humanizer
skillReview prose against 35 documented AI-writing patterns and revise it for naturalness, specificity, rhythm, and voice while protecting meaning and quotations.
skills/humanizer/SKILL.md
Open component record →What blader/humanizer is—in plain language
Portable writing skill that identifies and removes common signs of formulaic AI-generated prose while preserving meaning, facts, and quoted material.
Mental model: This repository extends a host application. The host loads its commands, skills, hooks, or agents; most day-to-day use happens inside that host rather than by launching a separate app.
InterfacesAgent Skill and Claude slash command
Primary languageMarkdown; Python only for package-validation scripts
Typical useProvide the draft and, when possible, a sample of the intended voice; then review every change
Your first 15 minutes
- Complete the linked Installation Guide and its verification step.
- Create a disposable test folder or use non-sensitive sample data.
- Run the small example below and observe what files, ports, or prompts appear.
- Read the result before approving writes, network calls, account access, or costs.
- Only then repeat the workflow with a real project.
Starter workflow
# In your agent, ask:
Use Humanizer to revise this paragraph. Preserve facts and quoted text, and show me the diff.Complete indexed functionality map
Each card below corresponds to a component identified in the repository research. Open a component record for its path, purpose, capabilities, dependencies, risks, and relationships.
Upstream feature-by-feature guide
These capabilities are derived from the current first-party README and supporting documentation. Names follow upstream terminology so you can search the source documentation precisely.
Upstream capability
Skills CLI
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns skills cli. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Claude Code plugin
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns claude code plugin. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Claude Desktop upload
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns claude desktop upload. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Manual
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns manual. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Usage
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns usage. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Match your voice
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns match your voice. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
How it works
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns how it works. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Wikipedia's main point
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns wikipedia's main point. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Content patterns
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns content patterns. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Language and grammar patterns
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns language and grammar patterns. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Style patterns
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns style patterns. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Chatbot patterns
Upstream treats this as a distinct part of blader/humanizer. In plain language, use this area when your task concerns chatbot patterns. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
How to use the main workflows
Choose the smallest relevant function
Start with one capability card instead of asking the repository to do everything at once. This makes permissions, inputs, and output easier to understand.
Prepare a disposable input
Use a sample URL, copied repository, test document, or sandbox account. Keep production credentials and irreplaceable files out of the first run.
Run, observe, and stop
Watch Terminal output or the host application's activity view. If the behavior differs from the README, stop with Control + C or cancel inside the host before retrying.
Inspect the result
Check generated files, diffs, API responses, logs, or previews. Never assume “command finished” means the result is correct.
Save a repeatable recipe
Record the working command and non-secret configuration in your project's README. Store secrets in the documented environment file or password manager.
Copy-paste recipes from upstream documentation
These examples are selected from the repository's first-party documentation. Replace obvious placeholders, keep quotation marks intact, and run them only in the context indicated by the surrounding explanation.
Open the live upstream manual
open "https://github.com/blader/humanizer#readme"Configuration, accounts, and files
Configuration files
Agent skill registration
A configuration file changes behavior without changing source code. Make one change at a time and keep a backup before editing JSON, TOML, YAML, or environment files.
Important directories
skills/humanizer/
Paths identify where the relevant implementation or generated files live. Paths beginning with ~ are inside your home folder.
Credentials
None
Prefer temporary, least-privileged credentials. Never commit .env, tokens, cookies, private keys, or session exports.
External services
Only the chosen model/agent provider
Check pricing, data retention, rate limits, and account permissions before enabling optional integrations.
Safe operating habits
- Use test data first and keep a current backup or Git commit.
- Read commands before pasting. A README is useful evidence, not a substitute for judgment.
- Review agent-generated file changes with
git diffbefore committing. - Keep local services bound to
127.0.0.1unless you intentionally secure and expose them. - Do not give plugins or MCP servers broader filesystem, browser, GitHub, or cloud access than their current task requires.
- Confirm API costs and model names before running large batches.
- Stop and investigate repeated authentication failures instead of pasting a token into multiple places.
Reference and source trail
The manual reflects first-party files checked on August 18, 2026. It explains the indexed repository rather than promising that every optional third-party integration is available or safe.