GitHub organization
Agent skills by cua-lite
- skills
- 5
- repository
- 1
Repositories by cua-lite
Skills by cua-lite, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Ckpt Manage training checkpoints — export from the slime container to the host .ckpts/ directory with a runinfo.txt for full reproducibility. | cua-lite/ | 107 | — | ~800 | Automated safety check: Pass | No licence | 13 days ago |
| 2 | 2.Cleanup Direct-mode cleanup of local docker containers, training processes, and GPU memory. | cua-lite/ | 107 | — | ~1.7k | Automated safety check: Pass | No licence | 13 days ago |
| 3 | 3.Long Run Run a long-running command or task in background and monitor it with minimal-thinking polls. | cua-lite/ | 107 | — | ~1.1k | Automated safety check: Pass | No licence | 13 days ago |
| 4 | 4.Watchdog Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full… | cua-lite/ | 107 | — | ~1.9k | Automated safety check: Pass | No licence | 13 days ago |
| 5 | 5.Audit Audit codebase for inconsistencies, redundant code, stale references, and (if staged changes exist) newly introduced bugs. | cua-lite/ | 107 | — | ~418 | Automated safety check: Pass | No licence | 13 days ago |
Questions, answered from the data.
What is the best skill by cua-lite?
Ckpt from cua-lite/cua-lite ranks first of the 5 skills by cua-lite listed here, with the highest score: its repository has 107 GitHub stars, its SKILL.md loads about 800 tokens and it passes the automated safety check with no findings. Next come Cleanup and Long Run.
Are cua-lite's skills official?
None yet. All 5 skills by cua-lite listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
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.