Total 33,408 skills
Showing 12 of 33408 skills
OneKey monorepo architecture, project structure, package relationships, and import hierarchy rules.
Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure.
Expert guide for QuickBooks Online API integration covering authentication, CRUD operations, batch processing, and best practices for invoicing, payments, and customer management.
This skill should be used when running CI checks iteratively and fixing failures. Use when executing make targets (fast-ci, all-ci, ci), iterating on lint/format/type/test errors, or needing the devrun agent pattern for pytest/ty/ruff/prettier/make/gt commands.
Model Context Protocol development expert. Use when creating MCP servers, clients, or tools that enable AI agents to interact with external systems, APIs, and development environments.
Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.
Unified integration skill for React Native Update / Pushy（统一入口）across OpenClaw and Claude Code workflows. Use for 安装配置, appKey/update.json 接线, iOS/Android 原生改动, 更新策略（checkStrategy/updateStrategy）, expo-updates 冲突排查, and 热更新接入 troubleshooting in mixed agent CLI environments.
Use when syncing skills from local folders, GitHub URLs, or skillsmp.com pages to multiple AI coding tool directories
Used to publish recruitment posts on X (x.com). It includes copywriting specifications, image generation prompts and automated publishing scripts, and is preferred for use when publishing AI-related or design-related positions.
Create soft links (symbolic links) supporting Windows, macOS and Linux systems. Automatically select the correct command to create soft links for directories or files according to the current operating system. This skill is used when users need to create soft links, symbolic links, or need to share files/directories in different locations.
Execute git and GitHub operations through Grove Wrap (gw) with safety-tiered commands, Conventional Commits, and agent-safe defaults. Use when making commits, managing branches, working with PRs/issues, or performing any version control operations.
Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.