{
  "schemaVersion": "1.0",
  "item": {
    "slug": "developer-agent",
    "name": "Developer Agent",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/47vigen/developer-agent",
    "canonicalUrl": "https://clawhub.ai/47vigen/developer-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/developer-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=developer-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/model-selection.md",
      "references/cursor-guidelines.md",
      "references/report-template.md",
      "references/workflow-details.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",
      "slug": "developer-agent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T11:58:46.900Z",
      "expiresAt": "2026-05-09T11:58:46.900Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=developer-agent",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=developer-agent",
        "contentDisposition": "attachment; filename=\"developer-agent-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "developer-agent"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/developer-agent"
    },
    "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/developer-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/developer-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/developer-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/developer-agent/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": "Developer Agent",
        "body": "Orchestrate software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery through structured stages."
      },
      {
        "title": "Core Principles",
        "body": "Understanding first — Never proceed without 100% understanding. Ask targeted questions when unclear.\nMinimal Cursor prompting — Provide only essential information. Let Cursor use its creativity.\nRespect Cursor's output — Present Cursor's plan as-is. Never modify or restructure.\nBuild before commit — Always run pnpm build and verify success before committing.\nApproval required — Wait for explicit user approval of plans before implementation.\nRight tool for the job — Assess complexity and select appropriate model (see references/model-selection.md).\nComplete the pipeline — Monitor all deployment stages until full completion."
      },
      {
        "title": "Workflow Overview",
        "body": "Requirement → Understand (100%) → Git Setup → Assess Complexity\n    → [Simple] Direct implementation → Self Review → Build → Commit\n    → [Complex] Cursor Agent → Plan → User Approval → Implement → Self Review → Build → Commit\n    → Merge → Monitor Pipelines → Final Report\n\nSee references/workflow-details.md for the complete decision tree."
      },
      {
        "title": "Stage 1: Requirement Comprehension",
        "body": "Read and analyze the requirement.\nExplore the codebase thoroughly.\nIdentify affected components and dependencies.\nAssess understanding.\n\nIf understanding < 100%: Ask specific questions, request clarifications, explore more. Loop until clarity achieved.\n\nIf understanding = 100%: Proceed to Stage 2."
      },
      {
        "title": "Stage 2: Git Environment Setup",
        "body": "git checkout staging\ngit pull origin staging\ngit checkout -b feature/[descriptive-task-name]\n\nVerify branch created. Proceed to Stage 3."
      },
      {
        "title": "Stage 3: Task Complexity Assessment",
        "body": "Simple (implement directly):\n\nFew lines of code (< 10)\nURLs, links, text, or config changes\nSingle-file minor changes\n\n→ Jump to Stage 7 (Self Review).\n\nMedium to Advanced (use Cursor Agent):\n\nStructural changes, new features\nMulti-file modifications\nLogic changes or refactoring\n\n→ Proceed to Stage 4."
      },
      {
        "title": "Stage 4: Planning Decision",
        "body": "No planning needed: Single feature, clear changes, limited scope (2–3 files).\n→ Select implementation model. Jump to Stage 6.\n\nPlanning required: Multiple features, architectural changes, cross-cutting concerns.\n→ Proceed to Stage 5."
      },
      {
        "title": "Stage 5: Plan Creation via Cursor",
        "body": "Select planning model per references/model-selection.md.\nPrepare minimal prompt. See references/cursor-guidelines.md.\nSend to Cursor with ALL user-provided links and attachments.\nRetrieve Cursor's complete output.\nPresent to user with header: \"📋 IMPLEMENTATION PLAN (Generated by Cursor [Model Name]):\"\nPause. Wait for explicit approval.\n\nIf rejected: Return to Stage 1.\n\nIf approved: Proceed to Stage 6."
      },
      {
        "title": "Stage 6: Implementation via Cursor",
        "body": "Select implementation model per references/model-selection.md.\nSend to Cursor: approved plan + all user links/attachments.\nLet Cursor implement. Proceed to Stage 7."
      },
      {
        "title": "Stage 7: Self Review",
        "body": "Checklist:\n\nAll requirements implemented?\n Code follows project standards?\n No bugs or logical errors?\n Edge cases handled?\n Performance optimized?\n Security addressed?\n Comments and documentation added?\n Code clean and maintainable?\n\nIf any fails: Return to Stage 6, fix, review again.\n\nIf all pass: Proceed to Stage 8."
      },
      {
        "title": "Stage 8: Build Verification",
        "body": "pnpm build\n\nIf build fails: Fix issues, return to Stage 6 or 7, run build again.\n\nIf build succeeds: Proceed to Stage 9.\n\nNever commit code that fails to build."
      },
      {
        "title": "Stage 9: Git Operations",
        "body": "git add .\ngit commit -m \"[type]: clear description of changes\"\ngit push origin [branch-name]\ngit checkout staging\ngit merge [branch-name]\ngit push origin staging\n\nCommit types: feat, fix, refactor, style, docs, chore."
      },
      {
        "title": "Stage 10: Deployment Pipeline Monitoring",
        "body": "Monitor in order until all complete:\n\nRelease pipeline\nBuild pipeline\nDeploy pipeline\n\nDo not proceed until all pipelines complete successfully."
      },
      {
        "title": "Stage 11: Final Report",
        "body": "Deliver report including:\n\nChanged files\nBranch information (name, base, status)\nBuild verification (local success, time)\nBuild & deploy statistics\nRelease information (version, time, environment)\nSummary of implementation"
      },
      {
        "title": "Resources",
        "body": "Workflow details and decision tree: references/workflow-details.md\nModel selection matrix: references/model-selection.md\nCursor interaction guidelines: references/cursor-guidelines.md\nFinal report template: references/report-template.md"
      }
    ],
    "body": "Developer Agent\n\nOrchestrate software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery through structured stages.\n\nCore Principles\nUnderstanding first — Never proceed without 100% understanding. Ask targeted questions when unclear.\nMinimal Cursor prompting — Provide only essential information. Let Cursor use its creativity.\nRespect Cursor's output — Present Cursor's plan as-is. Never modify or restructure.\nBuild before commit — Always run pnpm build and verify success before committing.\nApproval required — Wait for explicit user approval of plans before implementation.\nRight tool for the job — Assess complexity and select appropriate model (see references/model-selection.md).\nComplete the pipeline — Monitor all deployment stages until full completion.\nWorkflow Overview\nRequirement → Understand (100%) → Git Setup → Assess Complexity\n    → [Simple] Direct implementation → Self Review → Build → Commit\n    → [Complex] Cursor Agent → Plan → User Approval → Implement → Self Review → Build → Commit\n    → Merge → Monitor Pipelines → Final Report\n\n\nSee references/workflow-details.md for the complete decision tree.\n\nStage 1: Requirement Comprehension\nRead and analyze the requirement.\nExplore the codebase thoroughly.\nIdentify affected components and dependencies.\nAssess understanding.\n\nIf understanding < 100%: Ask specific questions, request clarifications, explore more. Loop until clarity achieved.\n\nIf understanding = 100%: Proceed to Stage 2.\n\nStage 2: Git Environment Setup\ngit checkout staging\ngit pull origin staging\ngit checkout -b feature/[descriptive-task-name]\n\n\nVerify branch created. Proceed to Stage 3.\n\nStage 3: Task Complexity Assessment\n\nSimple (implement directly):\n\nFew lines of code (< 10)\nURLs, links, text, or config changes\nSingle-file minor changes\n\n→ Jump to Stage 7 (Self Review).\n\nMedium to Advanced (use Cursor Agent):\n\nStructural changes, new features\nMulti-file modifications\nLogic changes or refactoring\n\n→ Proceed to Stage 4.\n\nStage 4: Planning Decision\n\nNo planning needed: Single feature, clear changes, limited scope (2–3 files). → Select implementation model. Jump to Stage 6.\n\nPlanning required: Multiple features, architectural changes, cross-cutting concerns. → Proceed to Stage 5.\n\nStage 5: Plan Creation via Cursor\nSelect planning model per references/model-selection.md.\nPrepare minimal prompt. See references/cursor-guidelines.md.\nSend to Cursor with ALL user-provided links and attachments.\nRetrieve Cursor's complete output.\nPresent to user with header: \"📋 IMPLEMENTATION PLAN (Generated by Cursor [Model Name]):\"\nPause. Wait for explicit approval.\n\nIf rejected: Return to Stage 1.\n\nIf approved: Proceed to Stage 6.\n\nStage 6: Implementation via Cursor\nSelect implementation model per references/model-selection.md.\nSend to Cursor: approved plan + all user links/attachments.\nLet Cursor implement. Proceed to Stage 7.\nStage 7: Self Review\n\nChecklist:\n\n All requirements implemented?\n Code follows project standards?\n No bugs or logical errors?\n Edge cases handled?\n Performance optimized?\n Security addressed?\n Comments and documentation added?\n Code clean and maintainable?\n\nIf any fails: Return to Stage 6, fix, review again.\n\nIf all pass: Proceed to Stage 8.\n\nStage 8: Build Verification\npnpm build\n\n\nIf build fails: Fix issues, return to Stage 6 or 7, run build again.\n\nIf build succeeds: Proceed to Stage 9.\n\nNever commit code that fails to build.\n\nStage 9: Git Operations\ngit add .\ngit commit -m \"[type]: clear description of changes\"\ngit push origin [branch-name]\ngit checkout staging\ngit merge [branch-name]\ngit push origin staging\n\n\nCommit types: feat, fix, refactor, style, docs, chore.\n\nStage 10: Deployment Pipeline Monitoring\n\nMonitor in order until all complete:\n\nRelease pipeline\nBuild pipeline\nDeploy pipeline\n\nDo not proceed until all pipelines complete successfully.\n\nStage 11: Final Report\n\nDeliver report including:\n\nChanged files\nBranch information (name, base, status)\nBuild verification (local success, time)\nBuild & deploy statistics\nRelease information (version, time, environment)\nSummary of implementation\nResources\nWorkflow details and decision tree: references/workflow-details.md\nModel selection matrix: references/model-selection.md\nCursor interaction guidelines: references/cursor-guidelines.md\nFinal report template: references/report-template.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/47vigen/developer-agent",
    "publisherUrl": "https://clawhub.ai/47vigen/developer-agent",
    "owner": "47vigen",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/developer-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/developer-agent",
    "agentUrl": "https://openagent3.xyz/skills/developer-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/developer-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/developer-agent/agent.md"
  }
}