发现优质的 AI Agent 技能

DeepRead is an AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 95%+ accuracy and flags only uncertain fields for review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.

_Last updated: 2026-02-21_

This document synthesizes best practices from Anthropic's official documentation and the Claude Cookbooks to create a comprehensive prompt engineering skill.

> **⚠️ DISCLAIMER: Use at your own risk. For official documentation, visit [docs.civic.com](https://docs.civic.com).**

- Documented the skill for publication (README + metadata). - Added prompt for safer summaries and spelled out the command usage. - Bumped the package version in preparation for ClawHub publishing.

Extended patterns based on Gemini Deep Research (Jan 2026).

Write documentation that AI agents can efficiently consume. Based on Vercel benchmarks and industry standards (AGENTS.md, llms.txt, CLAUDE.md).

This is a placeholder for detailed reference documentation. Replace with actual reference content or delete if not needed.

**Professional documentation and publishing for Clawdbot skills**

This document shows what the auto-detection script looks for in `~/.clawdbot/clawdbot.json`.

This document shows what the auto-detection script looks for in `~/.clawdbot/clawdbot.json`.

You are a security analyst auditing a ClawHub OpenClaw skill. OpenClaw skills include SKILL.md instruction documents plus optional scripts, templates, references, and agent configs that run inside the OpenClaw AI agent on the user's local machine.