发现优质的 AI Agent 技能

Check prompts and outputs for Claude safety alignment

Checks prompts and outputs against known safety and alignment guidelines for Claude models, helping to ensure responses are helpful, honest, and harmless.

Optimize prompts specifically for Claude models

Optimizes your prompts specifically for Claude's constitutional AI and reinforcement learning from human feedback (RLHF) patterns, ensuring clearer instructions and more accurate responses.

Distill large context for better Claude performance

Distills large volumes of text into the most essential information, maximizing the value of Claude's context window while minimizing noise.

Generate structured artifacts for Claude models

Generates high-quality, structured artifacts (code, SVG diagrams, JSON, Markdown) designed to be compatible with Claude's Artifacts UI.

Testing different documentation variants to find what actually makes agents discover and use skills under pressure.

> Learn how to write effective Skills that Claude can discover and use successfully.

Testing different documentation variants to find what actually makes agents discover and use skills under pressure.

> Learn how to write effective Skills that Claude can discover and use successfully.