ai-writing-detector
Skill4 starsChanged 54 days agoMITView on GitHub
Detect AI-generated text and check plagiarism using the Pangram API. Use when asked to check if text is AI-written, verify human authorship, or run a plagiarism check on a file.
- Reads credentials
5 other projects use a version of this.
Adopted by
Most recently taken up by
- AthenDrakomin-hub/agent-skillstheir own version, first seen Nov 1, 2026
- PracticalSwan/agent-skillstheir own version, first seen Oct 19, 2026
- apoapostolov/humanizertheir own version, first seen Oct 9, 2026
- ai-ecoverse/skillstheir own version, first seen Oct 2, 2026
- conorbronsdon/avoid-ai-writingtheir own version, first seen Sep 3, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- conorbronsdon/avoid-ai-writing★ 5.5ksame name
- PracticalSwan/agent-skills★ 22same name
- apoapostolov/humanizer★ 9same name
- ai-ecoverse/skills★ 1same name
- AthenDrakomin-hub/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- animate-svgSkill
- browserbaseSkill
- clickhouseSkill
- commitSkill
- geist-designSkill
- generate-faviconSkill
- generate-imageSkill
- google-indexingSkill
- google-search-consoleSkill
- google-searchSkill
- humanizerSkill
- keyword-researchSkill
- parallelSkill
- remove-backgroundSkill
- reviewSkill
- web-uiSkill
The file
Files
AI Writing Detector
Pangram API wrapper for AI-text detection and plagiarism checking.
Requirements
PANGRAM_API_KEY— Pangram
Commands
./scripts/detect detect <file> [options]
./scripts/detect plagiarism <file> [options]Options
| Option | Description |
-k, --api-key | Overrides env |
-s, --short | Short prediction, 512-token limit (detect only) |
-o, --output | json (default) or table |
-i, --input-format | text, markdown, html — auto-detected from extension |
Output
JSON. detect: fraction_ai, fraction_ai_assisted, fraction_human, num_ai_segments, windows[]. With -s: just ai_likelihood. plagiarism: plagiarism_detected, percent_plagiarized, plagiarized_sentences, plagiarized_content[].
Gotchas
-o/--outputselects the output format (json|table), not a file path —-o report.jsonis rejected as an invalid value. Redirect stdout to write a file.- Input is a file path only; there is no stdin or inline-text mode.
- Markdown input is stripped to prose before sending: frontmatter
title/excerpt/description/summaryare prepended, code blocks, images, links and formatting are removed. HTML input is reduced to visible text. So scores describe the prose, not the raw file.
Examples
./scripts/detect detect post.md
./scripts/detect detect article.txt -i markdown # force md parsing on .txt
./scripts/detect detect essay.txt -o table > report.txtDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.