MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It directly solves the common problem of agents producing verbose, fragile skills by offering a structured, self-demonstrating framework of design principles, anti-patterns, and decision trees, all drawn from official documentation and community experience.
Who it is for
- Developers using AI coding agents (OpenCode, Codex, Claude Code, Cursor)
- Skill authors building reusable agent instructions
- AI tool power users who want to improve agent output quality
Use cases
- Teaching an agent to create well-architected skills for specific tasks
- Debugging and refining existing skills that fail in practice
- Learning best practices for skill structure, routing, and maintenance
- Auditing third-party skills for consistency and anti-drift
Strengths
- Single-file 328-line design with a task routing table for quick access
- Six design principles each paired with a check question and inline anti-pattern warning
- Includes a decision tree, degrees of freedom framework, and quality checklists
- Provides concrete examples of common patterns (gotchas, templates, validation loops)
Considerations
- Requires a compatible AI agent that supports skills (OpenCode, Codex, Claude Code, Cursor)
- Does not cover prompt phrasing or safety boundaries (orthogonal to prompt-writing skills)
- Self-referential nature may require initial effort to understand its own design principles
README quick start
Installation
Description
A skill that teaches agents how to design, write, and review agent skills — covers trigger design, progressive disclosure, common patterns, anti-patterns, and quality gates. Built from Anthropic, OpenAI, and community best practices. | 一个教 Agent 如何设计、编写和审查 Skill 的 Skill —— 涵盖触发设计、渐进披露、常见模式、反模式和质量关卡。综合 Anthropic、OpenAI 及社区最佳实践。
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.