Skill Claude CodeCodex
Add or update UniRL model package support. Use when adding diffusion or autoregressive model pipelines, model config dataclasses, Bundle/Pipeline/Stage/Conditions implementations, LoRA targets, FSDP wrapping hints, Sample/Part plumbing, or multimodal text/image/video/audio conditioning.
Skill Claude CodeCodex
Create and repair UniRL pull requests. Use when creating a PR, editing a PR body, responding to PR Body or Semantic Pull Request CI failures, running gh pr create, or when the user mentions PR body, pull request template, body check, title check, or pull request formatting.
Cursor rule Cursor
Shared code agent behavioral guidelines.
Instructions file CodexOpenCode
AGENTS.md instructions for Tencent-Hunyuan/UniRL, a project described as: UniRL is a Framework for Unified Multimodal Model Reinforcement Learning.
Instructions file
Claude Code instructions for Tencent-Hunyuan/UniRL, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Skill Claude CodeCodex
A development workflow and coding-standard skill for Python, PyTorch, deep-learning code, shell scripts, and configuration files. It requires understanding the project, proposing a plan for approval, writing tests, simplifying code, and reviewing the result.