826 boosters for "agent" — open source, verified from GitHub, ready to install
An orchestrator booster that automatically fetches GitHub issues, spawns AI sub-agents to implement fixes, opens pull requests, and manages review feedback. Ideal for teams looking to automate bug triage and fix workflows.
"name": "research-companion", "description": "Strategic research thinking agents — idea evaluation, project triage, and structured brainstorming inspired by Carlini's research methodology", "name": "Andre Huang",
Quoroom is an experimental open-source framework for building local AI agent systems with a Queen-Workers-Quorum architecture, designed for researchers and developers exploring multi-agent AI patterns with Claude and other LLMs.
1. Preserve custom rules from existing .gitignore 3. On auth error (401), retry with 4. Re-add preserved custom rules
A planning-first agent that generates structured task breakdowns before execution, helping developers clarify scope and avoid missteps on complex code operations. Ideal for teams using Claude in agentic workflows.
This skill documents how to run the Parchi relay daemon, connect the browser extension as an agent, and use the CLI to drive browser automation. 1. Build everything: 2. Start the relay daemon (terminal A):
"name": "langchain-skills", "description": "Agent skills for building agents with LangChain, LangGraph, and Deep Agents", "name": "LangChain",
BlockRun MCP Server enables Claude users to access 30+ AI models through x402 micropayments without requiring API keys. This benefits developers who want flexible model access and cost-efficient AI inference across multiple providers.
Heuristic scoring (no AI key configured).
This booster provides expert guidance for developing, debugging, and optimizing Azure AI Document Intelligence applications, covering architecture, security, best practices, and deployment patterns. Developers building document processing solutions on Azure will benefit from its comprehensive troubleshooting and design pattern knowledge.
VTCode is a system prompt designed to enhance a semantic AI coding agent for terminal-based development environments, providing clearer instructions and error handling for developers using Claude, Cursor, Windsurf, or ChatGPT.
"name": "ensue-memory", "description": "Persistent memory layer for AI agents via Ensue Memory Network", "email": "founders@ensue.dev"
This skill parses natural language shopping queries to extract structured product requirements like attributes, price limits, and specifications for e-commerce agents. It benefits developers building AI-powered shopping assistants and agents that need intelligent query understanding.
"name": "power-bi-agentic-development", "version": "0.19.0", "description": "A marketplace for skills and tools for agentic Power BI development.",
wraps your coding agent (Claude Code, Codex, OpenCode) in composable workflows: review loops, repeat passes, parallel races, and task-list orchestration. Operators compose left to right. Loop operators wrap everything to their left. Custom review/gate prompts (positional shorthand):
A CLI skill for interacting with Obsidian vaults—read, create, search, and manage notes, tasks, and properties directly from the command line, plus plugin/theme development support. Useful for developers and power users who want to automate vault operations and debug Obsidian extensions.
A system prompt for training AI agents on terminal/coding tasks using GRPO, enabling autonomous task completion in containerized Linux environments. Ideal for developers building advanced AI coding assistants and automation systems.
Sub-Agents is a lightweight framework for decomposing complex tasks into specialized child agents that collaborate under a parent orchestrator agent. Developers building multi-agent systems in Python will benefit from this pattern for creating modular, reusable agent hierarchies.
"description": "Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.", "sideEffects": false, "memorix": "./dist/cli/index.js"
You are writing behavioral specifications for functions/methods in a codebase. The codebase may be written in any programming language. Read these rules carefully before writing any spec. Describe what the function GUARANTEES to callers, not how it achieves it. Frame specs in terms of: Specifically
This Cursor rule guides developers to use Bun as their default runtime and build tool, replacing Node.js, npm, and common libraries with Bun's native equivalents. Ideal for agents and indie developers building with Cursor who want to standardize on Bun's faster, integrated toolchain.
LC-StudyLab provides Cursor IDE rules and documentation links for LangChain v1.0, enabling developers to quickly reference core components and advanced features while coding with LangChain's full ecosystem.
"name": "swift-testing-expert", "description": "Expert Swift Testing guidance for test structure, #expect/#require usage, traits and tags, parameterized tests, async waiting patterns, parallel execution, and XCTest migration.", "name": "Antoine van der Lee",
"name": "orchestrator-supaconductor", "description": "Conductor v3 — Multi-agent orchestration with Evaluate-Loop, parallel execution, Board of Directors, and bundled SupaConductor skills for Claude Code", "orchestrator-supaconductor",
