← All skills
autoreview
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By amd/gaia (GitHub) · coding · 1,622 stars · scanned at commit 3ec6ceb
Pre-commit/ship code review: Codex default; optional Claude or Pi.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 20 places.
Show 17 more
- tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 115
export AGENTS_HOME="${AGENTS_HOME:-$HOME/.agents}" - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 154
"$AUTOREVIEW" --mode local - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 167
"$AUTOREVIEW" --mode branch --base origin/main - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 173
"$AUTOREVIEW" --mode branch --base origin/main --prompt-file review-notes.md --dataset evidence.json - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 179
base=$(gh pr view --json baseRefName --jq .baseRefName) - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 186
"$AUTOREVIEW" --mode commit --commit HEAD - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 222
"$AUTOREVIEW" --parallel-tests "<focused test command>" - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 226
semantics used by Python `shell=True`. Use `--parallel-tests-shell powershell` - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 237
OPENCLAW_TESTBOX=1 "$AUTOREVIEW" --parallel-tests "pnpm check:changed" - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 259
"$AUTOREVIEW" --reviewers codex,claude,pi - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 265
"$AUTOREVIEW" --panel - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 271
"$AUTOREVIEW" --reviewers codex,claude --model codex=gpt-5.6-sol --thinking codex=high --model claude=claude-fable-5 --thinking claude=max - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 277
"$AUTOREVIEW" --reviewers codex:gpt-5.6-sol:high,claude:claude-fable-5:max - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 283
"$AUTOREVIEW" --engine pi --model anthropic/claude-sonnet-4 --thinking high - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 320
"$AUTOREVIEW" --engine codex --model gpt-5.6-sol --thinking high - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 389
"$AUTOREVIEW" --help - tests/fixtures/openclaw_skills/clawhub-autoreview/SKILL.md, line 395
"$AUTOREVIEW_HARNESS" --fixture benign --engine codex
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'autoreview' ] || [ -L ~/.agents/skills/'autoreview' ]; then echo 'A skill folder named autoreview already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/amd/gaia' "$d" && git -C "$d" checkout --quiet '3ec6ceb6429b99c4af63250689239478a4b06c34' -- 'tests/fixtures/openclaw_skills/clawhub-autoreview' && mkdir -p ~/.agents/skills && cp -R "$d"/'tests/fixtures/openclaw_skills/clawhub-autoreview' ~/.agents/skills/'autoreview' && rm -rf "$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/'autoreview' ~/.claude/skills/'autoreview' (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
The badge for amd/gaia shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/amd/gaia/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | 3ec6ceb | 97 |
| 2026-11-09 | 2abaa51 | 97 |
| 2026-11-07 | c11ea99 | 97 |