发现优质的 AI Agent 技能

The genviral skill has full analytics built in. Use it. This document explains how to pull data, cross-reference it with `workspace/performance/hook-tracker.json`, and make decisions that improve content over time.

This file documents the underlying hook patterns. These are templates, not finished hooks. The agent generates specific hooks by combining a formula with the product context from `context/product.md`.

The genviral skill has full analytics built in. Use it. This document explains how to pull data, cross-reference it with `workspace/performance/hook-tracker.json`, and make decisions that improve content over time.

**Ditch human documentation.** Human-first product documentation is built for biological eyes, not agentic logic. It is slow, fractured, and full of noise.

DeepRead is an AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL) review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.

OCR that never fails silently. Process PDFs and extract structured data with AI-powered confidence scoring that tells you exactly which fields need human review.

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).