rl-standard-job-cleanup

rl-standard-job-cleanup is a Fine-tuning & training data skill for AI agents, published by open-thoughts in the OpenThoughts-Agent repository on GitHub. Skillspace rates rl-standard-job-cleanup F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.

Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.

Preserve + publish a finished STANDARD (non-agentic GRPO) SkyRL RL checkpoint — the Delphi/rlvr/dapo math-and-reasoning cells launched via rl-standard-launch-leonardo (raw sbatch of hpc/skyrl_standard/leonardo/*, logger=console, NO Harbor/Daytona/trace_jobs). Covers: cancel pending retries, pick the BEST checkpoint by the trailing-5 EMA of reward via `parse_skyrl_metrics.py --format standard` (chain-aware, capped at the latest saved step), flatten weights to repo root, secret-scan, `hf upload` (Leonardo sbatch-tunnel) to laion/<run>-<step>-<size>B with the size suffix DERIVED FROM THE EXPORTED WEIGHTS (never the base-model name), DB register (--training-type RL + cross-user FK pre-check) ONLY for DB-registerable cells, clean up, and fire the Delphi downstream eval suite on the post-RL ckpt (defers to eval-standard-launch §5b). The ONLY artifacts are the model + the metric CSVs/report + the tracker scores — there is NO trace dataset. Use when a standard/non-agentic GRPO RL run finishes…

Grade

F

Quality

15 / 100

Safety

Unsafe

GitHub stars

259

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.