← All skills

eval-fix-loop

100 / 100 · Low risk

Fine to try.

By gke-labs/kube-agents (GitHub) · other · 124 stars · scanned at commit 26dabb5

Take one failing eval case (or one root cause behind several), diagnose it from its recorded runs, classify the miss, record a red, make the smallest allowed fix, prove three greens, and open the pull request. Use when a nightly or local run shows a red that someone must turn green, or when a repair list names a root cause.

Works with any agent that supports SKILL.md skills.

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/'eval-fix-loop' ] || [ -L ~/.agents/skills/'eval-fix-loop' ]; then echo 'A skill folder named eval-fix-loop already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/gke-labs/kube-agents' "$d" && git -C "$d" checkout --quiet '26dabb5f82fb077919624f7051b31c76fa5e6814' -- '.agents/skills/eval-fix-loop' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/eval-fix-loop' ~/.agents/skills/'eval-fix-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/'eval-fix-loop' ~/.claude/skills/'eval-fix-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

The badge for gke-labs/kube-agents shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/gke-labs/kube-agents.svg)](https://zalavijaysinh.github.io/skilltrust/repos/gke-labs/kube-agents/)

Score history