# Training

> Training is an Agent Skill for devops & security published in the PrimeIntellect-ai/prime-rl repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).

- Skill name: `training`
- Category: [DevOps & Security](https://www.openparable.com/skill/devops-security/1)
- Source: https://github.com/PrimeIntellect-ai/prime-rl/blob/HEAD/skills/training/SKILL.md
- Repository: PrimeIntellect-ai/prime-rl (1,663 GitHub stars when collected)

## SKILL.md

# Training

Two phases — start the run, then watch it.

- **Start a run** — see `start-run/SKILL.md` for the `rl`, `sft`, and `inference` entrypoints and how to launch them (single-node, SLURM, dry-run).
- **Monitor a run** — see `monitor-run/SKILL.md` for the runbook: how to find the output dir, what to tail, which metrics to watch, and how to restart safely.

Both subskills assume the `configs` skill for config-loading mechanics.

---

Source: https://www.openparable.com/skill/devops-security/training (OpenParable). Cite the canonical URL above.