Repository
EvolvingLMMs-Lab/LLaVA-OneVision-2 agent skills
- skills
- 8
- GitHub stars
- 1.2k
GitHub description: “Fully Open Framework for Democratized Multimodal Training”
- Stars
- 1,216 (75 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Sep 2025
- llava
- llm
- mllm
- qwen3
- vision-language-model
- llava-onevision
Install all skills
npx skills add EvolvingLMMs-Lab/LLaVA-OneVision-2Add --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in EvolvingLMMs-Lab/LLaVA-OneVision-2, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guide for writing clear, consistent git commit messages following this repository's conventions | EvolvingLMMs-Lab/ | 1.2k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Bilingual guide for understanding how culengths controls attention behavior across ViT and LLM stages, and how patchpositions scope differs between the two | EvolvingLMMs-Lab/ | 1.2k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Bilingual guide for running offlinepacking/autopipe.sh across multiple nodes to produce padding-free packed WebDataset shards for SFT, with Energon Metadataset assembly | EvolvingLMMs-Lab/ | 1.2k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Bilingual guide for understanding LengthPoolSortDataset cross-rank length synchronization mechanism in multi-GPU training | EvolvingLMMs-Lab/ | 1.2k | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Bilingual guide for running and interpreting LLaVA-OneVision2 HF vs Megatron consistency checks across TP and PP settings | EvolvingLMMs-Lab/ | 1.2k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Bilingual guide for the OFFLINEPACKINGBMR and OFFLINEPACKEDDATA environment variables that control LLaVA-OneVision2 training-side packing — what each gate does, why both must be enabled together… | EvolvingLMMs-Lab/ | 1.2k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Bilingual guide for merging ViT + LLM into LlavaOnevision2 HF checkpoint and validating weight/inference consistency | EvolvingLMMs-Lab/ | 1.2k | — | ~7.6k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Bilingual guidance for Megatron checkpoint 1D 2D 3D mprank layouts across tensor pipeline and expert parallel dimensions | EvolvingLMMs-Lab/ | 1.2k | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill in EvolvingLMMs-Lab/LLaVA-OneVision-2?
Commit Message from EvolvingLMMs-Lab/LLaVA-OneVision-2 ranks first of the 8 skills in EvolvingLMMs-Lab/LLaVA-OneVision-2 listed here, with the highest score: its repository has 1.2k GitHub stars, its SKILL.md loads about 1.9k tokens and it passes the automated safety check with no findings. Next come Cu Lengths Attention Flow and Distributed Offline Packing.
Are the skills in EvolvingLMMs-Lab/LLaVA-OneVision-2 official?
None yet. All 8 skills in EvolvingLMMs-Lab/LLaVA-OneVision-2 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 EvolvingLMMs-Lab/LLaVA-OneVision-2?
Run npx skills add EvolvingLMMs-Lab/LLaVA-OneVision-2 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.