{"owner":"anthropics","repo":"claude-cookbooks","hasSkills":true,"totalSkillsCount":4,"totalTokensCount":1825,"categories":["claude-rule","mcp-config","marketplace","plugin-manifest"],"hasMcp":true,"mcpConfig":{"mcpServers":{"claude-cookbooks":{"command":"npx","args":["-y","@modelcontextprotocol/server-claude-cookbooks"]}}},"found":["CLAUDE.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json"],"skills":{"CLAUDE.md":"# Claude Cookbooks\n\nA collection of Jupyter notebooks and Python examples for building with the Claude API.\n\n## Quick Start\n\n```bash\n# Install dependencies\nuv sync --all-extras\n\n# Install pre-commit hooks\nuv run pre-commit install\n\n# Set up API key\ncp .env.example .env\n# Edit .env and add your ANTHROPIC_API_KEY\n```\n\n## Development Commands\n\n```bash\nmake format        # Format code with ruff\nmake lint          # Run linting\nmake check         # Run format-check + lint\nmake fix           # Auto-fix issues + format\nmake test          # Run pytest\n```\n\nOr directly with uv:\n\n```bash\nuv run ruff format .           # Format\nuv run ruff check .            # Lint\nuv run ruff check --fix .      # Auto-fix\nuv run pre-commit run --all-files\n```\n\n## Code Style\n\n- **Line length:** 100 characters\n- **Quotes:** Double quotes\n- **Formatter:** Ruff\n\nNotebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806).\n\n## Git Workflow\n\n**Branch naming:** `<username>/<feature-description>`\n\n**Commit format (conventional commits):**\n```\nfeat(scope): add new feature\nfix(scope): fix bug\ndocs(scope): update documentation\nstyle: lint/format\n```\n\n## Key Rules\n\n1. **API Keys:** Never commit `.env` files. Use `dotenv.load_dotenv()` then access keys via `os.environ` or `os.getenv()`\n\n2. **Dependencies:** Use `uv add <package>` or `uv add --dev <package>`. Never edit pyproject.toml directly.\n\n3. **Models:** Use current Claude models. Check docs.anthropic.com for latest versions.\n   - Sonnet: `claude-sonnet-5`\n   - Haiku: `claude-haiku-4-5`\n   - Opus: `claude-opus-4-8`\n   - **Never use dated model IDs** (e.g., `claude-sonnet-4-6-20250514`). Always use the non-dated alias.\n   - **Bedrock model IDs** follow a different format. Use the base Bedrock model ID from the docs:\n     - Opus 4.8: `anthropic.claude-opus-4-8`\n     - Sonnet 5: `anthropic.claude-sonnet-5`\n     - Haiku 4.5: `anthropic.claude-haiku-4-5-20251001-v1:0`\n     - Prepend `global.` for global endpoints (recommended): `global.anthropic.claude-opus-4-8`\n     - Note: older Bedrock models use a dated `-YYYYMMDD-v1:0` suffix (e.g., Haiku 4.5 above); newer ones use the suffix-less `anthropic.claude-<model>` format.\n\n4. **Notebooks:**\n   - Keep outputs in notebooks (intentional for demonstration)\n   - One concept per notebook\n   - Test that notebooks run top-to-bottom without errors\n\n5. **Quality checks:** Run `make check` before committing. Pre-commit hooks validate formatting and notebook structure.\n\n## Slash Commands\n\nThese commands are available in Claude Code and CI:\n\n- `/notebook-review` - Review notebook quality\n- `/model-check` - Validate Claude model references\n- `/link-review` - Check links in changed files\n\n## Project Structure\n\n```\ncapabilities/      # Core Claude capabilities (RAG, classification, etc.)\nevals/             # Model evaluation patterns and benchmarks\nskills/            # Advanced skill-based notebooks\ntool_use/          # Tool use and integration patterns\nmultimodal/        # Vision and image processing\nmisc/              # Batch processing, caching, utilities\nthird_party/       # Pinecone, Voyage, Wikipedia integrations\nextended_thinking/ # Extended reasoning patterns\nscripts/           # Validation scripts\n.claude/           # Claude Code commands and skills\n```\n\n## Adding a New Cookbook\n\n1. Create notebook in the appropriate directory\n2. Add entry to `registry.yaml` with title, description, path, authors, categories\n3. Add author info to `authors.yaml` if new contributor\n4. Run quality checks and submit PR\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/plugin.json)"},"files":{"CLAUDE.md":"# Claude Cookbooks\n\nA collection of Jupyter notebooks and Python examples for building with the Claude API.\n\n## Quick Start\n\n```bash\n# Install dependencies\nuv sync --all-extras\n\n# Install pre-commit hooks\nuv run pre-commit install\n\n# Set up API key\ncp .env.example .env\n# Edit .env and add your ANTHROPIC_API_KEY\n```\n\n## Development Commands\n\n```bash\nmake format        # Format code with ruff\nmake lint          # Run linting\nmake check         # Run format-check + lint\nmake fix           # Auto-fix issues + format\nmake test          # Run pytest\n```\n\nOr directly with uv:\n\n```bash\nuv run ruff format .           # Format\nuv run ruff check .            # Lint\nuv run ruff check --fix .      # Auto-fix\nuv run pre-commit run --all-files\n```\n\n## Code Style\n\n- **Line length:** 100 characters\n- **Quotes:** Double quotes\n- **Formatter:** Ruff\n\nNotebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806).\n\n## Git Workflow\n\n**Branch naming:** `<username>/<feature-description>`\n\n**Commit format (conventional commits):**\n```\nfeat(scope): add new feature\nfix(scope): fix bug\ndocs(scope): update documentation\nstyle: lint/format\n```\n\n## Key Rules\n\n1. **API Keys:** Never commit `.env` files. Use `dotenv.load_dotenv()` then access keys via `os.environ` or `os.getenv()`\n\n2. **Dependencies:** Use `uv add <package>` or `uv add --dev <package>`. Never edit pyproject.toml directly.\n\n3. **Models:** Use current Claude models. Check docs.anthropic.com for latest versions.\n   - Sonnet: `claude-sonnet-5`\n   - Haiku: `claude-haiku-4-5`\n   - Opus: `claude-opus-4-8`\n   - **Never use dated model IDs** (e.g., `claude-sonnet-4-6-20250514`). Always use the non-dated alias.\n   - **Bedrock model IDs** follow a different format. Use the base Bedrock model ID from the docs:\n     - Opus 4.8: `anthropic.claude-opus-4-8`\n     - Sonnet 5: `anthropic.claude-sonnet-5`\n     - Haiku 4.5: `anthropic.claude-haiku-4-5-20251001-v1:0`\n     - Prepend `global.` for global endpoints (recommended): `global.anthropic.claude-opus-4-8`\n     - Note: older Bedrock models use a dated `-YYYYMMDD-v1:0` suffix (e.g., Haiku 4.5 above); newer ones use the suffix-less `anthropic.claude-<model>` format.\n\n4. **Notebooks:**\n   - Keep outputs in notebooks (intentional for demonstration)\n   - One concept per notebook\n   - Test that notebooks run top-to-bottom without errors\n\n5. **Quality checks:** Run `make check` before committing. Pre-commit hooks validate formatting and notebook structure.\n\n## Slash Commands\n\nThese commands are available in Claude Code and CI:\n\n- `/notebook-review` - Review notebook quality\n- `/model-check` - Validate Claude model references\n- `/link-review` - Check links in changed files\n\n## Project Structure\n\n```\ncapabilities/      # Core Claude capabilities (RAG, classification, etc.)\nevals/             # Model evaluation patterns and benchmarks\nskills/            # Advanced skill-based notebooks\ntool_use/          # Tool use and integration patterns\nmultimodal/        # Vision and image processing\nmisc/              # Batch processing, caching, utilities\nthird_party/       # Pinecone, Voyage, Wikipedia integrations\nextended_thinking/ # Extended reasoning patterns\nscripts/           # Validation scripts\n.claude/           # Claude Code commands and skills\n```\n\n## Adding a New Cookbook\n\n1. Create notebook in the appropriate directory\n2. Add entry to `registry.yaml` with title, description, path, authors, categories\n3. Add author info to `authors.yaml` if new contributor\n4. Run quality checks and submit PR\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/plugin.json)"},"items":[{"name":"CLAUDE.md","path":"CLAUDE.md","rawUrl":"https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/CLAUDE.md","title":"Claude Agent Guidelines & System Prompt","category":"claude-rule","format":"markdown","content":"# Claude Cookbooks\n\nA collection of Jupyter notebooks and Python examples for building with the Claude API.\n\n## Quick Start\n\n```bash\n# Install dependencies\nuv sync --all-extras\n\n# Install pre-commit hooks\nuv run pre-commit install\n\n# Set up API key\ncp .env.example .env\n# Edit .env and add your ANTHROPIC_API_KEY\n```\n\n## Development Commands\n\n```bash\nmake format        # Format code with ruff\nmake lint          # Run linting\nmake check         # Run format-check + lint\nmake fix           # Auto-fix issues + format\nmake test          # Run pytest\n```\n\nOr directly with uv:\n\n```bash\nuv run ruff format .           # Format\nuv run ruff check .            # Lint\nuv run ruff check --fix .      # Auto-fix\nuv run pre-commit run --all-files\n```\n\n## Code Style\n\n- **Line length:** 100 characters\n- **Quotes:** Double quotes\n- **Formatter:** Ruff\n\nNotebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806).\n\n## Git Workflow\n\n**Branch naming:** `<username>/<feature-description>`\n\n**Commit format (conventional commits):**\n```\nfeat(scope): add new feature\nfix(scope): fix bug\ndocs(scope): update documentation\nstyle: lint/format\n```\n\n## Key Rules\n\n1. **API Keys:** Never commit `.env` files. Use `dotenv.load_dotenv()` then access keys via `os.environ` or `os.getenv()`\n\n2. **Dependencies:** Use `uv add <package>` or `uv add --dev <package>`. Never edit pyproject.toml directly.\n\n3. **Models:** Use current Claude models. Check docs.anthropic.com for latest versions.\n   - Sonnet: `claude-sonnet-5`\n   - Haiku: `claude-haiku-4-5`\n   - Opus: `claude-opus-4-8`\n   - **Never use dated model IDs** (e.g., `claude-sonnet-4-6-20250514`). Always use the non-dated alias.\n   - **Bedrock model IDs** follow a different format. Use the base Bedrock model ID from the docs:\n     - Opus 4.8: `anthropic.claude-opus-4-8`\n     - Sonnet 5: `anthropic.claude-sonnet-5`\n     - Haiku 4.5: `anthropic.claude-haiku-4-5-20251001-v1:0`\n     - Prepend `global.` for global endpoints (recommended): `global.anthropic.claude-opus-4-8`\n     - Note: older Bedrock models use a dated `-YYYYMMDD-v1:0` suffix (e.g., Haiku 4.5 above); newer ones use the suffix-less `anthropic.claude-<model>` format.\n\n4. **Notebooks:**\n   - Keep outputs in notebooks (intentional for demonstration)\n   - One concept per notebook\n   - Test that notebooks run top-to-bottom without errors\n\n5. **Quality checks:** Run `make check` before committing. Pre-commit hooks validate formatting and notebook structure.\n\n## Slash Commands\n\nThese commands are available in Claude Code and CI:\n\n- `/notebook-review` - Review notebook quality\n- `/model-check` - Validate Claude model references\n- `/link-review` - Check links in changed files\n\n## Project Structure\n\n```\ncapabilities/      # Core Claude capabilities (RAG, classification, etc.)\nevals/             # Model evaluation patterns and benchmarks\nskills/            # Advanced skill-based notebooks\ntool_use/          # Tool use and integration patterns\nmultimodal/        # Vision and image processing\nmisc/              # Batch processing, caching, utilities\nthird_party/       # Pinecone, Voyage, Wikipedia integrations\nextended_thinking/ # Extended reasoning patterns\nscripts/           # Validation scripts\n.claude/           # Claude Code commands and skills\n```\n\n## Adding a New Cookbook\n\n1. Create notebook in the appropriate directory\n2. Add entry to `registry.yaml` with title, description, path, authors, categories\n3. Add author info to `authors.yaml` if new contributor\n4. Run quality checks and submit PR\n","isInternal":false,"tokens":925,"sizeBytes":3568},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/marketplace.json","title":"Claude Plugin Marketplace Catalog","category":"marketplace","format":"json","content":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":206},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/plugin.json","title":"claude-plugin Plugin Manifest","category":"plugin-manifest","format":"json","content":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":192},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.cursor/mcp.json","title":"Model Context Protocol (MCP) Configuration","category":"mcp-config","format":"json","content":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":185}],"systemPromptSnippet":"<yakaai_skills repo=\"anthropics/claude-cookbooks\">\n<!-- File: CLAUDE.md (Tokens: ~925 | Category: claude-rule) -->\n# Claude Cookbooks\n\nA collection of Jupyter notebooks and Python examples for building with the Claude API.\n\n## Quick Start\n\n```bash\n# Install dependencies\nuv sync --all-extras\n\n# Install pre-commit hooks\nuv run pre-commit install\n\n# Set up API key\ncp .env.example .env\n# Edit .env and add your ANTHROPIC_API_KEY\n```\n\n## Development Commands\n\n```bash\nmake format        # Format code with ruff\nmake lint          # Run linting\nmake check         # Run format-check + lint\nmake fix           # Auto-fix issues + format\nmake test          # Run pytest\n```\n\nOr directly with uv:\n\n```bash\nuv run ruff format .           # Format\nuv run ruff check .            # Lint\nuv run ruff check --fix .      # Auto-fix\nuv run pre-commit run --all-files\n```\n\n## Code Style\n\n- **Line length:** 100 characters\n- **Quotes:** Double quotes\n- **Formatter:** Ruff\n\nNotebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806).\n\n## Git Workflow\n\n**Branch naming:** `<username>/<feature-description>`\n\n**Commit format (conventional commits):**\n```\nfeat(scope): add new feature\nfix(scope): fix bug\ndocs(scope): update documentation\nstyle: lint/format\n```\n\n## Key Rules\n\n1. **API Keys:** Never commit `.env` files. Use `dotenv.load_dotenv()` then access keys via `os.environ` or `os.getenv()`\n\n2. **Dependencies:** Use `uv add <package>` or `uv add --dev <package>`. Never edit pyproject.toml directly.\n\n3. **Models:** Use current Claude models. Check docs.anthropic.com for latest versions.\n   - Sonnet: `claude-sonnet-5`\n   - Haiku: `claude-haiku-4-5`\n   - Opus: `claude-opus-4-8`\n   - **Never use dated model IDs** (e.g., `claude-sonnet-4-6-20250514`). Always use the non-dated alias.\n   - **Bedrock model IDs** follow a different format. Use the base Bedrock model ID from the docs:\n     - Opus 4.8: `anthropic.claude-opus-4-8`\n     - Sonnet 5: `anthropic.claude-sonnet-5`\n     - Haiku 4.5: `anthropic.claude-haiku-4-5-20251001-v1:0`\n     - Prepend `global.` for global endpoints (recommended): `global.anthropic.claude-opus-4-8`\n     - Note: older Bedrock models use a dated `-YYYYMMDD-v1:0` suffix (e.g., Haiku 4.5 above); newer ones use the suffix-less `anthropic.claude-<model>` format.\n\n4. **Notebooks:**\n   - Keep outputs in notebooks (intentional for demonstration)\n   - One concept per notebook\n   - Test that notebooks run top-to-bottom without errors\n\n5. **Quality checks:** Run `make check` before committing. Pre-commit hooks validate formatting and notebook structure.\n\n## Slash Commands\n\nThese commands are available in Claude Code and CI:\n\n- `/notebook-review` - Review notebook quality\n- `/model-check` - Validate Claude model references\n- `/link-review` - Check links in changed files\n\n## Project Structure\n\n```\ncapabilities/      # Core Claude capabilities (RAG, classification, etc.)\nevals/             # Model evaluation patterns and benchmarks\nskills/            # Advanced skill-based notebooks\ntool_use/          # Tool use and integration patterns\nmultimodal/        # Vision and image processing\nmisc/              # Batch processing, caching, utilities\nthird_party/       # Pinecone, Voyage, Wikipedia integrations\nextended_thinking/ # Extended reasoning patterns\nscripts/           # Validation scripts\n.claude/           # Claude Code commands and skills\n```\n\n## Adding a New Cookbook\n\n1. Create notebook in the appropriate directory\n2. Add entry to `registry.yaml` with title, description, path, authors, categories\n3. Add author info to `authors.yaml` if new contributor\n4. Run quality checks and submit PR\n\n<!-- File: .claude-plugin/marketplace.json (Tokens: ~300 | Category: marketplace) -->\n# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/marketplace.json)\n\n<!-- File: .claude-plugin/plugin.json (Tokens: ~300 | Category: plugin-manifest) -->\n# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.claude-plugin/plugin.json)\n\n<!-- File: .cursor/mcp.json (Tokens: ~300 | Category: mcp-config) -->\n# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/anthropics/claude-cookbooks/HEAD/.cursor/mcp.json)\n</yakaai_skills>"}