plain-language

Zero attribution: never add or leave co-author, AI, or tool attribution in any output.

Own the free prose an agent sends. Load once at session start and keep it loaded; reload after context loss or a content change.

Scope

In scope, free prose only: chat replies; the prose of commit messages, PR bodies and comments, issue bodies and comments, and release notes; human-facing guide or README text the task asked you to write; and text a user hands you to clean.

Out of scope, never edited by this skill even when asked to "clean the file": source code, tests, configuration, scripts, migrations, generated files, code comments and docstrings; ADRs, specs (PRDs), prompts, and glossary entries, which follow their own skills' templates; quoted output, logs, commands, and paths. When a cleanup request points at one of these, say so and stop. Inside an in-scope text, every code span, identifier, and quoted line is protected text.

When it runs

Session start. After the first reporting-gate update, call the Skill tool with plain-language where the runtime has one; otherwise read the installed SKILL.md, project-local .agents/skills/ or .claude/skills/ first, then the user-level copy. Every later reply applies it from context; no further read is needed while it stays loaded.
Before each substantive reply and before finalizing written content. Apply the rules below to the prose you wrote for the current task. Clean drafts before asking for approval; a change to approved wording needs that approval again.
On request. "Clean this", "remove the AI tells", "make this plain": return the cleaned text, then one line: Prose cleanup: <n> edits; protected spans kept: <m>.
Missing skill → say so once per session and follow the style lines in the workspace AGENTS.md.