123 tagged reinforcement-learning, measured the same way as everything else here.
Browse within: llm-agents 66small-language-models 60fine-tuning 13GRPO 12rl 12NVIDIA 11llm-reasoning 11machine-learning-systems 11mlsys 11model-training 11nemotron 11Post-Training 10gym 10ai-research 9
Skill Claude CodeCodex ✓ vendor
Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows. Use when asked to plan, cut, verify, or explain a release; treat nightly TestPyPI builds as a separate path.
Skill Claude CodeCodex ✓ vendor
Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract. Use when optimizing agent accuracy, cost, latency, or reliability.
Orchestra-Research/AI-Research-SKILLs
Skill Claude CodeCodex
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
Skill Claude CodeCodex
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Skill Claude CodeCodex
Guide for adding unit tests to AReaL. Use when user wants to add tests for new functionality or increase test coverage.
Skill Claude CodeCodex
Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.
Skill Claude CodeCodex
Add a new step under src/nemotron/steps/ / / — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the catalog so /nemotron-customize can route to it.
Skill Claude CodeCodex
Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the user asks facts about the model rather than building a pipeline.
Skill Claude CodeCodex
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
Skill Claude CodeCodex
Guide for adding a new benchmark or training environment to NeMo-Gym. Use when the user asks to add, create, or integrate a benchmark, evaluation, training environment, or resources server into NeMo-Gym. Also use when wrapping an existing 3rd-party benchmark library. Covers the full workflow: data preparation…
Skill Claude CodeCodex
Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
Skill Claude CodeCodex
Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish docs", any request that touches fern/.
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.
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.
Skill Claude CodeCodex
Use when designing a new benchenv task suite, adding several new tasks to an existing suite, or critiquing a task-set proposal for a mobile-gym App — before any class FooTask(...) is written under benchenv/task/.
Skill Claude CodeCodex
Use when adding or modifying offline judge tests for benchenv tasks — specifically entries in OFFLINEJUDGEPOSITIVECASES / OFFLINEJUDGENEGATIVECASES in benchenv/tests/ /testtasks.py, or writing live tests. Triggers after a new task is added, or when tightening judge coverage.
Skill Claude CodeCodex
Use when writing or modifying checkgoals() / getanswer() / App check methods in benchenv/task/, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.
Skill Claude CodeCodex
Port an mjlab task to mjswan: turn a local or remote GitHub repo that registers mjlab tasks into a browser app. Use when the user wants to run, visualize, or deploy an mjlab task (theirs or a third party's) in the browser with mjswan.
Skill Claude CodeCodex
Build, inspect, run, and debug OmniSim robotics worlds through the first-party MCP tools. Use for requests involving OmniSim scenes, robots, cameras, contacts, physics checks, or screenshots; do not use for unrelated simulators.
Skill Claude CodeCodex
Rules and steps for creating a compute kernel in RL.cu project.
Skill Claude CodeCodex
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
Skill Claude CodeCodex
For SWE/code tasks -- listfiles then searchcode to locate, viewfile then editfile to fix.
Skill Claude CodeCodex
For factual QA -- one search usually suffices, answer quickly after one good source.