run-rf100vl-benchmark

run-rf100vl-benchmark is a Model training & evaluation skill for AI agents, published by LibreYOLO in the libreyolo repository on GitHub. Skillspace rates run-rf100vl-benchmark F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Run the RF100-VL (Roboflow 100-VL) detection benchmark on LibreYOLO models end to end: dataset download with version locking, per-dataset fine-tuning, protocol-conformant pycocotools evaluation at maxDets 500, artifact publishing, and multi-GPU execution on vast.ai (the default compute). Use when someone wants to "run RF100-VL", "benchmark on Roboflow 100", reproduce or extend published RF100-VL numbers, add a model family to the campaign, asks why campaign GPUs look underutilized or the ETA looks wrong, or needs to decide stop-vs-destroy / packing depth. Training and eval run in the vision-analysis-benchmark harness; this skill holds the protocol, locked decisions, compute playbook, and the operational lessons that change money and wall-clock.

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
652

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.

View source on GitHubLibreYOLO/libreyolo

Our review

Architecture
80 / 100
Maturity
Basic: a single SKILL.md
Security scan
High-risk patterns
License
Not declared. Check the repository before reusing it.

What the scanner flagged

  • dynamic code execution (eval/exec)
  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Model training & evaluation

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