| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| Humanizer v3.1.0 source code.tar.gz | 2026-09-28 | 24.6 kB | |
| Humanizer v3.1.0 source code.zip | 2026-09-28 | 31.3 kB | |
| README.md | 2026-09-28 | 1.4 kB | |
| Totals: 3 Items | 57.3 kB | 80 | |
Humanizer 3.1.0 adds a pattern for replies that re-explain what the reader already knows, and it tightens the skill so each rule is stated once.
What changed
- Added pattern [#26] and section F for replies that re-explain context the reader already has (#269). It acts on replies, not standalone writing. 26 patterns total.
- Extended the core rule so "something the reader did not already have" counts the surrounding conversation, not only earlier text.
- Widened [#25] to text that describes its own sourcing, assembly, or layout (#290), and added headings written for effect to [#20].
- Extended [#2] to "That distinction matters." (#277) and to a sentence that explains what an example already showed (#295).
- Narrowed [#10] so words the dictionary always hyphenates keep their hyphen. Gave each watched word one pattern, and stated the evidence rule and the no-invention rule once each.
- Fixed the Voice section's dash reference (#273) and the marketplace schema URL (#288).
- Added a Cursor plugin manifest (#278).
- README: opens with a before/after, the five strongest tells, and install steps for each agent. States that getting past AI detectors is not a goal. The full example's rewrite now keeps every fact from its draft and adds none. Version history moved to CHANGELOG.md.
Thanks to @Kutomore, @jkhereford, @jabrahamtech, @dajiaohuang, @jakub-zieba, and @bitnom for the fixes, patterns, and reports in this release.
