Repository
inclusionAI/AReno agent skills
- skills
- 10
- GitHub stars
- 323
GitHub description: “An easy-to-use, fast toolkit to scale up RL post-training on a single node.”
- Stars
- 323 (127 forks)
- Licence
- Apache-2.0
- Last push
- Sep 2026
- Created
- Jun 2026
- agent
- agentic-ai
- grpo
- llm
- machine-learning
- post-training
- reinforcement-learning
- rl
- sft
- local-ai
- local-llm
- self-hosted
Install all skills
npx skills add inclusionAI/ARenoAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in inclusionAI/AReno, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Diagnose failed, hung, slow, OOM, NaN, illegal-memory-access, NCCL, compilation, rollout, or training runs in AReno. | inclusionAI/ | 323 | — | ~486 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 2 | Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator. | inclusionAI/ | 323 | — | ~498 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 3 | Run, configure, retry, and validate AReno SFT, DPO, GSPO, GRPO, PPO, and agentic training. | inclusionAI/ | 323 | — | ~782 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 4 | Add or modify an AReno algorithm, trainer, loss, advantage calculation, role model, or algorithm-specific configuration. | inclusionAI/ | 323 | — | ~501 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 5 | Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance. | inclusionAI/ | 323 | — | ~848 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 6 | Compare an AReno branch, model, checkpoint, algorithm, scheduler, or kernel against a baseline. | inclusionAI/ | 323 | — | ~389 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 7 | Add or debug an AReno model family, including config conversion, module construction, checkpoint load/save, text or multimodal inference, training backward, tensor parallelism, CUDA graph decode… | inclusionAI/ | 323 | — | ~722 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 8 | Create or debug an AReno multi-turn agentic dataset, runagent implementation, tool schemas, tool execution, reward, loss masks, interactive TUI game with OpenAI-compatible LLM inference, or agentic… | inclusionAI/ | 323 | — | ~435 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 9 | Start, validate, debug, and stop an AReno OpenAI-compatible serving endpoint. | inclusionAI/ | 323 | — | ~409 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 10 | Fit an AReno training or rollout workload to available GPUs by tuning TP, mini-batch, batch, sample count, and rollout concurrency. | inclusionAI/ | 323 | — | ~353 | Automated safety check: Pass | Apache-2.0 | 13 days ago |
Questions, answered from the data.
What is the best skill in inclusionAI/AReno?
Areno Debug Runtime from inclusionAI/AReno ranks first of the 10 skills in inclusionAI/AReno listed here, with the highest score: its repository has 323 GitHub stars, its SKILL.md loads about 486 tokens and it passes the automated safety check with no findings. Next come Areno Develop Kernel and Areno Run Training.
Are the skills in inclusionAI/AReno official?
None yet. All 10 skills in inclusionAI/AReno listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from inclusionAI/AReno?
Run npx skills add inclusionAI/AReno in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.