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,...
Run Codex CLI for deep code analysis and second-opinion reviews. Use when the user explicitly asks for Codex analysis, Codex help, or wants a second opinion from Codex on code, architecture, or...
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Idea for brainstorming and planning.
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,...
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...
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...
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...
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...
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...
>
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...
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
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...
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with...
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality