# Aide Evals > Use when building smoke, regression, compatibility, or scorekeeping scaffolds for evaluation and verification work. - Skill: `tomevault-io/aide-evals` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/aide-evals` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/aide-evals/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/aide-evals --- ## Scope - `evals/**` - evaluation scaffolds and verification scorekeeping - matrix-aligned verification posture work ## Trigger - when a prompt defines smoke checks, regression structure, or compatibility evidence records - when evaluation outputs must stay aligned with support and capability reporting ## Do Not Use - Do not use this skill when the task is product implementation instead of verification scaffolding. - Do not use this skill when the task is only environment acquisition with no evaluation structure. --- > Source: [Julesc013/aide](https://github.com/Julesc013/aide) — distributed by [TomeVault](https://tomevault.io).