AI dev tool
speak-human-tw
「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。
- Rank
- #3 of 2,432
- Stars
- 164★ +105/wk
- On radar
- since 2026-07-10
Momentum
rate of rise, not size · recomputes hourly
88.2
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
speak-human-tw is an AI dev tool ranked #3 of 2,432 on the Cresting momentum radar, with a score of 88.2. It has 164 GitHub stars, +105 in the last 7 days, and has been tracked since 2026-07-10.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.961 |
| Recency boost | 0.814 |
| Signal decay | 0.991 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+14 in window · 26 latest · 2 snapshots
github · stars+105 in window · 164 latest · 2 snapshots
Related ai dev tools
- pilotfishMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.#1 · 331★
- guizang-material-illustration归藏的材质插画 skill：生成带字解释图、图表美化和参考辅助配图。#4 · 538★
- fable-methodThe Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.#5 · 171★
- openscienceThe open-source AI workbench for scientific research#10 · 2,100★
- engramEvidence-based learning engine for Claude Code — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.#11 · 501★