Python · MIT
phuryn/work-humanizer
A humanizer for work writing: takes the AI tone out without changing what your text says or commits to. Agent Skill + evidence: blind judges, hand-checked meaning changes, Pangram.
★ 119
Stars
14 forks · 0 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
18.9
Momentum / 100
see the breakdown below
30d ago
Created
last push 28d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 12.8 | last push 28d ago; decays to zero at 180 days |
| Scale | 15 | 6.0 | 119 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.9 | capped at 35 because growth is unmeasured |
Detail
| Topics | agent-skillsai-detectionai-writingclaude-codeclaude-skillscodexhumanizerwriting |
| Matched on | Agent Skills & MCP (agent-skills) |
| Short window | +0 stars over 8 days = 0.0/day |
| Long window | +23 stars over 26 days = 0.9/day |
| Lifetime average | 4.38 stars/day over 27 days |
| First seen here | 2026-10-11 |
| Last read | 10d ago |