script-judges
xixihhhh/clipforgeSkill
A four-judge adversarial panel for short-video script lines (UGC ads, talking-head, mini-drama, 口播/带货台词). Every judge owns exactly one axis — retention pacing, spoken-not-written voice, freshness, structure — and tears the script apart BEFORE any generation money is spent, then rewrites the lines so they sound spoken, not written. Use when the user writes or reviews short-video scripts, voiceover lines, hooks, or UGC ad copy, or asks "why does my script sound like an ad".
Why this score
This repo hosts 2 skills, so its 1,034 stars are split between them (about 517 each) for scoring.
Popularity score: 78/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 21, 2026 at commit 1224b73b9139, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onescript-judges xixihhhh/clipforge · Skill | 78 | ★ 1.0k | ≈123 always | 27d ago |
| write-judge-prompt ai-evals-course/evals-skills · Skill Both about judge | 66 | ★ 1.5k | ≈24 always | 1mo ago |
| skill-judge shareAI-lab/Kode-CLI · Skill Both about judge | 77 | ★ 5.2k | ≈63 always | 19d ago |
| ugc-script-writer vibemarketer94/vibemarketer-skills · Skill Same job: ads | 48 | ★ 41 | ≈86 always | 5mo ago |
| judge-task-lifecycle sno-ai/sno-station · Skill Both about judge | 70 | ★ 765 | ≈38 always | 16d ago |
| eval-llm-judge Calibre-Labs/reforge-ai-evals · Skill Both about judge | 54 | ★ 76 | ≈26 always | 16d ago |