AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Prompt Engineering/
humanizer
humanizer logo

humanizer

Active·★ 70.4k·MIT·Updated 2026-11-10
★ Most Popular

Humanizer is a focused agent skill created by Blader that systematically rewrites AI-generated text to sound genuinely human without altering underlying facts, code snippets, or core meaning. Drawing directly from Wikipedia's authoritative 'Signs of AI writing' editorial guidelines, the skill targets the statistical artifacts typical of large language models, such as formulaic parallelism, dramatic one-line conclusions, and superficial rhetorical framing.

Rather than applying simple synonym swaps, Humanizer operates on 26 distinct linguistic patterns categorized into groups like 'Staging instead of stating' and 'Rhythm by rule'. It ruthlessly prunes overused tropes like 'Not X but Y' ('It's not just a tool, it's a paradigm'), hollow wisdom statements, and artificial triad rhythms. Crucially, the skill supports personalized voice matching: providing 2-3 sample paragraphs of human writing allows the agent to calibrate its cadence, punctuation habits, and colloquial nuances accordingly.

As an open Agent Skill, Humanizer integrates seamlessly across Claude Code (/plugin install humanizer@humanizer), Codex, Cursor, and any host compatible with the skills CLI (npx skills add blader/humanizer). Users should recognize that Humanizer edits for human readability and authentic communication; it explicitly does not attempt algorithmic evasion of AI detectors, and detector tools will still frequently flag its outputs.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
MIT
Latest release
v4.0.0 · 2026-11-10
Last commit
2026-11-10
Contributors
28
Forks
5,340
Open issues and PRs
2
First published
2026-01-18

Source: GitHub, npm and PyPI public APIs.

#agent-skills#ai-humanizer#ai-writing#chatgpt#claude#claude-code#codex#cursor
$ Install
$ npx skills add blader/humanizer
↗ Visit site★ GitHub
01

Features

01Checks recurring rhetorical and formatting patterns.
02Can match a supplied writing sample.
03Edits prose files while preserving code and link targets.
02

Why choose it

+Grounded in Wikipedia's editorial 'Signs of AI writing' guide, targeting 26 proven robotic patterns.
+Preserves all factual claims, quotes, technical code blocks, and markdown structures without hallucinations.
+Custom voice matching enables the model to adopt the author's personal rhythm, tone, and formatting quirks.
+Broad runtime compatibility via Agent Skills standard across Claude Code, Codex, Cursor, and pi.
03

Trade-offs

!Does not guarantee bypassing automated AI detectors (AI detection classifiers still flag most outputs).
!Pure prompt and rule-based behavior; output fidelity is directly constrained by the host model's reasoning capabilities.
!Can occasionally over-correct expressive marketing copy or brand-specific slogans into overly plain prose.
!Large markdown documents with dozens of chapters require manual chunking to avoid token budget exhaustion.
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-10
Commits, last 90 days
79
Releases, last 90 days
5
Latest release
v4.0.0 (2026-11-10)
Open issues
2
Recent issues with at least one comment
8/13
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 2, 7, 1, 1, 8, 0, 4, 2, 1, 1, 6

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Compatibility

agent-skills
Requires an Agent Skills-compatible host
Verified via docs
06

Quick start

1
$ npx skills add blader/humanizer
07

Use cases

↳Revise a product announcement into plain prose.
↳Review technical documentation for formulaic language.
↳Apply a supplied voice sample to a draft.
08

Alternatives

⚡Top VS:
VSshuorenhua★2.7k→VSnuwa-skill★38.5k→VStaste-skill★117.7k→VSoh-my-openagent★71.0k→
shuorenhua logo
shuorenhua★ 2.7k
说人话|中文优先的去 AI 味改写 skill:保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts.
VSCompare→
nuwa-skill logo
nuwa-skill★ 38.5k
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
VSCompare→
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
oh-my-openagent logo
oh-my-openagent★ 71.0k
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
VSCompare→
skills logo
skills★ 57.8k
Skills for Designers and Engineers.
VSCompare→
huashu-design logo
huashu-design★ 29.7k
Huashu Design 3.0 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent
VSCompare→
planning-with-files logo
planning-with-files★ 28.1k
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
VSCompare→
agency-agents-zh logo
agency-agents-zh★ 22.1k
🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
blader /
humanizer
↗

AI text humanizer skill based on Wikipedia's 26 artificial writing patterns

70.4k5.3kMIT
Last commit1w ago
StatusActive
CategoryPrompt Engineering
Contributors28
Latest releasev4.0.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.