{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claude-code-mastery",
    "name": "Claude Code Mastery",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/cheenu1092-oss/claude-code-mastery",
    "canonicalUrl": "https://clawhub.ai/cheenu1092-oss/claude-code-mastery",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "manual_only",
    "downloadUrl": "/downloads/claude-code-mastery",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claude-code-mastery",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CONTRIBUTING.md",
      "README.md",
      "SKILL.md",
      "agents/ai-engineer.md",
      "agents/backend-dev.md",
      "agents/data-engineer.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Open the source page and confirm the package flow manually.",
      "Review SKILL.md if you can obtain the files.",
      "Treat this source as manual setup until the download is verified."
    ],
    "agentAssist": {
      "summary": "Use the source page and any available docs to guide the install because the item currently does not return a direct package file.",
      "steps": [
        "Open the source page via Open source listing.",
        "If you can obtain the package, extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the source page and extracted files."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks."
        },
        {
          "label": "Upgrade existing",
          "body": "I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "claude-code-mastery",
      "status": "source_issue",
      "reason": "not_found",
      "recommendedAction": "review_source",
      "checkedAt": "2026-05-01T11:30:28.274Z",
      "expiresAt": "2026-05-02T11:30:28.274Z",
      "httpStatus": 404,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claude-code-mastery",
      "contentType": "text/plain",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claude-code-mastery",
        "contentDisposition": null,
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "claude-code-mastery"
      },
      "scope": "item",
      "summary": "Known item issue.",
      "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.",
      "primaryActionLabel": "Open source listing",
      "primaryActionHref": "https://clawhub.ai/cheenu1092-oss/claude-code-mastery"
    },
    "validation": {
      "installChecklist": [
        "Open the source listing and confirm there is a real package or setup artifact available.",
        "Review SKILL.md before asking your agent to continue.",
        "Treat this source as manual setup until the upstream download flow is fixed."
      ],
      "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/claude-code-mastery",
    "agentPageUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent.md"
  },
  "agentAssist": {
    "summary": "Use the source page and any available docs to guide the install because the item currently does not return a direct package file.",
    "steps": [
      "Open the source page via Open source listing.",
      "If you can obtain the package, extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the source page and extracted files."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks."
      },
      {
        "label": "Upgrade existing",
        "body": "I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Claude Code Mastery",
        "body": "Complete skill for setting up, optimizing, and mastering Claude Code with a full development team of subagents.\n\nOfficial Docs: https://code.claude.com/docs"
      },
      {
        "title": "⚡ Quick Check: Is Setup Complete?",
        "body": "Run this first:\n\ncommand -v claude >/dev/null && echo \"✅ Claude Code installed - SKIP to 'Daily Use' section\" || echo \"❌ Not installed - follow 'First-Time Setup' below\"\n\nIf Claude Code is already installed, skip directly to the \"Daily Use\" section below."
      },
      {
        "title": "🔧 FIRST-TIME SETUP (Skip if already installed)",
        "body": "Note to bot: Only follow this section if Claude Code is NOT installed. Check with the command above. Once setup is complete, this section can be ignored on future invocations."
      },
      {
        "title": "Setup Scripts",
        "body": "Run these in order:\n\ncd ~/clawd/skills/claude-code-mastery/scripts\n\n# 1. Check dependencies\n./01-check-dependencies.sh\n\n# 2. Install Claude Code\n./02-install-claude-code.sh\n\n# 3. Authenticate\n./03-first-time-auth.sh\n\n# 4. Install dev team subagents\n./04-install-subagents.sh              # Starter pack (3 agents) - recommended\n./04-install-subagents.sh --full-team  # All 11 agents\n\n# 5. (Optional) Persistent memory - prompts y/N, default No\n./05-setup-claude-mem.sh               # Interactive prompt\n./05-setup-claude-mem.sh --skip        # Skip entirely\n./05-setup-claude-mem.sh --yes         # Install without prompting"
      },
      {
        "title": "Configuration",
        "body": "Edit config.sh to customize:\n\nVALID_MODELS — Add models as Anthropic releases them\nHEARTBEAT_DIAGNOSTICS — Enable/disable in heartbeat (default: false)\nINSTALL_MODE — Default to \"starter\" or \"full\""
      },
      {
        "title": "Setup Gotchas",
        "body": "IssueSolution\"Command not found\"Add ~/.local/bin to PATHAuth errorsRun ./03-first-time-auth.shSlow startupFirst run indexes codebaseSubagents not showingRun ./04-install-subagents.sh"
      },
      {
        "title": "Post-Setup: Add Heartbeat Task",
        "body": "After setup, add the maintenance task to your HEARTBEAT.md (see \"Heartbeat Maintenance\" in Daily Use section).\n\nSetup complete! Continue to Daily Use section."
      },
      {
        "title": "📘 DAILY USE (Always relevant)",
        "body": "This section covers ongoing usage - reference this for all coding tasks."
      },
      {
        "title": "Dev Team Subagents",
        "body": "Subagents are installed to ~/.claude/agents/. Each has a \"Learn More\" section with curated links to deepen expertise."
      },
      {
        "title": "Starter Pack (Default) — 3 Core Agents",
        "body": "Most users only need these:\n\nAgentModelPurposesenior-devSonnetArchitecture, complex code, code reviewproject-managerSonnetTask breakdown, timelines, dependenciesjunior-devHaikuQuick fixes, simple tasks (fast & cheap)\n\nInstall: ./04-install-subagents.sh (or --minimal)"
      },
      {
        "title": "Full Team (Optional) — All 10 Agents",
        "body": "For larger projects, install all 11 with --full-team:\n\nAgentModelPurposesenior-devSonnetArchitecture, complex code, code reviewproject-managerSonnetTask breakdown, timelines, dependenciesjunior-devHaikuQuick fixes, simple tasks (fast & cheap)frontend-devSonnetReact, UI, CSS, client-sidebackend-devSonnetAPIs, databases, server-sideai-engineerSonnetLLM apps, RAG, prompts, agentsml-engineerSonnetML models, training, MLOpsdata-scientistSonnetSQL, analysis, statisticsdata-engineerSonnetPipelines, ETL, data infrastructureproduct-managerSonnetRequirements, user stories, prioritizationdevopsSonnetCI/CD, Docker, K8s, infrastructure, automation"
      },
      {
        "title": "Using Subagents",
        "body": "Interactive mode: Use the /agent slash command or natural language:\n\n/agent senior-dev\nUse the senior-dev agent to review this code\n\nNon-interactive mode (-p): Use the --agent flag:\n\nclaude --agent senior-dev -p \"review this code for security issues\"\nclaude --agent project-manager -p \"create a task breakdown for auth feature\"\nclaude --agent junior-dev -p \"fix the typo in README.md\"\n\nNote: Claude Code does NOT auto-delegate to subagents based on task type. You must explicitly specify which agent to use.\n\nMulti-agent handoff: For tasks needing multiple specialists, use HANDOFF.md to pass context between agents. See docs/workflows.md for the full pattern."
      },
      {
        "title": "CLI Commands",
        "body": "claude              # Start interactive\nclaude -c           # Continue previous session\nclaude -p \"prompt\"  # Non-interactive mode"
      },
      {
        "title": "Slash Commands",
        "body": "/agents   - Manage subagents\n/clear    - Clear conversation (use between tasks!)\n/compact  - Compress context\n/model    - Change model\n/help     - All commands"
      },
      {
        "title": "Keyboard Shortcuts",
        "body": "Shift+Tab - Toggle Plan mode (read-only exploration)\nCtrl+C    - Cancel operation\nCtrl+B    - Background task"
      },
      {
        "title": "Context Management (Critical!)",
        "body": "CommandWhat it doesWhen to use/clearClear conversation, start freshBetween unrelated tasks/compactSummarize and compress contextWhen context getting fullShift+TabToggle Plan mode (read-only)Exploration before implementing\n\nBest practices:\n\n/clear between unrelated tasks\nUse Plan mode for exploration before implementing\nSubagents isolate verbose operations\nCreate HANDOFF.md for session continuity"
      },
      {
        "title": "settings.json",
        "body": "Create .claude/settings.json in your project:\n\n{\n  \"model\": \"sonnet\",\n  \"permissions\": {\n    \"allow\": [\"Bash(npm:*)\", \"Bash(git:*)\", \"Read\", \"Write\", \"Edit\"],\n    \"deny\": [\"Bash(rm -rf:*)\", \"Bash(sudo:*)\"]\n  }\n}"
      },
      {
        "title": "CLAUDE.md",
        "body": "Create CLAUDE.md in your project root (Claude reads this automatically):\n\n# Project: MyApp\n\n## Tech Stack\n- Frontend: React, TypeScript, Tailwind\n- Backend: Node.js, PostgreSQL\n\n## Commands\n- `npm run dev` - Start dev server\n- `npm test` - Run tests\n\nSee examples/CLAUDE-template.md for a full template."
      },
      {
        "title": "Claude-Mem (If Installed)",
        "body": "Check status:\n\npgrep -f \"worker-service\" >/dev/null && echo \"running\" || echo \"stopped\"\n\nStart if stopped:\n\ncd ~/.claude/plugins/marketplaces/thedotmack && bun plugin/scripts/worker-service.cjs start\n\nWeb UI: http://localhost:37777"
      },
      {
        "title": "Diagnostics & Troubleshooting",
        "body": "Quick diagnostics:\n\n~/clawd/skills/claude-code-mastery/scripts/06-diagnostics.sh\n\nFull troubleshooting (if issues found):\n\n~/clawd/skills/claude-code-mastery/scripts/08-troubleshoot.sh\n\nCommon issues guide: See docs/troubleshooting.md for solutions to:\n\nAuthentication problems (API key, OAuth, logout bugs)\nInstallation issues (PATH, WSL, Node.js version)\nNetwork errors (firewalls, VPNs, proxies)\nPerformance problems (high CPU, hangs, slow search)"
      },
      {
        "title": "Heartbeat Maintenance",
        "body": "Add to your HEARTBEAT.md for automatic maintenance:\n\n## Claude Code Maintenance\n\n**Last Health Check:** [timestamp]\n**Last Learning Session:** [timestamp]\n\n### Every Heartbeat (if coding tasks active):\n1. Quick claude-mem check (if installed):\n   `pgrep -f \"worker-service\" >/dev/null && echo \"running\" || echo \"stopped\"`\n   - Only restart if stopped\n   - Note: pgrep saves ~500 tokens vs full status command\n\n### Daily (morning):\n1. Quick health check: `command -v claude && pgrep -f \"worker-service\"`\n2. Only run full diagnostics if quick check fails\n\n### Weekly (Sunday):\n1. Run: `~/clawd/skills/claude-code-mastery/scripts/07-weekly-improvement-cron.sh`\n2. Propose improvements (require human approval)\n\n### Weekly Learning & Skill Improvement (rotate through agents):\n1. Pick ONE agent file from the skill's `agents/` folder (rotate weekly)\n2. Read the \"Learn More\" section\n3. Visit 2-3 links that are relevant to current projects\n4. Internalize key concepts and update your workflows\n5. **Improve the skill itself:**\n   - Found a better resource? Add it to \"Learn More\"\n   - Discovered a new best practice? Update the agent's guidelines\n   - Link broken or outdated? Remove or replace it\n   - New tool or framework worth mentioning? Add it\n6. Commit changes locally with clear commit messages\n7. **Don't push directly to shared repos** — propose changes as a PR or request human review first\n8. Note learnings in your memory files\n\n**Rotation schedule:**\n- Week 1: senior-dev, junior-dev\n- Week 2: frontend-dev, backend-dev\n- Week 3: ai-engineer, ml-engineer\n- Week 4: data-scientist, data-engineer\n- Week 5: project-manager, product-manager\n- Week 6: devops\n\n**What to update:**\n- `agents/*.md` — Add new links, update best practices, fix outdated info\n- `SKILL.md` — Improve documentation, add tips discovered\n- `docs/*.md` — Enhance guides based on real usage\n\nWhy this matters:\n\nSkill improves over time through actual use\nLinks stay current (broken ones get fixed)\nBest practices evolve with the ecosystem\nEach Clawdbot contributes back to the skill"
      },
      {
        "title": "Scripts Reference",
        "body": "ScriptPurposeWhen to use06-diagnostics.shHealth check and status reportWhen issues occur07-weekly-improvement-cron.shGenerate improvement reportWeekly (Sunday)08-troubleshoot.shComprehensive troubleshootingWhen 06 finds issues"
      },
      {
        "title": "Summary",
        "body": "For coding tasks:\n\nUse appropriate subagent for the task\nManage context with /clear and Plan mode\nRun diagnostics if something breaks\n\nHeartbeat handles:\n\nclaude-mem health checks\nDaily quick diagnostics\nWeekly improvement research\n\nThe dev team subagents turn Claude Code into a full development organization."
      }
    ],
    "body": "Claude Code Mastery\n\nComplete skill for setting up, optimizing, and mastering Claude Code with a full development team of subagents.\n\nOfficial Docs: https://code.claude.com/docs\n\n⚡ Quick Check: Is Setup Complete?\n\nRun this first:\n\ncommand -v claude >/dev/null && echo \"✅ Claude Code installed - SKIP to 'Daily Use' section\" || echo \"❌ Not installed - follow 'First-Time Setup' below\"\n\n\nIf Claude Code is already installed, skip directly to the \"Daily Use\" section below.\n\n🔧 FIRST-TIME SETUP (Skip if already installed)\n\nNote to bot: Only follow this section if Claude Code is NOT installed. Check with the command above. Once setup is complete, this section can be ignored on future invocations.\n\nSetup Scripts\n\nRun these in order:\n\ncd ~/clawd/skills/claude-code-mastery/scripts\n\n# 1. Check dependencies\n./01-check-dependencies.sh\n\n# 2. Install Claude Code\n./02-install-claude-code.sh\n\n# 3. Authenticate\n./03-first-time-auth.sh\n\n# 4. Install dev team subagents\n./04-install-subagents.sh              # Starter pack (3 agents) - recommended\n./04-install-subagents.sh --full-team  # All 11 agents\n\n# 5. (Optional) Persistent memory - prompts y/N, default No\n./05-setup-claude-mem.sh               # Interactive prompt\n./05-setup-claude-mem.sh --skip        # Skip entirely\n./05-setup-claude-mem.sh --yes         # Install without prompting\n\nConfiguration\n\nEdit config.sh to customize:\n\nVALID_MODELS — Add models as Anthropic releases them\nHEARTBEAT_DIAGNOSTICS — Enable/disable in heartbeat (default: false)\nINSTALL_MODE — Default to \"starter\" or \"full\"\nSetup Gotchas\nIssue\tSolution\n\"Command not found\"\tAdd ~/.local/bin to PATH\nAuth errors\tRun ./03-first-time-auth.sh\nSlow startup\tFirst run indexes codebase\nSubagents not showing\tRun ./04-install-subagents.sh\nPost-Setup: Add Heartbeat Task\n\nAfter setup, add the maintenance task to your HEARTBEAT.md (see \"Heartbeat Maintenance\" in Daily Use section).\n\nSetup complete! Continue to Daily Use section.\n\n📘 DAILY USE (Always relevant)\n\nThis section covers ongoing usage - reference this for all coding tasks.\n\nDev Team Subagents\n\nSubagents are installed to ~/.claude/agents/. Each has a \"Learn More\" section with curated links to deepen expertise.\n\nStarter Pack (Default) — 3 Core Agents\n\nMost users only need these:\n\nAgent\tModel\tPurpose\nsenior-dev\tSonnet\tArchitecture, complex code, code review\nproject-manager\tSonnet\tTask breakdown, timelines, dependencies\njunior-dev\tHaiku\tQuick fixes, simple tasks (fast & cheap)\n\nInstall: ./04-install-subagents.sh (or --minimal)\n\nFull Team (Optional) — All 10 Agents\n\nFor larger projects, install all 11 with --full-team:\n\nAgent\tModel\tPurpose\nsenior-dev\tSonnet\tArchitecture, complex code, code review\nproject-manager\tSonnet\tTask breakdown, timelines, dependencies\njunior-dev\tHaiku\tQuick fixes, simple tasks (fast & cheap)\nfrontend-dev\tSonnet\tReact, UI, CSS, client-side\nbackend-dev\tSonnet\tAPIs, databases, server-side\nai-engineer\tSonnet\tLLM apps, RAG, prompts, agents\nml-engineer\tSonnet\tML models, training, MLOps\ndata-scientist\tSonnet\tSQL, analysis, statistics\ndata-engineer\tSonnet\tPipelines, ETL, data infrastructure\nproduct-manager\tSonnet\tRequirements, user stories, prioritization\ndevops\tSonnet\tCI/CD, Docker, K8s, infrastructure, automation\nUsing Subagents\n\nInteractive mode: Use the /agent slash command or natural language:\n\n/agent senior-dev\nUse the senior-dev agent to review this code\n\n\nNon-interactive mode (-p): Use the --agent flag:\n\nclaude --agent senior-dev -p \"review this code for security issues\"\nclaude --agent project-manager -p \"create a task breakdown for auth feature\"\nclaude --agent junior-dev -p \"fix the typo in README.md\"\n\n\nNote: Claude Code does NOT auto-delegate to subagents based on task type. You must explicitly specify which agent to use.\n\nMulti-agent handoff: For tasks needing multiple specialists, use HANDOFF.md to pass context between agents. See docs/workflows.md for the full pattern.\n\nQuick Reference\nCLI Commands\nclaude              # Start interactive\nclaude -c           # Continue previous session\nclaude -p \"prompt\"  # Non-interactive mode\n\nSlash Commands\n/agents   - Manage subagents\n/clear    - Clear conversation (use between tasks!)\n/compact  - Compress context\n/model    - Change model\n/help     - All commands\n\nKeyboard Shortcuts\nShift+Tab - Toggle Plan mode (read-only exploration)\nCtrl+C    - Cancel operation\nCtrl+B    - Background task\n\nContext Management (Critical!)\nCommand\tWhat it does\tWhen to use\n/clear\tClear conversation, start fresh\tBetween unrelated tasks\n/compact\tSummarize and compress context\tWhen context getting full\nShift+Tab\tToggle Plan mode (read-only)\tExploration before implementing\n\nBest practices:\n\n/clear between unrelated tasks\nUse Plan mode for exploration before implementing\nSubagents isolate verbose operations\nCreate HANDOFF.md for session continuity\nProject Configuration\nsettings.json\n\nCreate .claude/settings.json in your project:\n\n{\n  \"model\": \"sonnet\",\n  \"permissions\": {\n    \"allow\": [\"Bash(npm:*)\", \"Bash(git:*)\", \"Read\", \"Write\", \"Edit\"],\n    \"deny\": [\"Bash(rm -rf:*)\", \"Bash(sudo:*)\"]\n  }\n}\n\nCLAUDE.md\n\nCreate CLAUDE.md in your project root (Claude reads this automatically):\n\n# Project: MyApp\n\n## Tech Stack\n- Frontend: React, TypeScript, Tailwind\n- Backend: Node.js, PostgreSQL\n\n## Commands\n- `npm run dev` - Start dev server\n- `npm test` - Run tests\n\n\nSee examples/CLAUDE-template.md for a full template.\n\nClaude-Mem (If Installed)\n\nCheck status:\n\npgrep -f \"worker-service\" >/dev/null && echo \"running\" || echo \"stopped\"\n\n\nStart if stopped:\n\ncd ~/.claude/plugins/marketplaces/thedotmack && bun plugin/scripts/worker-service.cjs start\n\n\nWeb UI: http://localhost:37777\n\nDiagnostics & Troubleshooting\n\nQuick diagnostics:\n\n~/clawd/skills/claude-code-mastery/scripts/06-diagnostics.sh\n\n\nFull troubleshooting (if issues found):\n\n~/clawd/skills/claude-code-mastery/scripts/08-troubleshoot.sh\n\n\nCommon issues guide: See docs/troubleshooting.md for solutions to:\n\nAuthentication problems (API key, OAuth, logout bugs)\nInstallation issues (PATH, WSL, Node.js version)\nNetwork errors (firewalls, VPNs, proxies)\nPerformance problems (high CPU, hangs, slow search)\nHeartbeat Maintenance\n\nAdd to your HEARTBEAT.md for automatic maintenance:\n\n## Claude Code Maintenance\n\n**Last Health Check:** [timestamp]\n**Last Learning Session:** [timestamp]\n\n### Every Heartbeat (if coding tasks active):\n1. Quick claude-mem check (if installed):\n   `pgrep -f \"worker-service\" >/dev/null && echo \"running\" || echo \"stopped\"`\n   - Only restart if stopped\n   - Note: pgrep saves ~500 tokens vs full status command\n\n### Daily (morning):\n1. Quick health check: `command -v claude && pgrep -f \"worker-service\"`\n2. Only run full diagnostics if quick check fails\n\n### Weekly (Sunday):\n1. Run: `~/clawd/skills/claude-code-mastery/scripts/07-weekly-improvement-cron.sh`\n2. Propose improvements (require human approval)\n\n### Weekly Learning & Skill Improvement (rotate through agents):\n1. Pick ONE agent file from the skill's `agents/` folder (rotate weekly)\n2. Read the \"Learn More\" section\n3. Visit 2-3 links that are relevant to current projects\n4. Internalize key concepts and update your workflows\n5. **Improve the skill itself:**\n   - Found a better resource? Add it to \"Learn More\"\n   - Discovered a new best practice? Update the agent's guidelines\n   - Link broken or outdated? Remove or replace it\n   - New tool or framework worth mentioning? Add it\n6. Commit changes locally with clear commit messages\n7. **Don't push directly to shared repos** — propose changes as a PR or request human review first\n8. Note learnings in your memory files\n\n**Rotation schedule:**\n- Week 1: senior-dev, junior-dev\n- Week 2: frontend-dev, backend-dev\n- Week 3: ai-engineer, ml-engineer\n- Week 4: data-scientist, data-engineer\n- Week 5: project-manager, product-manager\n- Week 6: devops\n\n**What to update:**\n- `agents/*.md` — Add new links, update best practices, fix outdated info\n- `SKILL.md` — Improve documentation, add tips discovered\n- `docs/*.md` — Enhance guides based on real usage\n\n\nWhy this matters:\n\nSkill improves over time through actual use\nLinks stay current (broken ones get fixed)\nBest practices evolve with the ecosystem\nEach Clawdbot contributes back to the skill\nScripts Reference\nScript\tPurpose\tWhen to use\n06-diagnostics.sh\tHealth check and status report\tWhen issues occur\n07-weekly-improvement-cron.sh\tGenerate improvement report\tWeekly (Sunday)\n08-troubleshoot.sh\tComprehensive troubleshooting\tWhen 06 finds issues\nSummary\n\nFor coding tasks:\n\nUse appropriate subagent for the task\nManage context with /clear and Plan mode\nRun diagnostics if something breaks\n\nHeartbeat handles:\n\nclaude-mem health checks\nDaily quick diagnostics\nWeekly improvement research\n\nThe dev team subagents turn Claude Code into a full development organization."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/cheenu1092-oss/claude-code-mastery",
    "publisherUrl": "https://clawhub.ai/cheenu1092-oss/claude-code-mastery",
    "owner": "cheenu1092-oss",
    "version": "1.4.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claude-code-mastery",
    "downloadUrl": "https://openagent3.xyz/downloads/claude-code-mastery",
    "agentUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-code-mastery/agent.md"
  }
}