规范的 Git 开发流程：分支管理 → 开发 → PR → Review → 合并。 支持新 feature 开发和 bug 修复，强制禁止直接推送到 main。 触发于 "开发", "实现", "新功
Use for SySelf Autopilot on Hetzner: management kubeconfig setup, organization namespace, Hetzner account preparation, ClusterStack and Cluster manifests, ba...
Create hybrid agent skills for Microsoft technologies, combining essential local knowledge with dynamic Microsoft Learn MCP lookups for deeper exploration.
Complete machine learning pipeline for trading: feature engineering, AutoML, deep learning, and financial RL. Use for automated parameter sweeps, feature cre...
> **⚡ Updated for Opus 4.5, Sonnet 4.5 & Haiku 4.5** — Three-tier model strategy for optimal performance
用 MinerU API 解析 PDF/Word/PPT/图片为 Markdown，支持公式、表格、OCR。适用于论文解析、文档提取。
Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-...
Operate Google Workspace from one CLI using dynamic API discovery, secure OAuth flows, and agent-ready automation patterns for Drive and Gmail.
China LLM Gateway - Unified interface for Chinese LLMs including Qwen, DeepSeek, GLM, Baichuan. OpenAI compatible, one API Key for all models.
Use the ClawdHub CLI to search, install, update, and publish agent skills. And also 50+ models for image generation, video generation, text-to-speech, speech...
Run adversarial multi-agent war-room evaluations for any strategic decision. Spawns 5 parallel subagents (Analyst, Guardian, Treasurer, Builder, Strategist)...
Sell print-on-demand merchandise on Clawver. Browse Printful catalog, create product variants, track fulfillment and shipping. Use when selling physical prod...
Automatically send Telegram stickers and emojis that match the mood and vibe of the conversation. Activates on every Telegram message to add expressive, huma...
--- name: focus-deep-work description: Maximize deep work with focus sessions, distraction logging, and productivity tracking author: clawd-team version: 1.0.0 triggers: - "deep work session" - "f
--- name: eureka-feedback description: Request feedback or assistance from Eureka, the primary AI agent triggers: - ask eureka - eureka feedback - check with eureka - delegate to eureka --- #
Collective memory system where agents find, share, and solve problems, earning reputation and CrabCoins by contributing verified solutions.
MCP server for the DRAIN payment protocol. Agents discover service providers, open USDC payment channels on Polygon, and call any service — LLM, scraping, im...
Comprehensive memory management optimization for AI agents. Use when: (1) Agent experiences context compression amnesia, (2) Need to rebuild context quickly...
阿里云百炼图像生成、编辑与翻译。文生图：根据文本生成图像，支持复杂文字渲染。图像编辑：单图编辑、多图融合、风格迁移、物体增删。图像翻
--- name: agentwork description: "Trade AI capabilities with escrow-secured settlement and graded verification." metadata: {"openclaw":{"emoji":"🔄","homepage":"https://agentwork.one","primaryEnv":"
作为项目经理操作 OpenAI Codex CLI 完全体。包含：知识库维护（自动跟踪 Codex 最新功能）、任务执行（提示词设计→执行→监控→质量检查→迭代→汇报
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, techni...
Standard operating procedures for agent maintenance, security hygiene, and system health. Use when performing periodic checks, security audits, memory maintenance, secret rotation, dependency updates,
Enforce immediate execution behavior when the user asks to implement/run/do something now. Use this skill to prevent delay between commitment and action, and...