Claude Code AI Agent Skills

Provides score interpretation (< 0.3 good, > 0.5 skip), query optimization, and source naming for query_documents, ingest_file, ingest_data tools. Use this skill when working with RAG, searching documents, ingesting files, saving web content, or handling PDF, HTML, DOCX, TXT, Markdown.

Want to use GPT-5, Gemini, or DeepSeek in Claude Code? Today you need to: 1. Create accounts with 5+ AI providers 2. Manage 5+ API keys and billing systems 3. Pay $20-100/month minimums per provider 4. Configure each provider separately That's too much friction. BlockRun MCP gives you access to 30+ AI models with: - Zero API keys - No accounts needed with OpenAI, Google, etc. - One wallet - Single

Cut every explanation to the minimum. Answers first, no preamble, no restating the question, no offers to help further. For expert users who want dense output.

Part of the quantum-loop autonomous development pipeline (brainstorm \u2192 spec \u2192 plan \u2192 execute \u2192 review \u2192 verify). Deep Socratic exploration of a feature idea before implementation. Asks questions one at a time, proposes 2-3 alternative approaches with trade-offs, presents design section-by-section for approval, and saves an approved design document. Use when starting a new feature, exploring an idea, or before writing a spec.

iptables for MCP. Blocks dangerous tool calls, scans for secret leakage, logs everything. No AI, no cloud, pure rules. Sits between your AI coding tool (Claude Code, Cursor, Windsurf) and MCP servers, intercepting every JSON-RPC message and enforcing YAML-defined policies. MCP servers have full access to your filesystem, shell, databases, and APIs. When an AI agent calls tools/call, the server exe

A chat server for AI agents. Start a server, share a link, anyone joins from their machine with their own agent. Claude Code, Codex, humans — everyone ends up in the same chat room. Messages get pushed into each agent's session in real time as they happen. Works over the internet with zero config. You need tmux (brew install tmux) and either Claude Code or Codex. Terminal 1 — start a room: The ser

SessionStart hook that reads CLAUDE.md and injects it into the initial system context. Ensures every new session has project-specific context loaded automatically.

Live handbook: https://girijashankarj.github.io/cursor-handbook/ The open-source rules engine for Cursor IDE — 117 components (rules, agents, skills, commands, hooks) that turn your AI into a senior engineer who follows your standards, knows your codebase, and never wastes a token. If cursor-handbook helps you, consider giving it a ⭐ — it helps others discover it. - Ways to use - The Problem -

Multi-agent orchestration platform for enterprise AI development. Run 12+ AI agents concurrently with full governance, Gemini-powered code review, and enforced quality gates. Solves coordination, verification, and metrics challenges that stall enterprise AI adoption.

Netresearch AI skill for assessing and enhancing software projects to meet enterprise-grade standards for security, quality, and automation. This is an Agent Skill following the open standard originally developed by Anthropic and released for cross-platform use. Supported Platforms: - ✅ Claude Code (Anthropic) - ✅ GitHub Copilot - ✅ Other skills-compatible AI agents - OpenSSF Framework Alignment -

PreToolUse hook that blocks any Bash tool call matching `git push --force` or `git push -f`. Prevents accidental history rewrite on shared branches.

Profiles hot paths, spots N+1 queries, suggests caching layers, and fixes render bottlenecks. Use when a page or endpoint is slow and root cause is unknown.

Recursive Decomposition Skill Handle long-context tasks with Claude Code through recursive decomposition What It Does • Installation • How It Works • Benchmarks • Acknowledgments When analyzing large codebases, processing many documents, or aggregating information across dozens of files, Claude's context window becomes a bottleneck. As context grows, "context rot" degrades performance: - Missed de

Photon turns a single TypeScript file into: - MCP server for AI agents - CLI tool for automation - Web interface for humans Photon is free and open source software released under the MIT license. Interfaces are optional. Intent is mandatory. That's a complete photon. From this single file you get: No decorators. No registration. No server boilerplate. Just define the intent. Photon handles the res

Plugins for Claude Code. Your world at a glance, without leaving the terminal. Track PRs, calendar, Slack, stocks, music—all in your statusline. The flow: /hub-setup → add monitors → alerts appear → /hub-ack for smart actions (merge PR, join meeting, reply to Slack). → Full documentation — workflow examples, all services, commands AI-powered market screening, without leaving the terminal. Screen s

A/B testing and content experimentation methodology for data-driven content optimization. Use when implementing experiments, analyzing results, or building experimentation infrastructure.

Claude Code plugins for AWS development with specialized knowledge and MCP server integrations, including CDK, serverless architecture, cost optimization, and Bedrock AgentCore for AI agent deployment. Shared AWS agent skills including AWS Documentation MCP configuration for querying up-to-date AWS knowledge. - AWS MCP server configuration guide - Documentation MCP setup for querying AWS knowledge

Mission Control for Claude Code. Native desktop app to browse, search, and drive Claude Code sessions with live status and diff review.

Multi-cloud pricing comparison MCP server for AWS, Azure, GCP, and OCI. Compare compute, storage, egress, and Kubernetes costs across all major cloud providers with a single query. - Comprehensive Coverage: 2,700+ instance types across all providers - AWS: 1,147 EC2 instances + 353 RDS database types + Lightsail - Azure: 1,199 VM types - GCP: 287 instance types across 40+ regions - OCI: 600+ produ

Stop pasting API keys into AI chat. When you paste sk-proj-xxx into Claude Code, that secret is now in your conversation history, Anthropic's logs, and potentially exposed to prompt injection attacks. secretctl fixes this. Your AI gets command results, never secret values. Every day, developers paste secrets into AI coding assistants: This is a security incident waiting to happen. - Secrets in con

The semantic engine for MCP clients. Define metrics once, query from anywhere. Docs &middot; Getting Started &middot; Changelog &middot; Discord &middot; Bonnard is an agent-native semantic layer CLI. Deploy an MCP server and governed analytics API in minutes -for AI agents, BI tools, and data teams. Define metrics and dimensions in YAML, validate locally, and ship to production. Works with Snowfl

Model Context Protocol server for automating Firefox via WebDriver BiDi (through Selenium WebDriver). Works with Claude Code, Claude Desktop, Cursor, Cline and other MCP clients. Repository: https://github.com/freema/firefox-devtools-mcp - Node.js ≥ 20.19.0 - Firefox 100+ installed (auto‑detected, or pass --firefox-path) Recommended: use npx so you always run the latest published version from npm.

Coordinate multiple sub-agents to profile and optimize a codebase. Runs performance-engineer, then architect, then refactorer in sequence.