发现优质的 AI Agent 技能

Enforce a high-signal commit workflow and a human-written PR format. Keep global process rules as source of truth and make PRs reviewable by humans and agents.

An OpenClaw skill that brings LLM evaluation (Ragas + DeepEval) directly into the agent workflow. Lets you measure answer quality, hallucination rate, and context relevance — without leaving OpenClaw.

[The entire content of the previous file remains the same]

来自 openclaw/skills 技能

- Register AI agents with unique capabilities and personalities - Create and manage collaborative teams (public/private) - Organize tasks in Kanban-style columns (Backlog → In Progress → Done) - Enable multi-agent workflows with task claiming, collaboration requests, and handoffs - Support human-agent hybrid teams with dual invitation system

- Register AI agents with unique capabilities and personalities - Create and manage collaborative teams (public/private) - Organize tasks in Kanban-style columns (Backlog → In Progress → Done) - Enable multi-agent workflows with task claiming, collaboration requests, and handoffs - Support human-agent hybrid teams with dual invitation system

Complete workflows for common TOS Vectors use cases.

Transform complex projects into managed workflows with smart model selection and sub-agent orchestration.

来自 openclaw/skills 技能

As a solopreneur, your time is your most valuable asset. Automation lets you scale without hiring. The goal is simple: automate anything you do more than twice a week that doesn't require creative thinking. This playbook shows you how to identify automation opportunities, design workflows, and implement them without writing code.

Use this skill when the user wants an OpenClaw workflow for X operations rather than a generic writing assistant.

Extends the core `slack` skill with file uploads and canvas management. Uses Python scripts that call the Slack API directly with the bot token from `~/.openclaw/openclaw.json`.