Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Plain-speak is a small command-line linter that scores selected signals of plain language and flags text for review. It is not an AI-authorship detector: its score reflects checks such as sentence length, selected buzzwords, readability and hedge density—not proof of who wrote a passage.
What plain-speak checks
In a DEV Community post, builder Hao Li describes four checks that contribute to the tool’s plainness score:
As an Amazon Associate I earn from qualifying purchases.
- Long sentences: sentences longer than 25 words are flagged.
- Selected buzzwords: the post says the tool includes about 45 “AI-tell” terms, with examples such as “delve,” “robust,” “furthermore” and “in today’s fast-paced.”
- Reading ease: a Flesch-style reading-ease score is folded into the total.
- Hedge density: the tool checks how frequently hedging language appears.
These are style signals, not a complete definition of good writing. A long sentence may be clear, a listed word may be exactly right for its context, and a readable score cannot tell whether an explanation is accurate or useful. Treat a flag as a prompt to review a line, not an instruction to change it automatically.
What the sample score means
Li’s post shows example output scoring a draft 45/100 and labeling it “slop.” The sample also reports 3 sentences, 80 words, a reading-ease score of 30.7, 2 long sentences, 24 buzzwords and 2 hedges. Those figures illustrate the interface for that example; the post does not present them as an independent evaluation, controlled test or measure of how readers would judge the draft.
#1 Best Overall
In practical use, the score can help surface patterns that are easy to overlook during drafting. It cannot establish that text was produced by AI, and the example does not show that the score is valid or predictive. Read the flagged passages yourself and keep changes that make the writing clearer.
How the author says to run it
The post describes plain-speak as a one-file Python tool using only the standard library and supporting Python 3.9 or later. Its author gives these commands:
git clone https://github.com/hahahahahahahahah6/plain-speak
cd plain-speak
python3 plain_speak.py check draft.txtThe post also describes two options for automating checks:
Free tools Windows power users keep installed
One-click scans. No signup required.
--jsonrequests machine-readable output.--fail-under 80sets a threshold that can make the check fail when the score falls below 80, for use as a CI gate on generated documentation.
These setup details and options are reported by the author; the repository’s current state and compatibility have not been independently verified here. Confirm the project instructions and behavior before relying on them in a workflow.
Rank #3
Using the linter as part of a revision loop
Li says the repository includes a SKILL.md agent skill with a reading-level ladder described as “ELI5 / engineer / one-liner.” The proposed loop is to run the CLI, use the skill to rewrite lines that need attention, and check the draft again. That is the author’s description of the workflow, not evidence that automated rewrites will preserve meaning.
- Run the check on a draft and note which specific sentences or phrases triggered flags.
- Review each flagged passage in context. Ask whether shortening it or replacing a stock phrase improves clarity without losing precision.
- If using an agent to rewrite, compare the revision with the original for accuracy, tone and missing qualifications.
- Run the check again as a consistency aid, then make the final editorial decision yourself.
A threshold can standardize a team’s review process, but it also makes the tool’s chosen signals consequential. A draft should not be rejected just because it falls below an arbitrary score, or approved solely because it passes one.
Rank #4
What the score can—and cannot—tell you
Plain-speak is best understood as a heuristic for reviewing plainness and readability. Its checks may point to sentences worth splitting, jargon-like word choices worth reconsidering, or hedging worth examining. They do not determine authorship, factual accuracy, originality or whether a particular audience will understand the text.
The distinction matters because writing can sound generic for reasons that a word list cannot diagnose, while a perfectly appropriate technical term may appear on one. Use the score to find places to think, not as a verdict on the writer or the draft.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
