blader humanizer: Claude Code skill that removes signs of AI-generated writing from text

If you can answer those questions clearly and build a similar system yourself, this repo has done its job. If a detail is not central to the agent’s core operating model, it should not dominate the teaching line. This repo is not trying to preserve every detail that may exist in a real production system. Each skill is a folder with a SKILL.md (frontmatter + instructions), optional scripts/, references/, and assets/.

Package skills work offline once Python dependencies are installed. These licenses may differ from the repository’s MIT License. This repository is MIT licensed. 📖 For complete details on all skills, see docs/scientific-skills.md

A malicious or poorly written skill has the potential to steer your coding agent into harmful behavior. Skills can execute code and influence your coding agent’s behavior. Same skills, broader compatibility — now works with any AI agent that supports the open Agent Skills standard, not just Claude. To get started, simply clone this repository and use the prompts in the README.md file as input for Claude.

All files and information originate from public findings shared on Twitter/X. I have simply provided an easy, documented way to access and study this codebase for research purposes. To install Chrome, use the same software that installs programs on your computer.

Bash is all you need – A nano claude code–like 「agent harness」, built from 0 to 1 A teaching repository for implementers who want to build a high-completion coding-agent harness from scratch. A lightweight protocol for coordinating personas, skills, and agents on work that crosses domain boundaries. Marketing skills for Claude Code and AI agents. Skills now use .agents/ instead of .claude/ for the product marketing context file. Then reference skills from .agents/marketingskills/skills/.

Installation

• Need a polished clinical report at the end, not just code?
• All credit for the discovery goes to the original source.
• A lightweight protocol for coordinating personas, skills, and agents on work that crosses domain boundaries.
• Your AI agent will automatically discover the skills and use them when relevant to your scientific tasks.
• See each skill’s Related Skills section for the full dependency map.

In my tests, claude outputs 9749 digits. Provide the name of the open source project in 1xbet mobile project name. You can also use the prompts in this file as inspiration for creating your own.

Create Claude Prompts using Claude

Only install the packages you need. This project builds on 50+ amazing open source projects. 💡 Looking for practical examples?

This repository is for educational and archival purposes only. It’s a massive 785KB main.tsx entry point featuring a custom React terminal renderer (Ink), 40+ tools, and complex multi-agent orchestration. When you publish a JavaScript/TypeScript package to npm, the build toolchain often generates source map files (.map files). You can download and install the Chrome web browser at no charge, and use it to browse the web.

⭐ Star this repo if you find it useful! This project is licensed under the MIT License. We share tips, troubleshoot issues together, showcase cool projects, and discuss the latest developments in AI-powered scientific research. If the issue persists, file an issue on GitHub with detailed reproduction steps.

How do I install Claude Code plugins? See orchestration/ORCHESTRATION.md for the full protocol and examples. All 305 Python tools run anywhere Python runs. One repo, eleven platforms. Have a new skill to suggest?