Evol-ai

Eval Improve — Development skill for Claude Code

Development community

/eval-improve — Evaluate + Directed Improvement.

How to install Eval Improve

Installs to ~/.claude/skills/evol-ai-skillcompass-eval-improve/SKILL.md

Terminal

mkdir -p ~/.claude/skills/evol-ai-skillcompass-eval-improve && curl -fsSL https://raw.githubusercontent.com/Evol-ai/SkillCompass/HEAD/commands/eval-improve.md -o ~/.claude/skills/evol-ai-skillcompass-eval-improve/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Eval Improve does

/eval-improve — Evaluate + Directed Improvement

Prerequisites

Recommended model: Claude Opus 4.6 (claude-opus-4-6). Directed improvement requires understanding complex rubric feedback and generating precise, targeted edits. Weaker models may produce unfocused rewrites that fail to address the weakest dimension or introduce regressions in other dimensions.

Interaction Mode

If `--internal` is passed, skip all interactive prompts — return results silently. This flag is set when

Alternatives in Development

Hermes Agent Self Evolution — ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA 5.2k ★
Autoresearch — Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code 2.5k ★
Route Eval — /route-eval — Evaluate a project and set its routing profile 705 ★