# Eval Skills

> Evaluate Whetstone skills from session evidence when asked to compare procedure-following results or optimization candidates.

- Skill: `iliaal/eval-skills` (Agent Skill)
- Install (CLI): `npx skillmds@latest add iliaal/eval-skills`
- Raw SKILL.md: https://api.skillmd.com/api/skills/iliaal/eval-skills/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: iliaal (https://skillmd.com/u/iliaal)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/iliaal/eval-skills

---


# eval-skills

Read the [Codex adaptation](../claude-command-compatibility.md), then read the complete [maintained workflow](../../../.claude/commands/eval-skills.md) before acting. Apply that workflow to the current request with its scope and approval boundaries intact.

Use the text following `$eval-skills` as the workflow's `$ARGUMENTS`. When selected from a natural-language request, derive arguments only from the user's stated scope; apply the workflow's missing-argument behavior for anything unspecified.