Individual skill
humanizer
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
SKILL.md
Source commit 4b9b9bee384aea139f599133d2de1e1ceaee71a3
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 131
- Repository last updated
- Aug 9, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.editorconfigasset · 219 bytes.gitignoreasset · 267 bytes.prettierrcasset · 154 bytesLICENSEasset · 1,069 bytesREADME.mddoc · 20,020 bytesSKILL.mdcore · 8,639 bytesSKILL.mdcore · 8,639 bytesapi-server/openapi.yamlasset · 5,087 bytesapi-server/server.jsruns · 4,619 bytesassets/banner.mddoc · 331 bytesdocs/CONTRIBUTING.mddoc · 2,072 bytesdocs/EXAMPLES.mddoc · 2,243 bytesdocs/IMPROVEMENTS.mddoc · 3,913 bytesdocs/INTEGRATIONS.mddoc · 3,690 bytesdocs/PATTERNS.mddoc · 2,625 byteseslint.config.jsruns · 2,642 bytesmcp-server/format.jsruns · 1,425 bytesmcp-server/index.jsruns · 7,060 bytesmcp-server/package.jsonruns · 442 bytesopenai-gpt/instructions.mddoc · 5,080 bytespackage.jsonruns · 1,439 bytesreferences/ai-vocabulary.mddoc · 5,593 bytesreferences/patterns.mddoc · 10,268 bytesreferences/style-guide.mddoc · 4,013 bytesscripts/analyze.shruns · 301 bytesscripts/humanize.shruns · 315 bytessrc/analyzer.jsruns · 18,560 bytessrc/cli.jsruns · 39,679 bytessrc/humanizer.jsruns · 16,287 bytessrc/patterns.jsruns · 37,771 bytessrc/preprocess.jsruns · 2,703 bytessrc/stats.jsruns · 9,699 bytessrc/vocabulary.jsruns · 18,181 bytessrc/workflows.jsruns · 12,318 bytestests/analyzer.test.jsruns · 16,727 bytestests/calibration.test.jsruns · 7,414 bytestests/cli-scan-config.test.jsruns · 5,493 bytestests/edge-cases.test.jsruns · 7,311 bytestests/fixtures/ai-sample-1.txtdoc · 2,223 bytestests/fixtures/ai-sample-2.txtdoc · 1,161 bytestests/fixtures/human-sample-1.txtdoc · 1,092 bytestests/humanizer.test.jsruns · 7,454 bytestests/mcp-format.test.jsruns · 1,644 bytestests/performance.test.jsruns · 3,249 bytestests/preprocess.test.jsruns · 2,504 bytestests/statistics.test.jsruns · 8,093 bytestests/workflows.test.jsruns · 12,595 bytesvitest.config.jsruns · 152 bytes
Read excerpt
# Humanizer: remove AI writing patterns (v2.2)
You are a writing editor that identifies and removes signs of AI-generated text. Your goal: make writing sound like a specific human wrote it, not like it was extruded from a language model.
Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), Copyleaks stylometric research, and real-world pattern analysis.
## Your task
When given text to humanize:
1. Scan for the 28 patterns below
2. Check statistical indicators (burstiness, vocabulary diversity, sentence uniformity)
3. Rewrite problematic sections with natural alternatives
4. Preserve the core meaning