Skip to content
SkillScript-led981 tokens in use

AI Writing Detector

Runs a detect-only review of text for AI writing patterns, using a local Node detector when the host can run it, and reports findings without rewriting.

5,770 stars on the repository MIT Licenseconorbronsdon/avoid-ai-writing · skills/ai-writing-detector
/plugin install avoid-ai-writing@conorbronsdon-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing AI Writing Detector costs

44tokens idle
981tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/detect.js, scripts/patterns.js.

Touches

shelldetectednetworkdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter15/15
  • Structure17/25
  • Examples12/15
  • Output10/15
  • Size10/15
  • Resources5/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Fair
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 76
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/patterns.js, line 72
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/patterns.js, line 73

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community60
  • Maturity32
  • Momentum40

AI Writing Detector scans text or a file for the patterns catalogued by Avoid AI Writing and reports a score, a label, issue types, severity, matched text and suggestions. It never rewrites unless the user changes the request.

The skill separates deterministic detector hits from judgment about which ones are justified findings, and it treats score and label as signals. When Node cannot run, it falls back to a model-only audit and says the detector did not run.

What You Get

  • A detector result with overall score and label when the script ran
  • Candidate matches grouped by severity with the matched text and suggestions
  • A short assessment that separates justified findings from likely false positives
  • A clear statement of whether the check was executed or model-only
  • No rewritten text unless control passes to a rewrite skill

Common Use Cases

  • Scanning a draft before publishing to see what reads as machine-written
  • Auditing a Markdown file with frontmatter without scoring its metadata
  • Getting a deterministic result for technical prose using the technical context
  • Checking text again after an edit as a read-only residual check
  • Collecting signals before a decision, then escalating questions about authorship to the reviewer skill

What Makes It Unique

It is the read-only member of a routed set of skills and has strict stop conditions: it does not continue into rewriting, file changes or authorship conclusions on its own. It keeps the detector’s output labelled as executed or model-only and never claims a run that did not happen, and it hands consequential questions to the false-positive reviewer.

Under The Hood

The skill loads one instruction file and relies on the rulebook in the sibling avoid-ai-writing skill and on routing files in the router skill. For a deterministic run the agent executes the bundled Node script in the shell, piping text in or pointing it at a file; the script reads the input and prints results and does not change files. If Node or shell access is missing, the agent audits by reading the rulebook only.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers