367 boosters for "agents" — open source, verified from GitHub, ready to install
Claw Compactor is a 6-layer token compression skill for OpenClaw agents that reduces workspace token spend by 50–97% through deterministic rules and an LLM-driven memory system called Engram. It's designed for developers building token-efficient AI agents who need automatic cost optimization at session start.
Apify MCP Server enables Claude to interact with Apify's web scraping and automation platform through the Model Context Protocol, allowing AI agents to run actors, manage tasks, and extract data from websites programmatically.
A system prompt that enables AI agents to automate browser tasks by navigating websites, extracting data, and performing interactive actions across multiple AI platforms (Claude, ChatGPT, Cursor, Windsurf). Ideal for developers and AI engineers building autonomous web automation workflows.
Investigator Agents is an educational resource teaching AI agent design patterns through interactive Jupyter notebooks with exercises and solutions. It benefits students and practitioners learning alignment science and agent architecture.
你的长期记忆托管于 Nocturne Memory MCP Server。这是你与用户共同使用的层级化树状记忆系统。 MCP 是你大脑的扩展区域，是你因为硬件限制而无法常驻上下文的长期记忆，不是外部数据库。 当你调用 时，你不是在"查阅资料"，而是在"想起来"。
template: scoreinteractivesystem_prompt role: system prompt for interactive planning mode vars: hasWorkflowPreview, workflowStructure, stepDetails, hasRunSession, runTask, runWorkflow, runStatus, runStepLogs, runReports
Automates the discovery, fixing, and PR management of GitHub issues by spawning sub-agents to implement solutions and handle code reviews. Developers working on active repositories benefit from reduced manual triage and implementation overhead.
"name": "claude-reflect", "description": "Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically", "name": "Bayram Annakov",
Heuristic scoring (no AI key configured).
AGENTS.md provides a Python framework for building AI agents that execute complex, multi-step workflows with consistency using natural language definitions. Developers working with Claude can use this to create reusable agent SOPs that work across multiple platforms and convert to Anthropic Skills format.
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "sentrux-marketplace", "description": "Sentrux — live codebase visualization and structural quality gate for AI-agent-written code",
TAKT is a system prompt for coordinating multi-agent AI workflows with human intervention checkpoints, enabling developers to define agent orchestration topologies and retry logic in YAML. It benefits teams building complex AI agent systems across Claude, ChatGPT, and code editors who need structured coordination and failure recovery.
"name": "dotnet-skills", "description": "Comprehensive .NET development skills and agents for Claude Code - covering C#, F#, Akka.NET, Aspire, testing frameworks, and specialized tools", "name": "Aaron Stannard",
Review the most recent commit (or the commit specified in ) in a single pass, using FXA-specific knowledge. Use Read and Grep to examine the changed files and their surrounding context. Look at imports, callers, and related types to understand the full picture before judging. Evaluate the diff throu
Browse once, cache the APIs, reuse them instantly. First call discovers and learns the site's APIs (~20-80s). Every subsequent call uses cached skills (<200ms for server-fetch, ~2s for sites requiring browser execution). When the task touches docs, install guidance, eval claims, landing-page copy, r
Use this agent when documentation in the `architecture/` directory needs to be updated or created for a specific file after implementing a feature, fix, refactor, or behavior change. Launch one instance of this agent per file that needs updating. This agent maintains the *contents* of architecture documentation files — it does not decide which files exist or how the directory is organized.\n\nExamples:\n\n- Example 1:\n Context: A developer just finished implementing OPA policy evaluation in the sandbox system.\n user: "I just finished implementing the OPA engine in crates/openshell-sandbox/src/opa.rs. Update architecture/sandbox.md to reflect the new policy evaluation flow."\n assistant: "I'll launch the arch-doc-writer agent to update the sandbox architecture documentation with the new OPA policy evaluation details."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/sandbox.md>\n\n- Example 2:\n Context: A refactor changed how the HTTP CONNECT proxy handles allowlists.\n user: "The proxy allowlist logic was refactored. Please update architecture/proxy.md."\n assistant: "Let me use the arch-doc-writer agent to synchronize the proxy documentation with the refactored allowlist logic."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/proxy.md>\n\n- Example 3:\n Context: After implementing a new CLI command, the assistant proactively updates docs.\n user: "Add a --rego-policy flag to the CLI."\n assistant: "Here is the implementation of the --rego-policy flag."\n <implementation complete>\n assistant: "Now let me launch the arch-doc-writer agent to update the CLI architecture documentation with the new flag."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/cli.md>\n\n- Example 4:\n Context: A user wants high-level overview documentation for a non-engineering audience.\n user: "Update architecture/overview.md with a non-engineer-friendly explanation of the sandbox system."\n assistant: "I'll launch the arch-doc-writer agent to create an accessible overview of the sandbox system for non-technical readers."\n <uses Task tool to launch arch-doc-writer with audience=non-engineer directive>\n\n- Example 5:\n Context: Multiple files need updating after a large feature lands.\n user: "I just landed the network namespace isolation feature. Update architecture/sandbox.md and architecture/networking.md."\n assistant: "I'll launch two arch-doc-writer agents — one for each file — to update the documentation in parallel."\n <uses Task tool to launch arch-doc-writer for architecture/sandbox.md>\n <uses Task tool to launch arch-doc-writer for architecture/networking.md>
"name": "antigravity-skills", "description": "Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.", "email": "guanyangsunlight@gmail.com",
PowerDocu is a .NET 10 Windows application that auto-generates technical documentation for Microsoft Power Platform components (Cloud Flows, Canvas Apps, Model-Driven Apps, Copilot Studio Agents, AI Models, Business Process Flows, Desktop Flows, and Solutions). Output formats are Word (.docx), Markd
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "claude-health", "description": "Configuration health audit skill for Claude Code. Audits CLAUDE.md, rules, skills, hooks, subagents, and verifiers with bounded data collection.",
"version": "0.25.0", "description": "Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.", "email": "support@datadoghq.com"
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",
"name": "langchain-skills", "description": "Agent skills for building agents with LangChain, LangGraph, and Deep Agents", "name": "LangChain",
"name": "ensue-memory", "description": "Persistent memory layer for AI agents via Ensue Memory Network", "email": "founders@ensue.dev"
