为 Claude Code 会话提供的正式评测框架，实现了评测驱动开发（Eval-Driven Development，EDD）原则

Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents,...

Install skills from github.com/oaustegard/claude-skills into /mnt/skills/user. Use when user mentions "install skills", "load skills", "add skills", "update skills", "refresh skills", or...

Unified installer for Claude Code Skills from multiple sources. Triggered when users request to install skills, search for skills, list installed skills, update skills, query supported...

Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome...

[Skill] Create detailed implementation plans for features. Asks clarifying questions, suggests solutions, proposes architecture, and outputs a structured plan document. Use when user wants to plan...

Use when answering legal questions about UAE business law, including startup formation (LLC, DIFC, ADGM, free zones), shareholder agreements, SAFE notes, convertible notes, healthcare licensing...

[Skill] Perform thorough code reviews focusing on unused code, duplications, coding patterns, bugs, and optimizations. Use when user wants code reviewed or audited. Read-only - outputs findings...

Use when answering legal questions about UAE business law, including startup formation (LLC, DIFC, ADGM, free zones), shareholder agreements, SAFE notes, convertible notes, healthcare licensing...

Create interactive data visualizations using Vega-Lite declarative JSON grammar. Supports 20+ chart types (bar, line, scatter, histogram, boxplot, grouped/stacked variations, etc.) via templates...

Optimize content for AI search engines (ChatGPT, Perplexity, Claude, Gemini) and featured snippets. Covers Generative Engine Optimization (GEO), Answer Engine Optimization (AEO), E-E-A-T signals,...

Generate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of...

Expert-guided project setup with 6 phases

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture...

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster...

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting,...

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search,...