Keep code comments and docstrings concise, neutral, and human-authored in tone. Use when writing, refactoring, or reviewing code where comments may be added or changed; do not use to shorten required public API documentation, safety notes, or legal notices.
How this skill is triggered — by the user, by Claude, or both
Slash command
/universal-agent-skills:coding-styleThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Write code that explains itself through names, structure, and small functions. Treat comments as a last-mile explanation for information the code cannot express clearly.
Write code that explains itself through names, structure, and small functions. Treat comments as a last-mile explanation for information the code cannot express clearly.
Prefer:
// Keep the old key for clients that cache signed URLs.
const cacheKey = previousKey ?? currentKey;
Avoid:
// Here we use the previous key because I want to make sure that clients that
// may have cached a signed URL do not suddenly stop working after this change.
const cacheKey = previousKey ?? currentKey;
Omit comments that only restate the code:
retryCount += 1;
Before finishing, inspect new and edited comments. Shorten or remove any comment that sounds conversational, narrates the implementation, repeats the code, or reveals use of an AI assistant.
npx claudepluginhub 26zl/universal-agent-skills --plugin universal-agent-skillsCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.