← All skills

optimize-skill-loop

85 / 100 · Low risk

Fine to try.

By try-agora/qvr (GitHub) · coding · 26 stars · scanned at commit 7178391

Deterministic outer-loop optimizer for a skill that already carries a frozen eval (produced upstream by an eval source such as create-skill-eval). Runs the frozen eval across user-chosen agents on fresh headless sessions via a pluggable adapter, grades quality/cost/perf, keeps the pareto-best variant, and versions every iteration with qvr. Use when a skill is already instrumented and you want a reproducible, article-grade before/after. (To BUILD the eval first, use create-skill-eval.) Trigger p…

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'optimize-skill-loop' ] || [ -L ~/.agents/skills/'optimize-skill-loop' ]; then echo 'A skill folder named optimize-skill-loop already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/try-agora/qvr' "$d" && git -C "$d" checkout --quiet '71783910729031afe6ad1d640728b1534ee4c198' -- 'skills/optimize-skill-loop' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/optimize-skill-loop' ~/.agents/skills/'optimize-skill-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/'optimize-skill-loop' ~/.claude/skills/'optimize-skill-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 try-agora/qvr shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/try-agora/qvr.svg)](https://zalavijaysinh.github.io/skilltrust/repos/try-agora/qvr/)

Score history