harness-eval-loop
95 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Build the current LibrAgent revision, run the Harbor benchmark that matches the recent work, decide whether the experiment is accepted (adopt / revert / iterate / inconclusive) against a comparable baseline, and file newly found harness problems and performance-regression causes as GitHub issues. With an interval and dataset it repeats this on a schedule. Use when the user types "/harness-eval-loop", "/harness-eval-loop 2h layman", "harness_eval_loop", "벤치 돌려서 experiment 판정", "하네스 평가 루프", or as…
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/'harness-eval-loop' ] || [ -L ~/.agents/skills/'harness-eval-loop' ]; then echo 'A skill folder named harness-eval-loop already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/fritzprix/libr-agent' "$d" && git -C "$d" checkout --quiet '0679557c88a47a5b14b020b9785e0de95e0a1f94' -- '.agents/skills/harness-eval-loop' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/harness-eval-loop' ~/.agents/skills/'harness-eval-loop' && 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/'harness-eval-loop' ~/.claude/skills/'harness-eval-loop' (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/fritzprix/libr-agent/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | 0679557 | 95 |