Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
Humanizer solves the problem of AI-generated text being easily detectable by readers due to formulaic patterns, inflated language, and unnatural phrasing. Unlike generic paraphrasing tools, it targets specific AI-isms and allows voice calibration to match a user's personal writing style.
Deployment reality
The available setup signal starts with: npx skills add blader/humanizer --global. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build applications that automatically humanize AI-generated content for blogs, emails, reports, or social media posts. The skill can rewrite entire files in place, accept voice samples for personalized output, and performs a final audit pass to catch lingering AI patterns. Real-world use cases include cleaning up ChatGPT drafts, making LLM outputs suitable for publication, and ensuring consistent human tone across team-generated content.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
blader/humanizer is tracked as a Python project in the AI Agent, LLM Tool area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 32k total stars, with +0 today, +1.6k this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Moderate; the latest push was 32 days ago, and the open issue queue is 12, about 0.04% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 2.9k forks and 32k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need Python teams evaluating ecosystem-native tooling. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 1.6k. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyMIT is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
32k Stars
Reuse
2.9k Forks
Attention
32k Watchers
Maintenance
moderate
License
MIT
Open issues
12
Humanizer is a portable agent skill that removes signs of AI-generated writing from text, making it sound more natural and human. It detects 33 patterns of AI writing and rewrites text to be more human-like, with a no-fabrication rule.
Key Features
- Detects and rewrites 33 patterns of AI writing including significance inflation, AI vocabulary, passive voice, and emojis - Supports voice calibration by analyzing a user's own writing sample to match their personal style - Includes a final audit pass to catch lingering AI-isms and enforces a no-fabrication rule
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
npx skills add blader/humanizer --global70
Health Score
Moderate
Commit Activity
Jan 18, 2026
Created
Jul 22, 2026
Last push
+254
Today's growth
+254
7-day growth
+254
30-day growth
Forks
Open
Watchers
blader
GitHub profileobra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
✓
License
✓
Forked
~ Moderate
Maintained
Problem Solved
Humanizer solves the problem of AI-generated text being easily detectable by readers due to formulaic patterns, inflated language, and unnatural phrasing. Unlike generic paraphrasing tools, it targets specific AI-isms and allows voice calibration to match a user's personal writing style.
Capabilities
Developers can build applications that automatically humanize AI-generated content for blogs, emails, reports, or social media posts. The skill can rewrite entire files in place, accept voice samples for personalized output, and performs a final audit pass to catch lingering AI patterns. Real-world use cases include cleaning up ChatGPT drafts, making LLM outputs suitable for publication, and ensuring consistent human tone across team-generated content.
Bottom Line
Humanizer is ideal for writers, content creators, and developers who need to polish AI-generated text to avoid detection and improve readability. It should be avoided by those who prefer raw AI output or need factual additions, as it strictly avoids fabrication. The key trade-off is naturalness vs. specificity: it removes AI-isms but cannot add new facts or citations.