code-prose

SkillDev tools

Lets your agent rewrite code identifiers and comments for clearer wording without changing behavior.

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 code-prose skill

About this capability

Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior. Use when names, word choice, or comments need an editorial pass.

What this skill tells your AI

The instructions your AI receives, as published by epicenterhq/epicenter in .agents/skills/code-prose/SKILL.md and read by ahel’s review.

Review changes in the current branch, or in the scope the user specifies. Apply these criteria without changing behavior. Only touch code in that scope, and run the relevant existing checks after changes.

Word choice in code and comments

Variable names, function names, and comments are all prose. Apply Orwell's rules ("Politics and the English Language") to each:

Never use a long word where a short one will do.

If it is possible to cut a word out, always cut it out.

Never use the passive where you can use the active.

Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.

Latinate vocabulary (reconcile, coalesce, normalize, reconciliation) sounds technical and abstract; Anglo-Saxon words (prune, run, watch, stop, drop, walk) are short and physical. Prefer the Saxon word.

Names

  1. One word per concept, one concept per word. Keep a vocabulary. If sync names "pulling remote changes," it cannot also name "flushing edits to disk;" rename one of them.
  2. Cut words the context already carries. A module named workspaceWatcher does not need startNativeWorkspaceWatcher; watchWorkspace says the same thing.
  3. A compound name is usually a hedge:
  • lastObservedDiskContent is a specification to defend
  • baseline is a readable description

Comments

State, in plain English, the constraint the code cannot show: why the non-obvious exists.

  • ✅ If code is complex and the implementation is non-obvious, add a comment.
  • ✅ If a function contains complex behaviors or side effects, add a doc comment.
  • 🗑️ If a comment narrates change history from the conversation, delete it.
  • 🗑️ If a comment restates code whose behavior is self-evident, delete it.

Overfitting

Code must stand on its own. If a name or comment only makes sense to someone who watched it happen (this conversation, this PR), it is overfitted. Write for the reader who arrives with no history: rewrite it against the codebase's own vocabulary.

For the structural half of the same discipline — file shape, derivable state, and compatibility with code that never shipped — use refactoring.

Signals

GitHub stars
5k
Forks
378
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
code-prose
Source
github.com/epicenterhq/epicenter