task-review
79 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a research skill usually looks things up on the internet.
SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for cheating and skill invocation, and produces a `pr-N-task-timestamp-run.txt` review report alongside a `prN.zip` bundle of trajectories. Use when reviewing a SkillsBench task PR (by number, branch, or local task path), when the user asks to …
What this skill can do
Runs commands on your computer
Downloads and installs other software
Connects to the internet
Safer alternatives
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'task-review' ] || [ -L ~/.agents/skills/'task-review' ]; then echo 'A skill folder named task-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 "$d" checkout --quiet '21a79b5168bdf125c45b3119252ae89149164844' -- '.agents/skills/task-review' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/task-review' ~/.agents/skills/'task-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/'task-review' ~/.claude/skills/'task-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 | 79 |