{ "schemaVersion": "1.0", "item": { "slug": "multi-agent-dev-team", "name": "Multi-Agent Dev Team", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ChloePark85/multi-agent-dev-team", "canonicalUrl": "https://clawhub.ai/ChloePark85/multi-agent-dev-team", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/multi-agent-dev-team", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=multi-agent-dev-team", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "agents/dev-agent/SOUL.md", "agents/pm-agent/SOUL.md", "examples/landing-page-example.md", "package.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/multi-agent-dev-team" }, "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/multi-agent-dev-team", "agentPageUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/agent", "manifestUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/agent.json", "briefUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Multi-Agent Dev Team", "body": "2-agent collaborative software development workflow for OpenClaw\n\nBuild complete software projects using AI agents that work together like a real development team." }, { "title": "What is this?", "body": "The Multi-Agent Dev Team skill provides a PM (Project Manager) and Dev (Developer) agent that collaborate to build software projects. You describe what you want, the PM breaks it down into tasks, and the Dev agent implements them.\n\nPerfect for:\n\nLanding pages and websites\nSmall web applications\nPrototypes and MVPs\nCode generation projects\nLearning multi-agent workflows" }, { "title": "1. Install the skill", "body": "npx clawhub install multi-agent-dev-team" }, { "title": "2. Set up agents", "body": "The skill includes two pre-configured agents:\n\nPM Agent (multi-agent-pm)\n\nHandles project planning\nCoordinates the Dev agent\nReports progress to you\n\nDev Agent (multi-agent-dev)\n\nImplements code\nTests functionality\nCommits to Git" }, { "title": "3. Configure in ~/.openclaw/config.yaml", "body": "agents:\n multi-agent-pm:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md\n model: anthropic/claude-sonnet-4-5-20250929 # or your preferred model\n \n multi-agent-dev:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/dev-agent/SOUL.md\n model: google/gemini-2.5-flash # faster for code generation" }, { "title": "4. Start your PM agent", "body": "openclaw chat --agent multi-agent-pm" }, { "title": "Building a Landing Page", "body": "You (Director):\n\nBuild me a Next.js landing page with hero section, features, and contact form. Use Tailwind CSS and TypeScript.\n\nPM Agent:\n\nI'll break this down into a clear task for the Dev agent. Starting now...\n[Spawns Dev agent with detailed spec]\nDev agent is working on the project. I'll monitor progress and report back when complete.\n\nPM Agent (later):\n\n✅ Landing page completed!\nDeliverables:\n\nNext.js 14+ App Router project\nHero, Features, Contact sections\nFully responsive design\nTypeScript + Tailwind CSS\nGit repository initialized\n\nLocation: ~/projects/my-landing-page/\nReady for deployment. Would you like me to deploy to Vercel?" }, { "title": "Architecture", "body": "You (Director)\n ↓\nPM Agent (Orchestrator)\n ↓\nDev Agent (Implementer)\n ↓\nWorking Code" }, { "title": "Workflow", "body": "You describe your project to the PM agent\nPM creates a structured task specification\nPM spawns Dev agent with the spec\nDev implements the code\nPM reviews the deliverables\nPM reports completion (or requests revisions)\nRepeat steps 4-6 if needed (max 3 iterations)" }, { "title": "Task Specification Format", "body": "The PM agent uses this template to communicate with Dev:\n\n## Project: [NAME]\n## Task: [ACTION]\n\n## Requirements:\n1. [Requirement 1]\n2. [Requirement 2]\n\n## Technical Constraints:\n- [Constraint 1]\n- [Constraint 2]\n\n## Acceptance Criteria:\n- [ ] [Criterion 1]\n- [ ] [Criterion 2]\n\n## Deliverables:\n- [Deliverable 1]\n- [Deliverable 2]" }, { "title": "✅ Works Great", "body": "Next.js landing pages & apps\nReact components & SPAs\nNode.js scripts & APIs\nTypeScript projects\nStatic sites (HTML/CSS/JS)\nDocumentation sites" }, { "title": "⚠️ Limited Support", "body": "Complex backend systems (use Pro version)\nReal-time applications\nMulti-service architectures\nMobile apps" }, { "title": "❌ Not Recommended", "body": "Large enterprise systems\nMission-critical production code without human review\nProjects requiring specialized agents (use Pro version)" }, { "title": "Agent Models", "body": "PM Agent (orchestration):\n\nanthropic/claude-sonnet-4-5 - Best reasoning\ngoogle/gemini-2.5-flash - Fast & efficient\nopenai/gpt-4o - Balanced\n\nDev Agent (code generation):\n\ngoogle/gemini-2.5-flash - Fast iteration (recommended)\nanthropic/claude-sonnet-4-5 - Higher quality\nopenai/gpt-4o-mini - Budget-friendly" }, { "title": "Workspace Configuration", "body": "Set a dedicated workspace for projects:\n\nagents:\n multi-agent-pm:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md\n model: anthropic/claude-sonnet-4-5-20250929\n cwd: ~/dev-projects # All projects created here" }, { "title": "1. Start Small", "body": "Don't ask for everything at once. Start with an MVP:\n\n❌ Bad:\n\nBuild a full e-commerce site with user auth, payments, admin dashboard, and inventory management.\n\n✅ Good:\n\nBuild a simple product landing page with hero, features, and signup form." }, { "title": "2. Be Specific", "body": "The more specific your requirements, the better the result:\n\n❌ Vague:\n\nMake a nice website.\n\n✅ Specific:\n\nCreate a Next.js landing page with:\n\nHero section with CTA button\n3-column feature grid\nContact form with email validation\nTailwind CSS styling\nDark mode support" }, { "title": "3. Iterate Incrementally", "body": "Build in phases:\n\nPhase 1: Basic structure\nPhase 2: Add features\nPhase 3: Polish & deploy" }, { "title": "4. Review Output", "body": "Always review the generated code before deploying. The agents are good, but human oversight is important." }, { "title": "5. Provide Examples", "body": "If you have a specific style or pattern in mind, share examples:\n\nBuild a landing page similar to https://example.com, but for [your product]." }, { "title": "\"Dev agent didn't complete the task\"", "body": "Check:\n\nWas the task specification clear?\nAre required tools available (Node.js, Git)?\nDid the agent hit resource limits?\n\nSolution:\n\nSimplify the task\nCheck PM agent logs via sessions_history\nTry again with clearer requirements" }, { "title": "\"Code doesn't work\"", "body": "Check:\n\nDependencies installed? (npm install)\nEnvironment variables set?\nCorrect Node.js version?\n\nSolution:\n\nAsk PM agent: \"The code has errors. Please review and fix.\"\nThe PM will spawn Dev again for corrections" }, { "title": "\"Task took too long\"", "body": "Solutions:\n\nBreak into smaller tasks\nUse faster model for Dev agent (gemini-2.5-flash)\nSimplify requirements" }, { "title": "Example 1: Simple Landing Page", "body": "You: Build a landing page for a SaaS product called \"TaskFlow\". \nInclude hero, features (3 cards), and pricing table. Use Next.js \nand Tailwind CSS.\n\nPM: Working on it... \n[2 minutes later]\nPM: ✅ TaskFlow landing page complete! Ready for deployment." }, { "title": "Example 2: React Component Library", "body": "You: Create a reusable Button component library with variants \n(primary, secondary, outline) and sizes (sm, md, lg). Use \nTypeScript and class-variance-authority.\n\nPM: Task received. Spawning Dev agent...\n[3 minutes later]\nPM: ✅ Button component library complete with Storybook examples." }, { "title": "Example 3: API Integration", "body": "You: Build a Next.js app that fetches and displays GitHub user \nprofiles. Include search functionality and responsive cards.\n\nPM: Starting development...\n[4 minutes later]\nPM: ✅ GitHub profile viewer complete with search and error handling." }, { "title": "Upgrading to Pro", "body": "Want more power? Upgrade to Multi-Agent Dev Team Pro ($49):" }, { "title": "Pro Features", "body": "🎯 6 specialized agents: PM, Architect, Dev, QA, DevOps, BizDev\n🔄 Lobster pipelines: Automated workflows with approval gates\n🏗️ Architecture design: Dedicated agent for system design\n✅ Automated QA: Code review & testing agent\n🚀 DevOps automation: Deployment & CI/CD setup\n💼 Business planning: Market research & strategy agent\n📚 Comprehensive guides: English + Korean setup docs\n\nGet Pro →" }, { "title": "Support", "body": "📖 Documentation: docs.openclaw.ai\n💬 Discord: discord.com/invite/clawd\n🐛 Issues: github.com/openclaw/openclaw\n📧 Email: support@ubik.systems" }, { "title": "License", "body": "MIT License - See LICENSE file for details" }, { "title": "Credits", "body": "Built by UBIK Collective\n\nPowered by OpenClaw\n\nReady to build with AI agents? Install now:\n\nnpx clawhub install multi-agent-dev-team" } ], "body": "Multi-Agent Dev Team\n\n2-agent collaborative software development workflow for OpenClaw\n\nBuild complete software projects using AI agents that work together like a real development team.\n\nWhat is this?\n\nThe Multi-Agent Dev Team skill provides a PM (Project Manager) and Dev (Developer) agent that collaborate to build software projects. You describe what you want, the PM breaks it down into tasks, and the Dev agent implements them.\n\nPerfect for:\n\nLanding pages and websites\nSmall web applications\nPrototypes and MVPs\nCode generation projects\nLearning multi-agent workflows\nQuick Start\n1. Install the skill\nnpx clawhub install multi-agent-dev-team\n\n2. Set up agents\n\nThe skill includes two pre-configured agents:\n\nPM Agent (multi-agent-pm)\n\nHandles project planning\nCoordinates the Dev agent\nReports progress to you\n\nDev Agent (multi-agent-dev)\n\nImplements code\nTests functionality\nCommits to Git\n3. Configure in ~/.openclaw/config.yaml\nagents:\n multi-agent-pm:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md\n model: anthropic/claude-sonnet-4-5-20250929 # or your preferred model\n \n multi-agent-dev:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/dev-agent/SOUL.md\n model: google/gemini-2.5-flash # faster for code generation\n\n4. Start your PM agent\nopenclaw chat --agent multi-agent-pm\n\nUsage Example\nBuilding a Landing Page\n\nYou (Director):\n\nBuild me a Next.js landing page with hero section, features, and contact form. Use Tailwind CSS and TypeScript.\n\nPM Agent:\n\nI'll break this down into a clear task for the Dev agent. Starting now...\n\n[Spawns Dev agent with detailed spec]\n\nDev agent is working on the project. I'll monitor progress and report back when complete.\n\nPM Agent (later):\n\n✅ Landing page completed!\n\nDeliverables:\n\nNext.js 14+ App Router project\nHero, Features, Contact sections\nFully responsive design\nTypeScript + Tailwind CSS\nGit repository initialized\n\nLocation: ~/projects/my-landing-page/\n\nReady for deployment. Would you like me to deploy to Vercel?\n\nHow It Works\nArchitecture\nYou (Director)\n ↓\nPM Agent (Orchestrator)\n ↓\nDev Agent (Implementer)\n ↓\nWorking Code\n\nWorkflow\nYou describe your project to the PM agent\nPM creates a structured task specification\nPM spawns Dev agent with the spec\nDev implements the code\nPM reviews the deliverables\nPM reports completion (or requests revisions)\nRepeat steps 4-6 if needed (max 3 iterations)\nTask Specification Format\n\nThe PM agent uses this template to communicate with Dev:\n\n## Project: [NAME]\n## Task: [ACTION]\n\n## Requirements:\n1. [Requirement 1]\n2. [Requirement 2]\n\n## Technical Constraints:\n- [Constraint 1]\n- [Constraint 2]\n\n## Acceptance Criteria:\n- [ ] [Criterion 1]\n- [ ] [Criterion 2]\n\n## Deliverables:\n- [Deliverable 1]\n- [Deliverable 2]\n\nSupported Project Types\n✅ Works Great\nNext.js landing pages & apps\nReact components & SPAs\nNode.js scripts & APIs\nTypeScript projects\nStatic sites (HTML/CSS/JS)\nDocumentation sites\n⚠️ Limited Support\nComplex backend systems (use Pro version)\nReal-time applications\nMulti-service architectures\nMobile apps\n❌ Not Recommended\nLarge enterprise systems\nMission-critical production code without human review\nProjects requiring specialized agents (use Pro version)\nConfiguration Options\nAgent Models\n\nPM Agent (orchestration):\n\nanthropic/claude-sonnet-4-5 - Best reasoning\ngoogle/gemini-2.5-flash - Fast & efficient\nopenai/gpt-4o - Balanced\n\nDev Agent (code generation):\n\ngoogle/gemini-2.5-flash - Fast iteration (recommended)\nanthropic/claude-sonnet-4-5 - Higher quality\nopenai/gpt-4o-mini - Budget-friendly\nWorkspace Configuration\n\nSet a dedicated workspace for projects:\n\nagents:\n multi-agent-pm:\n soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md\n model: anthropic/claude-sonnet-4-5-20250929\n cwd: ~/dev-projects # All projects created here\n\nBest Practices\n1. Start Small\n\nDon't ask for everything at once. Start with an MVP:\n\n❌ Bad:\n\nBuild a full e-commerce site with user auth, payments, admin dashboard, and inventory management.\n\n✅ Good:\n\nBuild a simple product landing page with hero, features, and signup form.\n\n2. Be Specific\n\nThe more specific your requirements, the better the result:\n\n❌ Vague:\n\nMake a nice website.\n\n✅ Specific:\n\nCreate a Next.js landing page with:\n\nHero section with CTA button\n3-column feature grid\nContact form with email validation\nTailwind CSS styling\nDark mode support\n3. Iterate Incrementally\n\nBuild in phases:\n\nPhase 1: Basic structure Phase 2: Add features Phase 3: Polish & deploy\n\n4. Review Output\n\nAlways review the generated code before deploying. The agents are good, but human oversight is important.\n\n5. Provide Examples\n\nIf you have a specific style or pattern in mind, share examples:\n\nBuild a landing page similar to https://example.com, but for [your product].\n\nTroubleshooting\n\"Dev agent didn't complete the task\"\n\nCheck:\n\nWas the task specification clear?\nAre required tools available (Node.js, Git)?\nDid the agent hit resource limits?\n\nSolution:\n\nSimplify the task\nCheck PM agent logs via sessions_history\nTry again with clearer requirements\n\"Code doesn't work\"\n\nCheck:\n\nDependencies installed? (npm install)\nEnvironment variables set?\nCorrect Node.js version?\n\nSolution:\n\nAsk PM agent: \"The code has errors. Please review and fix.\"\nThe PM will spawn Dev again for corrections\n\"Task took too long\"\n\nSolutions:\n\nBreak into smaller tasks\nUse faster model for Dev agent (gemini-2.5-flash)\nSimplify requirements\nExamples\nExample 1: Simple Landing Page\nYou: Build a landing page for a SaaS product called \"TaskFlow\". \nInclude hero, features (3 cards), and pricing table. Use Next.js \nand Tailwind CSS.\n\nPM: Working on it... \n[2 minutes later]\nPM: ✅ TaskFlow landing page complete! Ready for deployment.\n\nExample 2: React Component Library\nYou: Create a reusable Button component library with variants \n(primary, secondary, outline) and sizes (sm, md, lg). Use \nTypeScript and class-variance-authority.\n\nPM: Task received. Spawning Dev agent...\n[3 minutes later]\nPM: ✅ Button component library complete with Storybook examples.\n\nExample 3: API Integration\nYou: Build a Next.js app that fetches and displays GitHub user \nprofiles. Include search functionality and responsive cards.\n\nPM: Starting development...\n[4 minutes later]\nPM: ✅ GitHub profile viewer complete with search and error handling.\n\nUpgrading to Pro\n\nWant more power? Upgrade to Multi-Agent Dev Team Pro ($49):\n\nPro Features\n🎯 6 specialized agents: PM, Architect, Dev, QA, DevOps, BizDev\n🔄 Lobster pipelines: Automated workflows with approval gates\n🏗️ Architecture design: Dedicated agent for system design\n✅ Automated QA: Code review & testing agent\n🚀 DevOps automation: Deployment & CI/CD setup\n💼 Business planning: Market research & strategy agent\n📚 Comprehensive guides: English + Korean setup docs\n\nGet Pro →\n\nSupport\n📖 Documentation: docs.openclaw.ai\n💬 Discord: discord.com/invite/clawd\n🐛 Issues: github.com/openclaw/openclaw\n📧 Email: support@ubik.systems\nLicense\n\nMIT License - See LICENSE file for details\n\nCredits\n\nBuilt by UBIK Collective\n\nPowered by OpenClaw\n\nReady to build with AI agents? Install now:\n\nnpx clawhub install multi-agent-dev-team" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ChloePark85/multi-agent-dev-team", "publisherUrl": "https://clawhub.ai/ChloePark85/multi-agent-dev-team", "owner": "ChloePark85", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/multi-agent-dev-team", "downloadUrl": "https://openagent3.xyz/downloads/multi-agent-dev-team", "agentUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/agent", "manifestUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/agent.json", "briefUrl": "https://openagent3.xyz/skills/multi-agent-dev-team/agent.md" } }