Antislop Code is the code comment skill of the antislop rulebook. When a task writes or edits comments, it filters out the ones that read as machine-made: banner separators, comments that restate the next line, step-by-step narration, empty labels, vague TODOs, signature echoes, decorative emoji and end markers.
It keeps comments that explain intent, security, performance, workarounds and edge cases, and it limits itself to comments only.
What You Get
- A catalog of useless comment patterns with a fix for each
- A list of comment kinds that must stay, such as business logic, security, concurrency and workarounds
- A length rule: one line, or two only when the second adds a new fact
- A comment checklist to run alongside the core Delivery Gate
- A guarantee that only comments change
Common Use Cases
- Cleaning a file full of AI-written banner and narration comments
- Keeping generated code comments short while it is being written
- Reviewing a pull request for comments that repeat the code
- Replacing vague TODOs with specific tasks or removing them
What Makes It Unique
Many linters flag comment style. This skill judges whether a comment carries a fact the code does not show, and it protects the valuable ones with an explicit keep list. It also targets over-long comments, where the length itself is the tell, and cuts them to the one constraint that matters.
Under The Hood
The skill is a single SKILL.md of instructions with no scripts. The frontmatter allows the agent to read, write and edit files and to search with glob and grep. When you apply it, the agent opens your source files, removes or shortens comments and saves the edits. It does not run commands, fetch web pages or call APIs. It is meant to load together with the core antislop skill, whose rules it cites by number.