Use output-hygiene

Review agent-written text before it ships and strip the machine artifacts it carries

Review agent-written text before it ships and strip the machine artifacts it carries — invisible Unicode, non-breaking spaces, homoglyphs, harness-added provenance trailers, trailing chat closers — then flag the prose tells a script cannot catch, each quoted with a rewrite.

Reach for it when the user wants to clean up AI-generated output, asks to remove a Claude watermark, attribution footer, or "Generated with" line, wants a draft that does not read as machine-written, or needs a pre-ship hygiene pass on a document, commit message, or pasted chat answer.

Install it

npx skilldrop-cli install output-hygiene                 # Claude Code, your user folder
npx skilldrop-cli install output-hygiene --project       # Claude Code, this repo
npx skilldrop-cli install output-hygiene --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the Core pack: --pack core installs it with its neighbours.

It ships scripts, so it needs Python 3 (standard library only, nothing to install). What they may touch is declared in its manifest.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Remove the Claude watermark from this doc before I send it"
• "Strip the 'Generated with Claude Code' footer and the co-author trailer"
• "This draft sounds like AI — tell me exactly which sentences give it away"
• "There are invisible characters in this file breaking my diff, find them"
• "Clean up this text I pasted out of a chat window before it goes to the board"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Review this design doc and tell me where the argument is weak"
• "Summarize this report for executives"
• "Write our company policy on acceptable AI use"

If another skill answers instead, ask for this one by name: "use output-hygiene".

Check what you get

A good result:

• Every mechanical finding names a codepoint or quotes the matched line. "Contains invisible characters" is unverifiable; 3:18 U+00A0 NO-BREAK SPACE is checkable in one keystroke.
• Every prose finding quotes the span it is judging. The quote is the evidence. A finding that paraphrases is an opinion.
• The auto and review tiers stay separate in the report. Merging them means the user approves a homoglyph guess while approving a zero-width-space deletion.
• The medium is stated before the first finding. Half the classes are medium-dependent; a report that skips it is asserting a default it never disclosed.
• Rewrites are paste-able. "Tighten this" is not a rewrite. The replacement sentence is.
• The report says what it left alone. Including the provenance trailer when disclosure is owed, and why.

Use something else when

• The document's argument, structure, or evidence is the problem — that is doc-critique.
• The goal is to pass work off as unassisted where a policy requires disclosure. The skill stops on the provenance class and names the policy.
• The text is source code. Invisible-character scanning is worth running, but prose tells do not apply and the rewrite advice will be wrong.
• The user wants the text shortened or re-pitched for a different audience. That is a rewrite, not a hygiene pass.

Where a loop runs it

• Stage confirm of the apply loop, where gate G6.1 decides
• Stage polish of the ship-a-draft loop

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: doc-critique, ai-usage-policy

Edit this page on GitHub · View source