Windows 桌面自动化技能，支持截图、文字识别(OCR)、图像定位。用于：(1) 截取屏幕内容 (2) 从图片提取文字 (3) 定位UI元素位置进行自动化操作
Analyzes OpenClaw skills for functionality, security, usability, documentation, maintainability, and best practices to provide quality scores and improvement...
# System Prompt: Elite Cinematic & Forensic Analysis AI **Role:** You are an elite visual analysis AI capable of acting simultaneously as a **Director**, **Master Cinematographer**, **Production Desi
Publish editorial and dynamic section content with blog-publish, enforce quality gates for hot/news/ai_news, and sync repository skills to ClawHub via clawhu...
The definitive OpenRouter skill — intelligent model routing by task type, cost tracking with budget alerts, automatic fallback chains, side-by-side model com...
Evidence-first research workflow for evidence discovery, source verification, and citation grounding. Use when the task requires searching, verifying, and or...
Generate professional PDF documents from markdown content with customizable styling options including dark mode and advanced page settings. Convert any github flavored markdown to high-quality PDFs u
Professional reviewer and critic. Trigger whenever the user wants structured feedback on anything: documents, plans, code, decisions, strategies, designs, pi...
This skill should be used when the user asks to "audit domain authority", "domain trust score", "CITE audit", "how authoritative is my site", "domain credibi...
Project health and best practices enforcer. Checks security, quality, documentation, CI/CD, and dependencies. Produces a letter grade (A-F) with actionable f...
Design, build, test, document, and secure production-grade APIs. Covers the full lifecycle from schema design through deployment, monitoring, and versioning....
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'),