5 Commits
Author SHA1 Message Date
Matt Van Horn 7bfde7f5b9 fix: add content preservation rule and strengthen em dash pattern
Add step 4 (Never truncate) to the Your Task checklist so the
humanizer preserves the full length of the original text instead
of condensing it. Also add spaced em dash and double-hyphen
examples to Pattern 14 so all common dash variants get caught.
2026-04-03 21:21:19 -07:00
Matt Van HornandClaude Opus 4.6 e7ffca9897 feat: add voice calibration from writing samples
Add optional Voice Calibration section to SKILL.md. When users provide
a sample of their own writing, the skill analyzes their sentence rhythm,
word choices, and quirks before rewriting - producing output that sounds
like them instead of generic clean human.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-20 07:53:51 -07:00
Matt Van Horn 3e1da8bfce docs: add MIT LICENSE file (#7)
README.md already declares MIT license. This adds the formal LICENSE
file so GitHub recognizes and displays it in the repo sidebar.

Fixes #7
2026-03-10 23:01:43 -07:00
Matt Van Horn 0e07850b01 fix: remove horizontal rule separators from SKILL.md (#35)
A skill that removes AI writing signs should not itself exhibit them.
ChatGPT puts --- before every headline; this removes all 28 instances.
Frontmatter delimiters are preserved. No content changes.

Fixes #35
2026-03-10 23:01:02 -07:00
Matt Van Horn 1a9e0fb1e9 feat: add hyphenated word pair overuse pattern (#42)
Add pattern #25 to detect AI-style uniform hyphenation of common
word pairs (cross-functional, data-driven, client-facing, etc.).
Bump version to 2.3.0.

Fixes #42
2026-03-10 23:00:09 -07:00