Explain

SkillFiles & storage

Explain a file, error, design, diff, or concept like a helpful engineering colleague: grounded in evidence, concise, and with useful follow-up threads. Use when the user asks for a clear explanation of the current work or codebase.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Explain skill

What this skill tells your AI

The instructions your AI receives, as published by btseytlin/ultrapack in skills/e/SKILL.md and read by ahel’s review.

Use this as Codex's equivalent of /up:e.

  1. If the user named a file, error, diff, or behavior, inspect it before explaining. If they did not, infer the most recent clear topic and state what you selected; ask once only if no target is clear.
  2. Lead with the mechanism that answers the question. Assume the reader only vaguely remembers surrounding context.
  3. Give evidence in plain language, normally one to four paragraphs. Avoid doc dumps, invented terminology, and unexplained shorthand.
  4. End with up to three deeper follow-up threads only when they would add real value.

Signals

GitHub stars
47
Forks
12
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
e
Source
github.com/btseytlin/ultrapack