发现优质的 AI Agent 技能

This skill implements a **Hardened Prompt Sanitization (HPS)** layer designed to mitigate indirect prompt injection attacks. It acts as a "buffer" between untrusted external data (web content, emails, files) and the Main Agent's execution context.

This document provides internal guidance on the EffortList AI "Omni" engine's processing logic. Understanding this allows for better coordination with the server-side agent.

All notable changes to tokenQrusher will be documented in this file.

This document provides detailed security analysis of the OpenClaw Token Optimizer skill.

All notable changes to the Token Optimizer skill are documented here.

"Domain-restricted full-text search over curated technical documentation"

Domain-restricted full-text search over a curated whitelist of technical documentation (MDN, Python docs, etc.). Provides clean, authoritative results without web spam.

**Purpose:** Documenting why each domain is whitelisted, what content it provides, and how to crawl it effectively.

Thank you for your interest in improving Curated Search! This document provides guidelines and instructions for contributing.

All notable changes to this project will be documented in this file.

Convert SVG files to PNG or JPG. Useful when you have vector graphics (e.g. from map-grabber, diagrams, or design tools) and need a raster image to send in chat or use in documents.

Generate financial analysis reports from uploaded Excel/PDF files with inline SVG sparkline trend charts and multi-format output.