Summary
Catches and removes the telltale signs that text came from an LLM: "delve into," "tapestry," "serves as," those three-item lists, the hedging that stacks qualifiers, the generic "exciting times ahead" conclusions. Built on 28 pattern detectors plus statistical analysis of burstiness and vocabulary diversity. Run it on drafts to get a score and specific suggestions, or use the always-on mode to bake the rules into your agent's system prompt so it never writes like a press release in the first place. The before/after examples are instructive: it's not about dumbing down, it's about writing with actual opinions and letting some natural mess back in.
Install to Claude Code
npx -y skills add brandonwise/humanizer --skill humanizer --agent claude-codeInstalls into .claude/skills of the current project.
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Files
SKILL.md
Select a file.
Featured
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
