missing\tNo verification after agent registration\nConfiguration management is documented\t❌ Missing\tNo auth-profiles.json documentation\nFailure recovery strategies exist\t❌ Missing\tNo recovery strategies for any phase\nDetailed Issues\n\nIssue 1: Missing BOOTSTRAP.md in file list\n\nPhase: Phase 2\nProblem: BOOTSTRAP.md is mentioned in AGENTS.md specs but not in file list\nImpact: New agents lack first-run guidance\nFix: Add BOOTSTRAP.md to Phase 2 file list\n\nIssue 2: No agent registration logic\n\nPhase: Missing\nProblem: No openclaw agents add command documented\nImpact: Users must manually configure openclaw.json\nFix: Add Phase 2.5 with openclaw agents add command\n\nIssue 3: No auth-profiles.json documentation\n\nPhase: Missing\nProblem: No authentication configuration documentation\nImpact: Agents cannot access external services (e.g., Feishu)\nFix: Add authentication section after Phase 2.5\n\nIssue 4: No backup mechanism\n\nPhase: Missing\nProblem: No backup before modifying openclaw.json\nImpact: Config errors can break entire OpenClaw system\nFix: Add backup step before Phase 2.5\n\nIssue 5: No configuration verification\n\nPhase: Missing\nProblem: No verification after agent registration\nImpact: Agent may not start correctly\nFix: Add Phase 2.6 with verification steps\n\nIssue 6: No directory creation robustness\n\nPhase: Phase 2\nProblem: No error handling for directory creation\nImpact: File writes fail silently if directory creation fails\nFix: Add mkdir -p with error checking\n\nIssue 7: No automated testing (Phase 8)\n\nPhase: Missing\nProblem: Only Phase 4 (acceptance tests), no automated testing\nImpact: No complete testing workflow\nFix: Add Phase 8 with automated test commands\n\nIssue 8: No failure recovery strategies\n\nPhase: All phases\nProblem: No recovery strategies for any phase\nImpact: Users don't know how to recover from failures\nFix: Add failure recovery section to each phase\n\nIssue 9: Unclear Feishu binding method\n\nPhase: Phase 1\nProblem: Question 2 asks \"Which channels?\" but doesn't clarify Feishu binding\nImpact: Users unclear about channel binding vs /agentname command\nFix: Clarify Feishu binding options in Phase 1\n\nIssue 10: Optional systemd heartbeat\n\nPhase: Optional\nProblem: No systemd service configuration option\nImpact: Cannot run agent as systemd service\nFix: Add optional systemd service configuration\nScore Summary\nSKILL REVIEW SCORECARD\n═══════════════════════════════════════\nSkill: agent-builder-plus\nReviewer: 大鱼\nDate: 2026-02-27\n\nCategory              Score    Max\n─────────────────────────────────────\nLevel 1: Format       10       10  ✅\nLevel 2: Writing\n  - Structure          6        6  ✅\n  - Description        8        8  ✅\n  - Example density    1        3  ⚠️\n  - Organization       6        6  ✅\n  - Actionability     10       10  ✅\nLevel 3: Functional    0       20  ❌ CRITICAL\nLevel 4: Best Practices\n  - Progressive       5        5  ✅\n  - Resources         5        5  ✅\n  - Triggering        5        5  ✅\nLevel 5: Optimization  0       10  (recommendations provided)\n)\nLevel 6: Workflow      0       20  ❌ CRITICAL\n─────────────────────────────────────\nTOTAL                 56       116\n\nRATING: 56/116 = Fair — significant gaps to address\nVERDICT: REWORK (functional and workflow verification failed)\n\nTop Defects\n\n1. Functional Mismatch: AGENTS.md template missing critical OpenClaw specifications.\n\n2. Workflow Incomplete: Missing agent registration, configuration verification, backup mechanisms, error handling, and failure recovery strategies.\n\nRecommendation\nUpdate references/templates.md AGENTS.md template with all required sections\nAdd Phase 2.5 (agent registration with openclaw agents add)\nAdd Phase 2.6 (configuration verification)\nAdd backup mechanism before config changes\nAdd failure recovery strategies to each phase\nAdd directory creation error handling\nAdd Phase 8 (automated testing)\nClarify Feishu binding options in Phase 1\nAdd optional systemd service configuration\nReview Workflow Guide\nLevel 1: Format Validation\n\nRun automatic validation using package_skill.py:\n\npython3 /home/yupeng/.npm-global/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py <skill-path>\n\nLevel 2: Writing Quality Assessment\n\nCheck structure, description, examples, organization, and actionability.\n\nLevel 3: Functional Verification\n\nFor OpenClaw skills, compare generated templates with actual specifications.\n\nLevel 4: Best Practices Check\n\nVerify progressive disclosure, resource organization, and triggering accuracy.\n\nLevel 5: Optimization Recommendations\n\nProvide prioritized recommendations (Critical/Major/Minor).\n\nLevel 6: Workflow Validation (For Workflow Tools)\nWorkflow Completeness Check\nWORKFLOW COMPLETENESS CHECK:\n\n[ ] Each phase has clear operational steps\n[ ] Correct CLI commands are used\n[ ] Error handling is documented\n[ ] Backup and recovery mechanisms exist\n[ ] Verification steps are included\n[ ] Configuration management is documented\n[ ] Failure recovery strategies exist\n\nPhase-by-Phase Validation\n\nFor each phase in the workflow:\n\nPHASE VALIDATION CHECKLIST:\n\nPhase: [phase name]\n\nOperational Steps:\n[ ] Clear, step-by-step instructions provided\n[ ] Commands are accurate and complete\n[ ] Required parameters are specified\n\nError Handling:\n[ ] Common errors are documented\n[ ] Recovery steps are provided\n[ ] Error messages are explained\n\nVerification:\n[ ] Success criteria are defined\n[ ] Verification steps are included\n[ ] How to confirm completion is explained\n\nDependencies:\n[ ] Prerequisites are listed\n[ ] Order dependencies are clear\n[ ] Previous phase completion is verified\n\nCLI Command Validation\n\nFor workflow tools that use OpenClaw CLI commands:\n\nCLI COMMAND VALIDATION:\n\n[ ] Commands are verified with `openclaw <command> --help`\n[ ] Command syntax is correct\n[ ] Required options are documented\n[ ] Default values are explained\n[ ] Example commands are runnable\n\nConfiguration Management\n\nFor tools that modify OpenClaw configuration:\n\nCONFIGURATION MANAGEMENT CHECK:\n\n[ ] Files being modified are listed\n[ ] Backup mechanism is provided\n[ ] Rollback steps are documented\n[ ] Configuration validation is included\n[ ] Authentication requirements are explained\n\nCommon Defects\nCritical\nInvalid frontmatter\nBroken code examples\nMisleading description\nFunctional mismatch (OpenClaw skills)\nWorkflow incomplete (missing phases, no CLI commands)\nNo backup before config changes\nMajor\nNo \"When to Use\" information\nText walls without examples\nExamples missing language tags\nAbstract organization\nDuplication between SKILL.md and references\nNo error handling\nNo verification steps\nNo failure recovery strategies\nMinor\nPlaceholder values\nInconsistent formatting\nExtraneous files\nMissing cross-references\nNo quick start guide\nLanguage Adaptation Guidelines\n\nCRITICAL: Always respond in the same language as the user's request.\n\nDetection Rules\n\nDetect user language from the request message\n\nCheck the language of the user's input message\nUse the same language for all responses\n\nLanguage mapping\n\nChinese (中文/汉语) → Respond in Chinese\nEnglish → Respond in English\nJapanese (日本語) → Respond in Japanese\nKorean (한국어) → Respond in Korean\nOther languages → Respond in the detected language\n\nConsistency\n\nOnce language is detected, use it for the entire review\nAll section headers, descriptions, and feedback should be in the same language\nTechnical terms (like \"Level 1\", \"Level 2\") can remain in English if they are standard terminology\nExample Scenarios\n\nScenario 1: User asks in Chinese\n\nUser: 请审查一下 agent-builder-plus 这个 skill\nAI: (responds in Chinese)\n## 审查结果：agent-builder-plus\n...\n\n\nScenario 2: User asks in English\n\nUser: Please review the agent-builder-plus skill\nAI: (responds in English)\n## Review Results: agent-builder-plus\n...\n\n\nScenario 3: User asks in mixed language\n\nUser: 请审查 agent-builder-plus skill\nAI: (responds in Chinese, as the primary language is Chinese)\n## 审查结果：agent-builder-plus\n...\n\nImplementation Notes\nLanguage detection should be done at the start of the review\nUse simple language detection (check for Chinese characters, etc.)\nIf language cannot be detected, default to the language of the previous interaction\nMaintain language consistency throughout the entire review process\nTechnical Terms\n\nKeep technical terms in English when appropriate:\n\nSkill names (e.g., \"agent-builder-plus\")\nFile names (e.g., \"SKILL.md\", \"IDENTITY.md\")\nCLI commands (e.g., \"openclaw agents add\")\nTechnical concepts (e.g., \"workspace\", \"agent\", \"channel\")\n\nBut translate descriptions, feedback, and explanations to the user's language."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/YKaiXu/skill-reviewer-pro",
    "publisherUrl": "https://clawhub.ai/YKaiXu/skill-reviewer-pro",
    "owner": "YKaiXu",
    "version": "2.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-reviewer-pro",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-reviewer-pro",
    "agentUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-reviewer-pro/agent.md"
  }
}