skill-autobench
95 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard compan…
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/'skill-autobench' ] || [ -L ~/.agents/skills/'skill-autobench' ]; then echo 'A skill folder named skill-autobench already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/garrytan/gbrain' "$d" && git -C "$d" checkout --quiet '001c8c39e84d726e9bb6ecbae053458c970d5af3' -- 'skills/skill-autobench' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/skill-autobench' ~/.agents/skills/'skill-autobench' && 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/'skill-autobench' ~/.claude/skills/'skill-autobench' (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/garrytan/gbrain/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-10 | 001c8c3 | 95 |
| 2026-11-08 | 98dda48 | 95 |
| 2026-11-07 | a03306c | 95 |