Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission.
Add support for a HuggingFace model in XTuner so it can be trained with the full set of parallelism strategies and optimization switches. The user can provide a HuggingFace Hub repo id, a local model directory, or a model family already supported by `transformers`. This skill walks through the full path: locating the reference implementation, classifying the model, splitting new code across the model / module / ops layers, implementing the XTuner model class and config, registering the entry point, validating bitwise numerical parity with HuggingFace, writing regression tests, and enabling the training optimizations (EP/SP, micro-batch, torch.compile, fp8, activation offload).
Normalize an HF model checkpoint — quantize bf16/fp16 weights to per-block FP8, and/or repack engine-named safetensors into HF-standard ~4GB shards.
Merge a base HF model dir with an extra HF model dir by index diff — take tensors only present in extra, append them to a new output dir in HF-standard shard layout. Base wins on overlap.
Use when `make html` or `sphinx-build` fails with `Extension error (sphinx.ext.autosummary)`, `ImportExceptionGroup`, or other Sphinx autosummary / autodoc import failures. Provides automated pdb diagnosis for `autodoc_mock_imports` issues.
Use when creating, modifying, or reviewing XTuner RL judgers under xtuner/v1/rl/judger or configs that build custom judgers. Enforces the preferred Judger payload contract and the BaseJudger/ComposedJudger constraints.
Synchronize xtuner's supported model documentation (docs/en/pretrain_sft/advanced_tutorial/model.md and docs/zh_cn/pretrain_sft/advanced_tutorial/model.md) with the actual Config classes defined under xtuner/v1/model/. Use when (1) new TransformerConfig, MoEConfig, or BaseComposeConfig subclasses are added, removed, or renamed in xtuner/v1/model/, (2) existing model configs change their inheritance hierarchy, scale, or HuggingFace counterpart, or (3) a code review or user request points out that model.md is out of sync with the codebase.