# Humanizer

> Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative…

- **Type:** Skill
- **Install:** `agentstack add skill-skyfox675-agents-skills-humanizer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skyfox675](https://agentstack.voostack.com/s/skyfox675)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skyfox675](https://github.com/skyfox675)
- **Source:** https://github.com/skyfox675/agents-skills/tree/main/.claude/skills/humanizer

## Install

```sh
agentstack add skill-skyfox675-agents-skills-humanizer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# humanizer (pointer skill)

Pointer skill — the implementation is **not** stored here. The `name` above is the stable local contract; the body lives upstream and is fetched/installed from source so consumers always get the latest version.

- **Canonical source:** https://github.com/blader/humanizer/blob/main/SKILL.md
- **Raw SKILL.md:** https://raw.githubusercontent.com/blader/humanizer/main/SKILL.md
- **What it does:** Identifies and rewrites statistical patterns common to LLM output, replacing them with natural alternatives while preserving meaning and the writer's voice.
- **License:** MIT (upstream). Upstream declares `allowed-tools` (Read, Write, Edit, Grep, Glob, AskUserQuestion) and compatibility with claude-code / opencode.

## Installing this skill

Recommended: git clone into your skills directory (gets `SKILL.md` plus bundled assets and stays updatable via `git pull`).

- **Claude Code:** `git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer` (Cursor & Copilot also read `~/.claude/skills/`).
- **Project scope / other tools:** clone into `.cursor/skills/humanizer`, `.github/skills/humanizer`, or `.claude/skills/humanizer`. OpenCode: `~/.config/opencode/skills/humanizer`.

Do not copy the upstream body into this file; that would freeze the version and defeat the pointer.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skyfox675](https://github.com/skyfox675)
- **Source:** [skyfox675/agents-skills](https://github.com/skyfox675/agents-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skyfox675-agents-skills-humanizer
- Seller: https://agentstack.voostack.com/s/skyfox675
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.