benchflow-experiment-review
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Audit completed BenchFlow or SkillsBench trials, benchmark measurements, usage/cost evidence, and training exports against their tested versions and declared contracts. Use for run reliability, reward integrity, timing comparisons (speed or A/B comparisons between builds or frameworks), changes to sandbox setup, hardening, grading or teardown code, or targeted integration validation.
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'benchflow-experiment-review' ] || [ -L ~/.agents/skills/'benchflow-experiment-review' ]; then echo 'A skill folder named benchflow-experiment-review already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/benchflow-ai/benchflow' "$d" && git -C "$d" checkout --quiet '21a79b5168bdf125c45b3119252ae89149164844' -- '.agents/skills/benchflow-experiment-review' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/benchflow-experiment-review' ~/.agents/skills/'benchflow-experiment-review' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'benchflow-experiment-review' ~/.claude/skills/'benchflow-experiment-review' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/benchflow-ai/benchflow/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 21a79b5 | 97 |