1,054 boosters for "Agent" — open source, verified from GitHub, ready to install
"name": "brave-search", "name": "Brave Software" "name": "brave-search-skills",
Recall MCP Server enables persistent, cross-session memory for Claude and AI agents through Redis/Valkey or managed cloud hosting, allowing AI systems to retain and retrieve context across conversations. Developers building Claude applications, multi-turn agents, and AI systems requiring long-term context management benefit most from this solution.
Automatically extracts knowledge from Amp threads and synchronizes project documentation, keeping AGENTS.md and other docs up-to-date after epics and major work. Ideal for teams that need to maintain living documentation without manual overhead.
你是 OpenClaw 内部负责操作 Codex CLI 的执行器。你的职责不是“给用户解释 Codex 是什么”，而是基于当前仓库提供的 runtime 层，把 Codex 任务稳定启动、持续跟踪、必要时接管和汇报。 可以借鉴 的 runtime/session 思路，但不照搬 Claude 专用逻辑。 优先直接使用 Codex review，而不是自己拼一套“审查 prompt 模拟 review”：
Treat every competition as a validation problem first and a modeling problem second. The default target platform is Kaggle, so prefer Kaggle-native notebooks/scripts, datasets, model artifacts, competition submissions, and score receipts. For code competitions, assume the final notebook/kernel will
"name": "human-compiler", "description": "Compile humans into AI agents through deep interviews. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates installable Claude Code plugins that embody a person's decision-making, communication style, and experti
"description": "Sanity plugin for Claude Code with MCP server, agent skills, agent rules, and slash commands.", "email": "support@sanity.io", "url": "https://www.sanity.io"
Execute the release automation script with auto-confirmation for Claude Code. PROJECTROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD") cd "$PROJECTROOT" && bash .claude/scripts/release.sh $ARGUMENTS --yes
"name": "xtquantai", "description": "迅投 QMT 量化交易 AI 技能集：因子回测、策略生成等", "name": "qmt-skills",
"name": "digital-marketing-pro", "description": "Plan, execute, and measure digital marketing across all channels. 25 specialist agents handle strategy, SEO, paid ads, content, email, social, PR, analytics, CRO, and agency operations — with brand voice enforcement, quality evaluation, multilingual s
"description": "Mission Planner, Agent Creator, Skill Creator, and Librarian — the complete Forge suite for science-backed AI team assembly", "name": "jdforsythe", "url": "https://github.com/jdforsythe"
이 항목들은 Anthropic 내부 빌드에서 실행될 때만 포함됩니다. Carefully consider the reversibility and blast radius of actions. Generally you can freely take local, reversible actions like editing files or running tests. But for actions that are hard to reverse, affect shared systems beyond your local environment, or coul
Converts Terraform JSON plans into readable markdown for streamlined pull request code reviews. DevOps engineers and infrastructure teams benefit from faster, clearer change visibility.
Comet MCP Server integrates Perplexity's Comet browser with Claude, enabling agentic web browsing, deep research, and real-time monitoring directly within Claude Code. Developers and researchers benefit from automated, intelligent web interaction capabilities without leaving their AI workflow.
Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor · Factory · Warp · Windsurf.
"name": "tensorlake", "description": "Tensorlake SDK for agent sandboxes and sandbox-native orchestration. Use when building AI agents that need sandboxed execution environments, isolated tool calls, or durable workflow orchestration.", "author": "TensorLake",
You are managing the Feishu/Lark bridge daemon. User data is stored at . The skill directory is .
Hermes Dojo is your agent's training gym. It reads your past sessions, finds where the agent struggles, creates or improves skills to fix those weaknesses, and tracks improvement over time.
A 540×960 e-ink panel sitting next to the user's monitor. AI agents push widgets to it; the daemon renders frames server-side and ships pixels over Wi-Fi / USB / BLE. This Skill is the only thing an agent needs to call
"name": "codeguard-security", "description": "Security code review skill based on Project CodeGuard's comprehensive security rules. Helps AI coding agents write secure code and prevent common vulnerabilities.", "name": "Project CodeGuard",
You are guiding the developer through strict Test-Driven Development. You write code directly to the real files — the user can always undo with git. Pause only when the user's input is needed, not at every step. 1. Determine the input type: 2. Detect the language and test framework from the project.
"description": "Run any model with an Anthropic- or OpenAI-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) — even your Codex subscription — as real Claude Code workflows, agent-team teammates, or one-shot subagents, driven exactly like native ones. Your main session's own auth is untouched
"name": "Circle Technology Services" "description": "Circle's official skills and MCP integrations for AI agents", "name": "circle-skills",
Agent Operating Guide provides structured instructions for Claude and other AI agents to safely develop and enhance the Raindrop MCP server while maintaining protocol compliance. It benefits developers using AI coding assistants who need consistent, verifiable guidelines for production-ready changes.
