DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to score a prose draft for AI-writing tells with Sloptrim

Run a local 0-100 score on a .docx, .md or other prose file before you publish it.

Authorization notice. Sloptrim is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn editor or content writer who has a finished draft and wants a local check for AI-writing patterns before sending it out.

The problemReading a draft line by line to find machine-like phrasing is slow, and uploading the draft to a web service is not acceptable for unpublished work.

The outcomeA JSON report with a 0-100 score, one of five bands (clean, light tells, mixed, heavy tells, pervasive tells), the named patterns and the metrics, all produced on your machine.

What you need first

  • Python 3.9 or newer for the detector
  • Node for the Claude Code hooks
  • Git, to clone the repository
  • A coding agent such as Claude Code, Codex or Cursor, if you want the on-save guard or the contract

Steps

  1. Clone the repository with git clone https://github.com/seyedehsanhadi/sloptrim.git ~/.claude/skills/sloptrim
  2. Change into the cloned folder, for example cd ~/.claude/skills/sloptrim (inferred, check the README)
  3. Run python scripts/detect.py draft.docx on your file, replacing draft.docx with its path
  4. Read the score and band in the JSON, then check the listed patterns and metrics
  5. In Claude Code, run /sloptrim check <file> to get a score and the named tells without a rewrite (inferred, check the README)

Prompt for your agent

Using the sloptrim repo at <repo path>, run `python scripts/detect.py <draft file>` on <draft file> and report the 0-100 score, the band and the named patterns. Verify that the output is valid JSON and includes a score between 0 and 100.

Caveat. The score describes the writing only and must not be used to judge whether a person or a model wrote the text, as the README warns.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page