ProSkillsLibraryFreePassScan

Scan reports · Orchestra-Research/AI-Research-SKILLs

grpo-rl-training: scan report

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training An automated scan of this public skill from Orchestra-Research/AI-Research-SKILLs: security, token cost, spec and clarity, with every finding and its fix.

Result

Verdict

grpo-rl-training

57/100 · grade F

Orchestra-Research/AI-Research-SKILLs/06-post-training/grpo-rl-training at 773a529

Spec 21 · Efficiency 11 · Clarity 25 · Security 0 (each out of 25)

Always loaded 28 tokens · on trigger 4,196 · on demand 5,285

  • sec/hidden-unicode critical · README.md:89Invisible or bidirectional Unicode characters can hide instructions from reviewers.
  • eff/body-lines warn · SKILL.mdSKILL.md body is 564 lines; keep it under 500 and move detail into reference files.
  • eff/description-trigger warn · SKILL.mddescription doesn't say *when* to use the skill ("Use when …"). Agents decide from this line alone.
  • sec/undocumented-script warn · SKILL.mdBundles scripts that SKILL.md never explains. Say what each script does and when it runs.
  • spec/non-portable-keys warn · SKILL.mdNon-spec frontmatter (version, author, tags, dependencies). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.

Where it comes from

Source

FactValue
RepositoryOrchestra-Research/AI-Research-SKILLs
Skill folder06-post-training/grpo-rl-training
Stars13,703
LicenseMIT
Commit scanned773a529
Scanned2026-10-19
Files4

ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.

For maintainers

Badge for the README

If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.

[![ProSkills scan 57/100](https://proskills.dev/badge?score=57)](https://proskills.dev/reports/orchestra-research-grpo-rl-training)

Same repository

More from Orchestra-Research/AI-Research-SKILLs

FAQ

Questions

Is grpo-rl-training safe to install?
1 critical finding: read before installing. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
How was this score calculated?
Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
Is this report current?
It was made from commit 773a529 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
I wrote this skill. Can I fix the score or have the page removed?
Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.

Related

Keep reading

Free tool

Scan your own skill

Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.

Want a skill that already passes? Start with a free one.