← All skills

evaluate-implementation

95 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By bparlan/omp-agent (GitHub) · coding · 44 stars · scanned at commit 3eb5d8d

Post-Implementation Evaluator-Optimizer Agent (Phase 2). Executes tests against the implemented codebase, validates test-failure attribution (VALID_TEST vs INVALID_TEST), and triggers the autonomous Optimizer Loop to surgically repair minor logical bugs and typos in the production code.

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/'evaluate-implementation' ] || [ -L ~/.agents/skills/'evaluate-implementation' ]; then echo 'A skill folder named evaluate-implementation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bparlan/omp-agent' "$d" && git -C "$d" checkout --quiet '3eb5d8dd5b4731d24d0a1d8c8a1e0c8e949515cf' -- 'skills/evaluate-implementation' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/evaluate-implementation' ~/.agents/skills/'evaluate-implementation' && 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/'evaluate-implementation' ~/.claude/skills/'evaluate-implementation' (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 bparlan/omp-agent shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/bparlan/omp-agent.svg)](https://zalavijaysinh.github.io/skilltrust/repos/bparlan/omp-agent/)

Score history