Explain diff
SkillDev toolsExplain a code change, its reasons, effects, trade-offs, and verification limits.
Use Explain diff in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Explain diff and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Explain diff skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by hashgraph-online/awesome-codex-plugins in plugins/reidemeister94/development-skills/skills/explain-diff/SKILL.md and read by Ahel’s review.
Explain the change so the user can understand its behavior and maintain it.
Manual mode is repository-read-only; --visual may write only to system temp.
Use the requested worktree, branch, range, pull request, patch, or packet. Default to the current worktree.
Inspect the implementation, request, relevant decisions, verification, review verdict, and evidence limits.
Use runtime data and logs when they settle a material claim. Label absent or stale evidence Unverified change.
For --visual, read visual mode.
Explain the result, prior behavior, reasons, important failure cases, operational effects, and trade-offs. The explanation must stand alone without requiring the user to open the repository. Explain public or operational names before using them. Include implementation detail only when it helps the user's purpose. Use a diagram or concrete example when it makes the behavior clearer.
Optional dialogue
When the user wants an interactive explanation, ask applied questions one at a time. Ask the user to predict behavior, make a decision, or diagnose an observable result. Test useful reasoning, not remembered syntax or file layout. The user can skip questions or request another explanation. Do not delay task completion for a mandatory quiz or record personal comprehension scores.
When an answer exposes conflicting requirements or behavior, inspect the evidence before treating the answer as wrong. Persist only confirmed, useful decisions in the document that owns them. Manual mode proposes edits without writing.
If evidence disproves the implementation, return to the affected workflow step. Changed code repeats verification and review before the final explanation.
Signals
- GitHub stars
- 1k
- Forks
- 316
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
explain-diff-hashgraph-online- Source
- github.com/hashgraph-online/awesome-codex-plugins
github.com/hashgraph-online/awesome-codex-plugins