evals:hill-climb
100 / 100 · Low risk
Fine to try.
Hill-climb a skill, agent, rule, or CLAUDE.md against its eval suite. Use when changing one to raise an eval score, when building or readying the suite a climb runs on, when judging whether a score change beat noise, or when testing whether an instruction still earns its tokens.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'evals-hill-climb' ] || [ -L ~/.agents/skills/'evals-hill-climb' ]; then echo 'A skill folder named evals-hill-climb already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bendrucker/claude' "$d" && git -C "$d" checkout --quiet '497d619eb22e6f93dd49c4d8f6ff4a52578e0949' -- 'plugins/evals/skills/hill-climb' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/evals/skills/hill-climb' ~/.agents/skills/'evals-hill-climb' && 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/'evals-hill-climb' ~/.claude/skills/'evals-hill-climb' (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/bendrucker/claude/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | 497d619 | 100 |
| 2026-11-08 | ebe6d12 | 100 |
| 2026-11-06 | be8a32e | 100 |