Skills and MCP tagged “ai-agents”

context-engineering addyosmani skill Helps you set up agent context: which rules, specs and files to feed the agent, and when. Use it at the start of a session, when output quality drops, or when switching tasks. Claude Code CX Codex Cursor +1 60,900installs hindsight-docs vectorize-io skill This skill gives AI agents Hindsight documentation for architecture, APIs, configuration, and SDKs. Use it when adding Hindsight memory to an agent. Claude Code CX Codex Cursor +1 9,100installs agent-introspection-debugging affaan-m skill Provides a structured self-debugging loop for AI agent runs that loop on tools, hit context limits, or fail repeatedly. Replaces blind retries with systematic diagnosis. Claude Code CX Codex Cursor +1 4,600installs agent-eval affaan-m skill Compares AI coding agents head-to-head on custom tasks using pass rate, cost, and time metrics. Helps teams select tools based on benchmarks instead of impressions. Claude Code CX Codex Cursor +1 4,500installs ai-first-engineering affaan-m skill Sets team process, review gates and architecture rules for codebases where AI agents produce most of the implementation. Claude Code CX Codex Cursor +1 4,500installs agent-governance official github skill Provides governance patterns for AI agents that use APIs, databases, or file systems. Use it when agent actions need policy checks, threat detection, and audit records. GitHub Copilot 9,623installs agent-platform-alert-configuration official google skill This skill creates Terraform alert policies for AI agents from OpenTelemetry metrics. Use it to watch latency, errors, token usage, and quality. Claude Code Gemini CLI CX Codex 6,857installs google-cloud-solution-agentic-ai-bidirectional-streaming official google skill This skill designs Google Cloud solutions for live, bidirectional multimodal streams handled by AI agents. Use it for real-time technical guidance or safety monitoring. Claude Code Gemini CLI CX Codex 5,411installs google-cloud-solution-build-deploy-agents official google skill This skill designs and deploys AI agents and multi-agent systems on Google Cloud. Use it when you need a guided path from requirements to deployment instructions. Claude Code Gemini CLI CX Codex 5,100installs prompt-engineer Seth Hobson subagent This subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work. Claude Code CX Codex Cursor 16,078installs developing-genkit-python official google skill A skill for building Genkit apps in Python: generation, streaming, tools, flows and agents. Useful when your agent fumbles imports or Genkit API calls. Claude Code Gemini CLI CX Codex 3,600installs developing-genkit-js official google skill This skill helps build and troubleshoot Genkit AI apps in Node.js and TypeScript. Use it for flows, agents, tools, and Genkit API errors. Claude Code Gemini CLI CX Codex 3,600installs antislop-code miqdadbadjuber skill This skill filters out comments that look AI-generated: ones that repeat what the code shows, chop the flow into steps, or decorate section headers. It keeps comments with real information and never touches executable code. Claude Code CX Codex Cursor +1 5,700installs flow-nexus-swarm ruvnet skill Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs n8n-agents czlonkowski skill A skill that guides the model through building n8n AI nodes: choosing Agent, chain or classifier, wiring memory and tools, keeping structured output from breaking. Claude Code CX Codex Cursor +1 1,900installs agent-architecture official github skill Designs AI agent architectures from requirements or audits existing agents for flaws. Focuses purely on architectural decisions and verification without implementing code. GitHub Copilot 42installs webmcpify official github skill This skill turns a web app into WebMCP tools for AI agents, checks them in a real browser, and heals issues found during verification. GitHub Copilot 27installs continual-learning microsoft skill A skill that teaches AI agents to remember mistakes, tool patterns, and project conventions between sessions. Without it, each run starts fresh; with it, agents compound their knowledge and work more accurately. Claude Code GitHub Copilot 79installs