li-human cleans a draft with humanize.py and scores it with detect.py, both Python scripts with no dependencies that run on your machine. The cleaner deletes invisible characters, converts em dashes, curly quotes and ellipses, and swaps stock words and phrases from an editable lexicon.
Structural tells such as the not-only-but-also pattern, rule-of-three lists, hashtag walls and engagement bait are flagged for you to rewrite. The scorer rates burstiness, specificity, slop density, fingerprint and voice and gives a verdict of pass, review or flagged.
What You Get
- A cleaned draft with a report of every invisible character, typographic change and replaced word
- A list of structural tells flagged for you to rewrite by hand
- A human score from 0 to 100 across five checks with a pass, review or flagged verdict
- A before and after comparison that shows the change in score between two drafts
Common Use Cases
- Cleaning a draft before it goes on LinkedIn
- Checking whether text carries zero-width characters from copy and paste
- Removing em dashes and stock phrases from any writing
- Comparing a draft with its cleaned version to see what moved the score
What Makes It Unique
It runs real scripts, so cleaning and scoring are repeatable and measured by code. The word list lives in an editable slop.json file, and the scorer weights the weakest single check at 40 percent because a detector needs only one signal. Its instructions also limit the claim: the checks are local heuristics, they do not call any detector service and the skill never tells you text is undetectable.
Under The Hood
The skill tells the agent to run python3 humanize.py and python3 detect.py from its folder on your draft files, so it runs shell commands and can write a cleaned output file you name. Both scripts read slop.json, the lexicon, and work entirely on your machine with no network calls and no uploads. They use only the Python standard library. The agent then rewrites the flagged lines itself and re-runs the scorer.