About humanizer
humanizer is a skill for revising text to remove AI-writing artifacts while retaining its meaning, factual claims, and intended voice. It guides a bounded, reversible editing process with checks for unsupported changes.
Key features
- 01AI-writing pattern removal
- 02Preserve meaning and factual claims
- 03Scope-limited editing workflow
- 04Review changes and remaining risks
Use cases
- 01Revise text with AI-writing artifacts
- 02Edit within a clearly defined request
- 03Verify that revisions add no claims
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/humanizerin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
README.mdWARP.mdreferences/full-guide.mdDetails
From the project READMEHumanizer
Use this skill to remove AI-writing artifacts while preserving the author's meaning, factual claims, and intended voice.
Routing
- Start here to confirm scope, safety boundaries, and the minimum workflow.
- Load
references/full-guide.mdbefore executing detailed commands, applying templates, or relying on examples from this skill. - Keep the work limited to the user-requested target; do not add adjacent improvements unless the user asks.
Quick Workflow
- Confirm the target, available context, constraints, and done-when signal.
- Read the relevant section of
references/full-guide.mdfor task-specific details. - Execute the smallest reversible action that satisfies the request.
- Verify that meaning is preserved, claims are not added, and the revised text no longer uses the targeted AI-writing patterns.
- Report changed files, commands run, evidence collected, and any remaining risk.
References
references/full-guide.md- complete command patterns, examples, checklists, and edge cases.
Comments
Markdown supported