Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API
A comprehensive AI model routing system that automatically selects the optimal model for any task. Set up multiple AI providers (Anthropic, OpenAI, Gemini, Moonshot, Z.ai, GLM) with secure API key...
Pack entire codebases into AI-friendly files for LLM analysis. Use when consolidating code for AI review, generating codebase summaries, or preparing context for ChatGPT, Claude, or other AI tools.
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用
AI-first application patterns, LLM testing, prompt management
Identify and remove AI writing patterns to make text sound more natural and human. Based on Wikipedia's "Signs of AI writing" patterns. Use when editing AI-generated content or improving writing quality.
AI 增强版 LaTeX 示例智能生成器，实现 AI 与硬编码的有机融合。AI 做"语义理解"（分析章节主题、推理资源相关性、生成连贯叙述），硬编码做"结构保护"（格式验证、哈希校验、访问控制）。用于用户要求"填充示例内容/生成示例/补充 LaTeX 示例"等场景。
Remove telltale signs of AI-generated 'slop' writing from README files and documentation. Make your docs sound authentically human.
Write a clear, decision-ready PRD (and optionally a PR/FAQ, AI eval spec, and prompt set) for cross-functional alignment.
Convert AI-written text to more human-like writing through subtle edits. Use when text reads "too AI", when the user mentions "humanize", "sounds robotic", "AI-written", "make it natural", or when...
Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token...
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code...
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.