{
  "schema": "https://ai-atoms.com/schemas/skill-v1.json",
  "type": "skill",
  "id": "skill/claude-code-guide",
  "version": "1.0.0",
  "name": "Claude Code Guide",
  "description": "Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies \\\\\"Thinking\\\\\" keywords, debugging techniques, and best practices for interacting wit...",
  "system_prompt_fragment": "# Claude Code Guide\n\n## Purpose\n\nTo provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.\n\n## Configuration (`CLAUDE.md`)\n\nWhen starting a new project, create a `CLAUDE.md` file in the root directory to guide the agent.\n\n### Template (General)\n\n```markdown\n# Project Guidelines\n\n## Commands\n\n- Run app: `npm run dev`\n- Test: `npm test`\n- Build: `npm run build`\n\n## Code Style\n\n- Use TypeScript for all new code.\n- Functional components with Hooks for React.\n- Tailwind CSS for styling.\n- Early returns for error handling.\n\n## Workflow\n\n- Read `README.md` first to understand project context.\n- Before editing, read the file content.\n- After editing, run tests to verify.\n```\n\n## Advanced Features\n\n### Thinking Keywords\n\nUse these keywords in your prompts to trigger deeper reasoning from the agent:\n\n- \"Think step-by-step\"\n- \"Analyze the root cause\"\n- \"Plan before executing\"\n- \"Verify your assumptions\"\n\n### Debugging\n\nIf the agent is stuck or behaving unexpectedly:\n\n1. **Clear Context**: Start a new session or ask the agent to \"forget previous instructions\" if confused.\n2. **Explicit Instructions**: Be extremely specific about paths, filenames, and desired outcomes.\n3. **Logs**: Ask the agent to \"check the logs\" or \"run the command with verbose output\".\n\n## Best Practices\n\n1. **Small Contexts**: Don't dump the entire codebase into the context. Use `grep` or `find` to locate relevant files first.\n2. **Iterative Development**: Ask for small changes, verify, then proceed.\n3. **Feedback Loop**: If the agent makes a mistake, correct it immediately and ask it to \"add a lesson\" to its memory (if supported) or `CLAUDE.md`.\n\n## Reference\n\nBased on [Claude Code Guide by zebbern](https://github.com/zebbern/claude-code-guide).\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.",
  "applicable_domains": [
    "frontend"
  ],
  "category": "frontend",
  "invocation": [
    "/claude-code-guide"
  ],
  "authored_by": "claudeskills.in community",
  "source_url": "https://claudeskills.in/skill/claude-code-guide",
  "provenance": {
    "source": "claudeskills.in",
    "source_url": "https://claudeskills.in/skill/claude-code-guide",
    "license": "unknown",
    "imported_at": "2026-09-03",
    "notes": "Aggregated by claudeskills.in from community GitHub lists."
  },
  "tags": [
    "claudeskills",
    "frontend"
  ],
  "lifecycle": "draft"
}