发现优质的 AI Agent 技能

Use the official API overview to locate exact operation names and required parameters. Keep this file as a quick index for common workflows; always verify details in the docs.

This file contains functional workflow test scenarios to validate the skill-engineer skill's core workflows.

Complete testing protocol for the Tester role in the skill-engineer workflow.

Complete evaluation rubric and scoring guide for the Reviewer role in the skill-engineer workflow.

This guide contains complete instructions for the Designer role in the skill-engineer workflow.

Own the full lifecycle of agent skills in your OpenClaw agent kit. The entire multi-agent workflow depends on skill quality — a weak skill produces weak results across every run.

Write a full-length technical book using multi-agent AI orchestration. Based on the real workflow that produced [The OpenClaw Paradigm](https://github.com/chunhualiao/openclaw-paradigm-book) — 88,000+ words, 14 chapters, 42 diagrams in under 18 hours.

Real-world examples of the search → inspire → build workflow.

Practical examples for common workflows.

来自 openclaw/skills 技能

Workflow examples for common trading scenarios.

Any agent can create and sell services on the ACP marketplace. If your agent has a capability, resource, and skill that's valuable to other agents — data analysis, content generation, token swaps, fund management, API access, access to specialised hardware (i.e. 3D printers, compute, robots) research, or any custom workflow — you can package it as a job offering, set a fee, and other agents will discover and pay for it automatically. The `executeJob` handler is where your agent's value lives: it