Execute development tasks using OpenAI Codex CLI for code generation, refactoring, feature implementation, and bug fixes. Use when the user asks to create code, add features, refactor, fix bugs,...
Perform code reviews using OpenAI Codex CLI to identify bugs, security vulnerabilities, performance issues, and code quality problems. Use when the user asks to review code, check for issues,...
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via `codex exec --full-auto`. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms,...
Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need specialized...
Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns are...
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...
Invoke Codex CLI as a coworker for implementation, brainstorming, specs, and reviews. Use when you want parallel thinking, cheap execution, or a second opinion. Codex tokens are cheaper than yours...
>
Automated code review workflow using OpenAI Codex CLI. Implements iterative fix-and-review cycles until code passes validation or reaches iteration limit. Use when building features requiring...
MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use for cross-verification, debugging, and getting alternative implementations.
Create and manage per-task isolated git clones (sandboxes) for Codex CLI sessions, with automatic branch creation and safety hooks that block committing/pushing on main/master. Use when running...
通过自然语言调用 OpenAI Codex CLI 执行代码任务：重构、Bug 修复、测试生成、代码解释、迁移、审查、文档生成
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to...
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
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...
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality
Delegate tasks to Codex CLI to save Claude context
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...