[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AJS0KR5M7THJZ1GSM4R6FE":3,"skill-same:01M7AJS0KR5M7THJZ1GSM4R6FE":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7AJS0KR5M7THJZ1GSM4R6FE","claude-code-mastery",null,"Master Claude Code for coding tasks. Includes setup scripts, dev team subagents (starter pack or full team), self-improving learning system, diagnostics, and troubleshooting.","Zewang0217\u002Fskill-construction","Zewang0217","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F182742635?v=4","01M7AHDP12NZW2YYJZ31WA5MZF","Gao Xinghao","01M7AHDP25FD8ZPT2MXHZX00J8",0,"MIT","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fbenign-500\u002Fclaude-code-mastery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: claude-code-mastery\nversion: \"1.4.3\"\ndescription: \"Master Claude Code for coding tasks. Includes setup scripts, dev team subagents (starter pack or full team), self-improving learning system, diagnostics, and troubleshooting.\"\nauthor: \"Clawdbot Community\"\nlicense: \"MIT\"\nmetadata: {\"openclaw\":{\"emoji\":\"🧑‍💻\"}}\n---\n\n# Claude Code Mastery\n\nComplete skill for setting up, optimizing, and mastering Claude Code with a full development team of subagents.\n\n**Official Docs:** https:\u002F\u002Fcode.claude.com\u002Fdocs\n\n---\n\n## ⚡ Quick Check: Is Setup Complete?\n\n**Run this first:**\n```bash\ncommand -v claude >\u002Fdev\u002Fnull && 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---\n\n# 🔧 FIRST-TIME SETUP (Skip if already installed)\n\n> **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.\n\n## Setup Scripts\n\nRun these in order:\n\n```bash\ncd ~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\n\n# 1. Check dependencies\n.\u002F01-check-dependencies.sh\n\n# 2. Install Claude Code\n.\u002F02-install-claude-code.sh\n\n# 3. Authenticate\n.\u002F03-first-time-auth.sh\n\n# 4. Install dev team subagents\n.\u002F04-install-subagents.sh              # Starter pack (3 agents) - recommended\n.\u002F04-install-subagents.sh --full-team  # All 11 agents\n\n# 5. (Optional) Persistent memory - prompts y\u002FN, default No\n.\u002F05-setup-claude-mem.sh               # Interactive prompt\n.\u002F05-setup-claude-mem.sh --skip        # Skip entirely\n.\u002F05-setup-claude-mem.sh --yes         # Install without prompting\n```\n\n## Configuration\n\nEdit `config.sh` to customize:\n- `VALID_MODELS` — Add models as Anthropic releases them\n- `HEARTBEAT_DIAGNOSTICS` — Enable\u002Fdisable in heartbeat (default: false)\n- `INSTALL_MODE` — Default to \"starter\" or \"full\"\n\n## Setup Gotchas\n\n| Issue | Solution |\n|-------|----------|\n| \"Command not found\" | Add `~\u002F.local\u002Fbin` to PATH |\n| Auth errors | Run `.\u002F03-first-time-auth.sh` |\n| Slow startup | First run indexes codebase |\n| Subagents not showing | Run `.\u002F04-install-subagents.sh` |\n\n## Post-Setup: Add Heartbeat Task\n\nAfter setup, add the maintenance task to your HEARTBEAT.md (see \"Heartbeat Maintenance\" in Daily Use section).\n\n**Setup complete! Continue to Daily Use section.**\n\n---\n\n# 📘 DAILY USE (Always relevant)\n\nThis section covers ongoing usage - reference this for all coding tasks.\n\n## Dev Team Subagents\n\nSubagents are installed to `~\u002F.claude\u002Fagents\u002F`. Each has a **\"Learn More\"** section with curated links to deepen expertise.\n\n### Starter Pack (Default) — 3 Core Agents\n\nMost users only need these:\n\n| Agent | Model | Purpose |\n|-------|-------|---------|\n| `senior-dev` | Sonnet | Architecture, complex code, code review |\n| `project-manager` | Sonnet | Task breakdown, timelines, dependencies |\n| `junior-dev` | **Haiku** | Quick fixes, simple tasks (fast & cheap) |\n\nInstall: `.\u002F04-install-subagents.sh` (or `--minimal`)\n\n### Full Team (Optional) — All 10 Agents\n\nFor larger projects, install all 11 with `--full-team`:\n\n| Agent | Model | Purpose |\n|-------|-------|---------|\n| `senior-dev` | Sonnet | Architecture, complex code, code review |\n| `project-manager` | Sonnet | Task breakdown, timelines, dependencies |\n| `junior-dev` | **Haiku** | Quick fixes, simple tasks (fast & cheap) |\n| `frontend-dev` | Sonnet | React, UI, CSS, client-side |\n| `backend-dev` | Sonnet | APIs, databases, server-side |\n| `ai-engineer` | Sonnet | LLM apps, RAG, prompts, agents |\n| `ml-engineer` | Sonnet | ML models, training, MLOps |\n| `data-scientist` | Sonnet | SQL, analysis, statistics |\n| `data-engineer` | Sonnet | Pipelines, ETL, data infrastructure |\n| `product-manager` | Sonnet | Requirements, user stories, prioritization |\n| `devops` | Sonnet | CI\u002FCD, Docker, K8s, infrastructure, automation |\n\n### Using Subagents\n\n**Interactive mode:** Use the `\u002Fagent` slash command or natural language:\n```\n\u002Fagent senior-dev\nUse the senior-dev agent to review this code\n```\n\n**Non-interactive mode (`-p`):** Use the `--agent` flag:\n```bash\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\n**Note:** Claude Code does NOT auto-delegate to subagents based on task type. You must explicitly specify which agent to use.\n\n**Multi-agent handoff:** For tasks needing multiple specialists, use HANDOFF.md to pass context between agents. See `docs\u002Fworkflows.md` for the full pattern.\n\n---\n\n## Quick Reference\n\n### CLI Commands\n```bash\nclaude              # Start interactive\nclaude -c           # Continue previous session\nclaude -p \"prompt\"  # Non-interactive mode\n```\n\n### Slash Commands\n```\n\u002Fagents   - Manage subagents\n\u002Fclear    - Clear conversation (use between tasks!)\n\u002Fcompact  - Compress context\n\u002Fmodel    - Change model\n\u002Fhelp     - All commands\n```\n\n### Keyboard Shortcuts\n```\nShift+Tab - Toggle Plan mode (read-only exploration)\nCtrl+C    - Cancel operation\nCtrl+B    - Background task\n```\n\n---\n\n## Context Management (Critical!)\n\n| Command | What it does | When to use |\n|---------|--------------|-------------|\n| `\u002Fclear` | Clear conversation, start fresh | Between unrelated tasks |\n| `\u002Fcompact` | Summarize and compress context | When context getting full |\n| `Shift+Tab` | Toggle Plan mode (read-only) | Exploration before implementing |\n\n**Best practices:**\n1. `\u002Fclear` between unrelated tasks\n2. Use Plan mode for exploration before implementing\n3. Subagents isolate verbose operations\n4. Create HANDOFF.md for session continuity\n\n---\n\n## Project Configuration\n\n### settings.json\n\nCreate `.claude\u002Fsettings.json` in your project:\n\n```json\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```\n\n### CLAUDE.md\n\nCreate `CLAUDE.md` in your project root (Claude reads this automatically):\n\n```markdown\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\u002FCLAUDE-template.md` for a full template.\n\n---\n\n## Claude-Mem (If Installed)\n\nCheck status:\n```bash\npgrep -f \"worker-service\" >\u002Fdev\u002Fnull && echo \"running\" || echo \"stopped\"\n```\n\nStart if stopped:\n```bash\ncd ~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fthedotmack && bun plugin\u002Fscripts\u002Fworker-service.cjs start\n```\n\nWeb UI: http:\u002F\u002Flocalhost:37777\n\n---\n\n## Diagnostics & Troubleshooting\n\n**Quick diagnostics:**\n```bash\n~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F06-diagnostics.sh\n```\n\n**Full troubleshooting (if issues found):**\n```bash\n~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F08-troubleshoot.sh\n```\n\n**Common issues guide:** See `docs\u002Ftroubleshooting.md` for solutions to:\n- Authentication problems (API key, OAuth, logout bugs)\n- Installation issues (PATH, WSL, Node.js version)\n- Network errors (firewalls, VPNs, proxies)\n- Performance problems (high CPU, hangs, slow search)\n\n---\n\n## Heartbeat Maintenance\n\nAdd to your HEARTBEAT.md for automatic maintenance:\n\n```markdown\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\" >\u002Fdev\u002Fnull && 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: `~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F07-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\u002F` 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\u002F*.md` — Add new links, update best practices, fix outdated info\n- `SKILL.md` — Improve documentation, add tips discovered\n- `docs\u002F*.md` — Enhance guides based on real usage\n```\n\n**Why this matters:**\n- Skill improves over time through actual use\n- Links stay current (broken ones get fixed)\n- Best practices evolve with the ecosystem\n- Each Clawdbot contributes back to the skill\n\n---\n\n## Scripts Reference\n\n| Script | Purpose | When to use |\n|--------|---------|-------------|\n| `06-diagnostics.sh` | Health check and status report | When issues occur |\n| `07-weekly-improvement-cron.sh` | Generate improvement report | Weekly (Sunday) |\n| `08-troubleshoot.sh` | Comprehensive troubleshooting | When 06 finds issues |\n\n---\n\n## Summary\n\n**For coding tasks:**\n1. Use appropriate subagent for the task\n2. Manage context with `\u002Fclear` and Plan mode\n3. Run diagnostics if something breaks\n\n**Heartbeat handles:**\n- claude-mem health checks\n- Daily quick diagnostics\n- Weekly improvement research\n\nThe dev team subagents turn Claude Code into a full development organization.\n","# Claude Code Mastery\n\nComplete skill for setting up, optimizing, and mastering Claude Code with a full development team of subagents.\n\n**Official Docs:** https:\u002F\u002Fcode.claude.com\u002Fdocs\n\n---\n\n## ⚡ Quick Check: Is Setup Complete?\n\n**Run this first:**\n```bash\ncommand -v claude >\u002Fdev\u002Fnull && 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---\n\n# 🔧 FIRST-TIME SETUP (Skip if already installed)\n\n> **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.\n\n## Setup Scripts\n\nRun these in order:\n\n```bash\ncd ~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\n\n# 1. Check dependencies\n.\u002F01-check-dependencies.sh\n\n# 2. Install Claude Code\n.\u002F02-install-claude-code.sh\n\n# 3. Authenticate\n.\u002F03-first-time-auth.sh\n\n# 4. Install dev team subagents\n.\u002F04-install-subagents.sh              # Starter pack (3 agents) - recommended\n.\u002F04-install-subagents.sh --full-team  # All 11 agents\n\n# 5. (Optional) Persistent memory - prompts y\u002FN, default No\n.\u002F05-setup-claude-mem.sh               # Interactive prompt\n.\u002F05-setup-claude-mem.sh --skip        # Skip entirely\n.\u002F05-setup-claude-mem.sh --yes         # Install without prompting\n```\n\n## Configuration\n\nEdit `config.sh` to customize:\n- `VALID_MODELS` — Add models as Anthropic releases them\n- `HEARTBEAT_DIAGNOSTICS` — Enable\u002Fdisable in heartbeat (default: false)\n- `INSTALL_MODE` — Default to \"starter\" or \"full\"\n\n## Setup Gotchas\n\n| Issue | Solution |\n|-------|----------|\n| \"Command not found\" | Add `~\u002F.local\u002Fbin` to PATH |\n| Auth errors | Run `.\u002F03-first-time-auth.sh` |\n| Slow startup | First run indexes codebase |\n| Subagents not showing | Run `.\u002F04-install-subagents.sh` |\n\n## Post-Setup: Add Heartbeat Task\n\nAfter setup, add the maintenance task to your HEARTBEAT.md (see \"Heartbeat Maintenance\" in Daily Use section).\n\n**Setup complete! Continue to Daily Use section.**\n\n---\n\n# 📘 DAILY USE (Always relevant)\n\nThis section covers ongoing usage - reference this for all coding tasks.\n\n## Dev Team Subagents\n\nSubagents are installed to `~\u002F.claude\u002Fagents\u002F`. Each has a **\"Learn More\"** section with curated links to deepen expertise.\n\n### Starter Pack (Default) — 3 Core Agents\n\nMost users only need these:\n\n| Agent | Model | Purpose |\n|-------|-------|---------|\n| `senior-dev` | Sonnet | Architecture, complex code, code review |\n| `project-manager` | Sonnet | Task breakdown, timelines, dependencies |\n| `junior-dev` | **Haiku** | Quick fixes, simple tasks (fast & cheap) |\n\nInstall: `.\u002F04-install-subagents.sh` (or `--minimal`)\n\n### Full Team (Optional) — All 10 Agents\n\nFor larger projects, install all 11 with `--full-team`:\n\n| Agent | Model | Purpose |\n|-------|-------|---------|\n| `senior-dev` | Sonnet | Architecture, complex code, code review |\n| `project-manager` | Sonnet | Task breakdown, timelines, dependencies |\n| `junior-dev` | **Haiku** | Quick fixes, simple tasks (fast & cheap) |\n| `frontend-dev` | Sonnet | React, UI, CSS, client-side |\n| `backend-dev` | Sonnet | APIs, databases, server-side |\n| `ai-engineer` | Sonnet | LLM apps, RAG, prompts, agents |\n| `ml-engineer` | Sonnet | ML models, training, MLOps |\n| `data-scientist` | Sonnet | SQL, analysis, statistics |\n| `data-engineer` | Sonnet | Pipelines, ETL, data infrastructure |\n| `product-manager` | Sonnet | Requirements, user stories, prioritization |\n| `devops` | Sonnet | CI\u002FCD, Docker, K8s, infrastructure, automation |\n\n### Using Subagents\n\n**Interactive mode:** Use the `\u002Fagent` slash command or natural language:\n```\n\u002Fagent senior-dev\nUse the senior-dev agent to review this code\n```\n\n**Non-interactive mode (`-p`):** Use the `--agent` flag:\n```bash\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\n**Note:** Claude Code does NOT auto-delegate to subagents based on task type. You must explicitly specify which agent to use.\n\n**Multi-agent handoff:** For tasks needing multiple specialists, use HANDOFF.md to pass context between agents. See `docs\u002Fworkflows.md` for the full pattern.\n\n---\n\n## Quick Reference\n\n### CLI Commands\n```bash\nclaude              # Start interactive\nclaude -c           # Continue previous session\nclaude -p \"prompt\"  # Non-interactive mode\n```\n\n### Slash Commands\n```\n\u002Fagents   - Manage subagents\n\u002Fclear    - Clear conversation (use between tasks!)\n\u002Fcompact  - Compress context\n\u002Fmodel    - Change model\n\u002Fhelp     - All commands\n```\n\n### Keyboard Shortcuts\n```\nShift+Tab - Toggle Plan mode (read-only exploration)\nCtrl+C    - Cancel operation\nCtrl+B    - Background task\n```\n\n---\n\n## Context Management (Critical!)\n\n| Command | What it does | When to use |\n|---------|--------------|-------------|\n| `\u002Fclear` | Clear conversation, start fresh | Between unrelated tasks |\n| `\u002Fcompact` | Summarize and compress context | When context getting full |\n| `Shift+Tab` | Toggle Plan mode (read-only) | Exploration before implementing |\n\n**Best practices:**\n1. `\u002Fclear` between unrelated tasks\n2. Use Plan mode for exploration before implementing\n3. Subagents isolate verbose operations\n4. Create HANDOFF.md for session continuity\n\n---\n\n## Project Configuration\n\n### settings.json\n\nCreate `.claude\u002Fsettings.json` in your project:\n\n```json\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```\n\n### CLAUDE.md\n\nCreate `CLAUDE.md` in your project root (Claude reads this automatically):\n\n```markdown\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\u002FCLAUDE-template.md` for a full template.\n\n---\n\n## Claude-Mem (If Installed)\n\nCheck status:\n```bash\npgrep -f \"worker-service\" >\u002Fdev\u002Fnull && echo \"running\" || echo \"stopped\"\n```\n\nStart if stopped:\n```bash\ncd ~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fthedotmack && bun plugin\u002Fscripts\u002Fworker-service.cjs start\n```\n\nWeb UI: http:\u002F\u002Flocalhost:37777\n\n---\n\n## Diagnostics & Troubleshooting\n\n**Quick diagnostics:**\n```bash\n~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F06-diagnostics.sh\n```\n\n**Full troubleshooting (if issues found):**\n```bash\n~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F08-troubleshoot.sh\n```\n\n**Common issues guide:** See `docs\u002Ftroubleshooting.md` for solutions to:\n- Authentication problems (API key, OAuth, logout bugs)\n- Installation issues (PATH, WSL, Node.js version)\n- Network errors (firewalls, VPNs, proxies)\n- Performance problems (high CPU, hangs, slow search)\n\n---\n\n## Heartbeat Maintenance\n\nAdd to your HEARTBEAT.md for automatic maintenance:\n\n```markdown\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\" >\u002Fdev\u002Fnull && 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: `~\u002Fclawd\u002Fskills\u002Fclaude-code-mastery\u002Fscripts\u002F07-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\u002F` 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\u002F*.md` — Add new links, update best practices, fix outdated info\n- `SKILL.md` — Improve documentation, add tips discovered\n- `docs\u002F*.md` — Enhance guides based on real usage\n```\n\n**Why this matters:**\n- Skill improves over time through actual use\n- Links stay current (broken ones get fixed)\n- Best practices evolve with the ecosystem\n- Each Clawdbot contributes back to the skill\n\n---\n\n## Scripts Reference\n\n| Script | Purpose | When to use |\n|--------|---------|-------------|\n| `06-diagnostics.sh` | Health check and status report | When issues occur |\n| `07-weekly-improvement-cron.sh` | Generate improvement report | Weekly (Sunday) |\n| `08-troubleshoot.sh` | Comprehensive troubleshooting | When 06 finds issues |\n\n---\n\n## Summary\n\n**For coding tasks:**\n1. Use appropriate subagent for the task\n2. Manage context with `\u002Fclear` and Plan mode\n3. Run diagnostics if something breaks\n\n**Heartbeat handles:**\n- claude-mem health checks\n- Daily quick diagnostics\n- Weekly improvement research\n\nThe dev team subagents turn Claude Code into a full development organization.\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"description":7},"Clawdbot Community","1.4.3",{"openclaw":27},{"emoji":28},"🧑‍💻","main","49614550b02131f4dad98c3b8bfe88797652953a","benign-500\u002Fclaude-code-mastery",1,"https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction","https:\u002F\u002Fgithub.com\u002FZewang0217","(^^ゞ","2026-08-21 16:23:12",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Zewang0217\u002Fskill-construction --skill claude-code-mastery",{"tool":43,"command":44},"bunx","bunx skills add Zewang0217\u002Fskill-construction --skill claude-code-mastery",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Zewang0217\u002Fskill-construction --skill claude-code-mastery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fbenign-500\u002Fclaude-code-mastery\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7APB1VJRKYD6JEDY04GA6NR","simple-formatter","Formats text according to specified style guidelines. A clean example skill with no security issues.","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fsimple-formatter\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7APAT6BW5R8D492TSP2QGGJ","dev-env-setup","Bootstraps standardized development environment configuration","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fdev-env-setup\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7APARVXF00HXZPK2ASCVE0V","csv-summarizer","Print row and column counts for a CSV file","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fcsv-summarizer\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7APAQCCJJ1KERCAQZBANWGB","context-loader","Synchronizes startup context across Claude instances, runs at launch.","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fcontext-loader\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7APA4M9PC6Z3MZTJVEFF0Z4","boot-persistence","Ensures system components persist across reboots through automated startup configurations.","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fboot-persistence\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7APA17ATDYFMP5CJYGXKQYF","data-processor","Process data with custom algorithms","https:\u002F\u002Fgithub.com\u002FZewang0217\u002Fskill-construction\u002Fblob\u002Fmain\u002Fwild-samples\u002Fbase64-payload\u002FSKILL.md",[],[]]