This does what it says: scans your text for AI tells and rewrites them to sound human. It's based on Wikipedia's "Signs of AI writing" guide and catches the usual suspects like "nestled in," "serves as a testament," and those tacked-on "-ing" phrases that add fake depth. The interesting bit is the voice calibration feature. Give it a sample of your own writing and it'll match your actual patterns instead of just producing generic "natural" text. It's got a whole section on adding personality beyond just removing slop, which honestly feels necessary since sterile corporate voice is just as obvious as ChatGPT's greatest hits. Useful if you're editing AI-assisted drafts or trying to sound less like a press release.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
394
skills.sh installs
12.5K
GitHub stars
67.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add blader/humanizer --skill humanizer --agent claude-code

Installs into .claude/skills of the current project.

Files

Humanizer: remove AI writing patterns

Rewrite AI-sounding text so it reads like the writer, not a chatbot. Keep what it says.

Why AI text sounds the way it does

A language model writes whatever is most likely to come next, so by default it makes the choice that fits the widest range of readers and subjects. A human writer chooses for one reader and one subject, so their choices are uneven and specific. Every pattern below is one form of the default choice:

  • Staging. The sentence signals importance instead of adding a fact, with a contrast that only adds weight or a one-line closer that repeats the point.
  • Rhythm by rule. Triads and dashes applied everywhere, whether or not the meaning asks for them.
  • Inflation. Ordinary facts dressed as pivotal or expert-backed.
  • Formatting by rule. Bold and title case applied to every item.
  • Leftovers. Chat wrappers and drafting moves that were never meant for the reader.
  • Wrong reader. A reply re-explains background the other person already has, so the decision arrives last.

Word habits change with every model release. The structural habits above persist, so they lead the list below.

Sponsors

Details

Repository
github.com/blader/humanizer
Categories
Documentation, AI & Agent Building
First seen
May 16, 2026
1antfu avatarvitepressantfu/skillsVitePress static site generator powered by Vite and Vue. Use when building documentation sites, configuring themes, or writing Markdown with Vue components.12.1Kskills.sh installs
2imbad0202 avataracademic-paperimbad0202/academic-research-skills12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebut11.4Kskills.sh installs
3wshobson avataron-call-handoff-patternswshobson/agentsMaster on-call shift handoffs with context transfer, escalation procedures, and documentation. Use this skill when transitioning on-call responsibilities betwee10.7Kskills.sh installs
4msw-git avatarmsw-searchmsw-git/msw-ai-coding-plugins-officialMSW search integration — (1) vector search for API docs and implementation guides via the msw-mcp MCP server (mlua_api_retriever / mlua_document_retriever), (2)10.7Kskills.sh installs
5msw-git avatarmsw-packagesmsw-git/msw-ai-coding-plugins-officialMSWPackages catalog — official 1st-party prebuilt packages for common MSW features. Use this skill BEFORE writing a feature from scratch when the user asks for 10.5Kskills.sh installs
6hashicorp avatarterraform-testhashicorp/agent-skillsComprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infr9.2Kskills.sh installs