← ClaudeAtlas

wise-code-commentslisted

Code-comment rules for EVERY comment and docstring written on the user's behalf in ANY programming language. ALWAYS consult this skill before writing, rewriting, or reviewing a code comment, docstring, or inline annotation - whether adding comments to new code, editing code that carries comments, or when the user says "add comments", "document this function", "comment this code", "explain this in the code", or "clean up the comments". A comment MUST read like a plain-language (ELI5) statement of what the code does or what constraint it obeys RIGHT NOW - concise, present tense, no history, no ticket archaeology.
e1024kb/wise-claude · ★ 4 · AI & Automation · score 77
Install: claude install-skill e1024kb/wise-claude
# Code-comment standards Before asking any user question, read and follow the [question lifecycle](../../references/workflow-host-control.md#keep-asynchronous-questions-open). Keep asynchronous prompts open until answered; this rule does not authorize questions in autonomous or otherwise prompt-free procedures. Standing contract for every code comment and docstring wise writes, in any language. No slash command - it is auto-consulted whenever comments are written or edited. ## The rules (MUST) 1. **ELI5 wording.** Write so a developer new to the codebase understands the comment on first read. Plain words, short sentences, the simplest domain term that carries the fact. No jargon a newcomer would have to look up when a common word works. 2. **Concise.** One comment states one fact, once. If the comment can lose a word without losing the fact, lose the word. A comment that restates what the line below obviously does is deleted, not shortened. 3. **Present-tense facts only.** Describe what the code does or what constraint it obeys *now*. The comment must stay true when read in isolation years later by someone with no access to the project's history. 4. **No history.** Never explain how the code came to be: no ticket numbers as narrative ("in PROJ-12345 we refactored this to ..."), no "previously this used X", no "changed to fix the bug where ...", no "now correctly handles ...". History lives in commit messages, PR descriptions, and