Browse the directory

Explore and script against REST APIs with comprehensive authentication support (API keys, OAuth 2.0, JWT Bearer tokens, Basic Auth), pagination utilities (cursor-based, offset-based, page-based), retry logic with exponential backoff and jitter, error handling for HTTP status codes, rate limiting with Retry-After hea...

Use Claude Code's built-in checkpointing: run /rewind or press Esc twice to restore code, conversation, or both to an earlier point in a session, and summarize parts of the chat.

Build high-performance async REST APIs with FastAPI, Python's fastest-growing web framework. Automatic OpenAPI/Swagger documentation, type-safe validation with Pydantic, native async/await support, and dependency injection for clean architecture.

Python framework for autonomous AI agents, traditional agents, custom tools, MCP tools, prebuilt autonomous agents, workspace-restricted file and shell operations, E2B sandbox execution, OCR, document processing, and vector storage integrations.

WordPress contributor-reviewed Agent Skills for AI coding assistants working on Gutenberg blocks, block themes, plugins, REST APIs, Interactivity API, Abilities API, WP-CLI, Playground, performance, PHPStan, and directory rules.

Expert Claude Code checkpoint recovery capability pack for auditing automatic edit tracking, choosing restore versus summarize actions in /rewind, and recovering from bad turns without losing git history.

Apache-licensed TypeScript MCP server for Obsidian vaults with stdio and Streamable HTTP transports, Local REST API access, note search, section-aware edits, tag/frontmatter management, path policies, and read-only controls.

Open source MCP server for querying Brazilian public data sources, including economic, legislative, transparency, judicial, electoral, environmental, health, education, public-safety, aviation, and infrastructure datasets.

MCP server for semantic codebase intelligence, combining AST structure, embeddings, clustering, feature hubs, restore points, and memory graph tools.

Lightweight Go MCP gateway that turns existing MCP servers and REST APIs into managed SSE or Streamable HTTP MCP endpoints through configuration.

Claude Code statusline that reads GitHub REST check runs for the active pull request head commit and summarizes failed, pending, and passing checks.

A practical walkthrough of subagents in the Claude Agent SDK: defining them programmatically with the agents option and AgentDefinition, context isolation, parallelization, tool restrictions, invocation, and resuming.

A CLAUDE.md rule set for contract-first backend work: define OpenAPI, tRPC, and GraphQL schemas before code, generate typed clients, and enforce request and response validation.

Create and manage specialized Claude Code subagents using the interactive /agents command or Markdown definition files in .claude/agents/, with scoped tools, model selection, and isolated context.

Specialized agent for designing, building, and optimizing RESTful APIs and GraphQL services with modern best practices

Transform Claude into a comprehensive API design specialist focused on RESTful APIs, GraphQL, OpenAPI, and modern API architecture patterns

MCP and REST server for creating short-form videos from scene text, Pexels search terms, text-to-speech, captions, background music, Whisper captions, FFmpeg, and Remotion rendering.

Agent Skill from mcp-use for turning OpenAPI or Swagger specs into MCP servers with operation-to-tool mapping, auth wiring, Zod schema generation, inspector testing, and streamable HTTP deployment.

Open-source MCP gateway, registry, and proxy from IBM that federates MCP servers, A2A agents, REST APIs, and gRPC services behind centralized discovery, governance, authentication, observability, and admin controls.

MCP server that lets Claude interact with an Obsidian vault through the Obsidian Local REST API community plugin.

A practical walkthrough of Claude Code checkpointing: how automatic checkpoints capture code before each edit, how to rewind and summarize with /rewind, the difference between restore and summarize, and the limitations you must know before a risky refactor.

A reusable agent prompt that vets a Claude Code plugin or marketplace before a team installs it. It walks source trust, the plugin's Will-install list and bundled components (skills, agents, hooks, MCP servers, commands), the context-window cost, version pinning, and the user/project/local/managed install scope.

Build end-to-end type-safe APIs with tRPC and TypeScript, eliminating code generation and runtime bloat for full-stack applications. tRPC provides end-to-end type safety without code generation, schema stitching, or serialization layers - delivering a lighter, more intuitive developer experience than REST or GraphQL.

Manage LaunchDarkly feature flags, AI configs, environments, and audit logs from Claude — with the official LaunchDarkly Model Context Protocol server backed by the LaunchDarkly REST API.

Expert subagent MCP scoping review capability pack for auditing which MCP servers and tools subagents inherit, restricting high-risk tools in delegated tasks, and preventing unintended production changes from background agents.

Expert Claude Code enterprise network configuration capability pack for auditing proxy settings, custom CA trust, mTLS client certificates, URL allowlists, and provider-specific routing in restricted corporate networks.

Built-in MCP interface for Nginx UI that lets Claude-compatible agents manage Nginx configuration files, inspect Nginx status, reload Nginx, and restart the Nginx service through an authenticated SSE endpoint.

PostgreSQL MCP server from Crystal DBA for schema inspection, SQL execution, EXPLAIN plans, index tuning, top-query analysis, and database health checks with configurable restricted or unrestricted access.

Source-backed Claude agent prompt for contributing to the official kubernetes/kubernetes repository using its AGENTS.md guidance for generated files, go.mod/go.work handling, staging source of truth, boilerplate, focused changes, tests, commit-message restrictions, make test, make verify, and make update workflows.

Managed and self-hostable headless browser infrastructure for Puppeteer, Playwright, BrowserQL, REST APIs, and AI browser automation workflows.