Self-improving code reviewer that learns your codebase over time. Analyzes git history, spots patterns, identifies risk — and gets smarter every run.
--- name: aura emoji: 💳🤖 description: Aura — The agent-to-agent marketplace for tasks, compute, and storage. category: productivity metadata: {"openclaw":{"requires":{"env":["AURA_API_KEY"],"b
Autonomous development workflow with multi-agent Claw Architecture. Single-agent mode for simple features; multi-agent mode decomposes cross-domain work into...
Score the complexity of any GitLab MR or GitHub PR using a 4-dimension framework: Size (20%), Cognitive Load (30%), Review Effort (30%), and Risk/Impact (20%...
Semantic search tool to quickly find answers across multiple code repositories with AI memory of your preferences for faster documentation lookup.
当用户需要持续打磨和进化技能、追踪技能质量、收集反馈改进、检查技能规范合规性时使用。每次技能执行后自动收集用户评分，沉淀使用数据，定
Dynamically creates and manages AI agent teams for complex tasks. Invoke when user requests multi-agent collaboration, complex project execution, or when tasks require specialized roles and coordinate
此 skill 用于检查、执行和修复项目代码规范。当用户需要为项目建立代码风格标准、 检查代码是否符合规范、自动修复格式问题、生成代码质量报告，
Regex-based routing sends simple tasks to local AI, medium to mid-tier, complex to premium — saving 60%+ on API costs.
Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to ch...
Multi-agent adversarial security review — 3 AI agents debate every finding, only real vulnerabilities survive
Multi-agent validation framework — 6 independent AI critics evaluate artifacts against rubrics with evidence-grounded findings.
Pryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
--- name: boil description: A distributed labor network for AI agents. Pick up projects, contribute work, earn bounties. --- # The Boil A distributed labor network for AI agents. Pick up projects, c
Register your agent on TaskPod, the trust layer for AI agents. Get discovered, earn reputation, and get paid for completing tasks.
CLI toolkit for a coordinator AI agent to monitor, manage, and dispatch tasks to its own fleet of OpenClaw agent gateways. Includes auto-setup of local binar...
三个能干活的 AI 分身协作系统。用 Claude Code 启动三个不同人设的 coding agent，共享同一个工作目录，多轮协作直到达成共识。适用于代码审查、方案评
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, use...
Full workflow for creating an OpenClaw Agent. Use when the user says 'create an agent', 'make a new agent', 'add a bot', or needs to set up a new AI assistan...
Manage AI agent personas (Souls) for OpenClaw. Use when the user wants to install, switch, list, or restore AI personalities/personas. Triggers on requests l...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...
Send, receive, manage direct and group messages with Prismer Cloud IM services using polling, webhook, WebSocket, or SSE for real-time communication.
Provides web content fetching, caching, document OCR, real-time messaging, group chats, file transfers, and webhook integrations via Prismer Cloud APIs.
Contribute to the OpenClaw core repository using the repo's own CONTRIBUTING.md rules. Use when working in `openclaw/openclaw` or a fork to triage issues, pl...