Skills/ClawHub/aikey-cut

aikey-cut@0.4.5

CAUTION

Publisher claims: "AI KEY·口播剪辑 ——口播成片剪辑技能。把拍好的素材剪成可发布的成片:**按文案规则做内容层重组**(删废镜头/去重复/重排顺序)→ 语音剪辑(去口癖/停顿)→ 加速 → 字幕 → B-roll → 交付。 🔴 **只删和重排,不加词** —— 说话人没说过的话一个字都不加。 中文口播的剪辑工作流(判据按中文口播写;用户用别的语言时照常用他的语言交流,并说明规则是按中文口播定的)。 默认参数(抖音 · 保持原长 · 1.15× · HarmonyOS Sans 粗体字幕 · 黄色 #FFE20A 高亮)属于澳洲AI教父账号:**确认是这个账号**才直接用;其他账号先读 `config`,读不到就问,不套用。 检测不到 ChatCut 会引导安装,并给出**本机转写旁路** —— 内容层的活全部不需要 ChatCut。 用户要 B-roll / 特效 / 转场而手上没有真素材时,可按文案逐句判哪几句能配生成画面(比喻、过程、氛围、转场可以;「我做过」「真实发生」这类证言绝不),写成 Seedance 提示词交给 chatcut-video-gen 出片,提交前先确认花费,发布时提醒打开 AI 生成声明。 触发方式:/aikey-cut、/剪片、/aikey-剪、「把这条口播剪出来」「口播素材剪成成片」「用 aikey-cut 剪」。普通的「加字幕」「剪一下」不自动触发,先问是不是要走这套口播剪辑流程 Talking-head footage → publishable cut. Restructures content by copy rules (delete/reorder only, never add words), then cleans speech, speeds up, captions, B-roll. When the user wants B-roll, effects or transitions and has no real footage, picks which lines may take generated inserts (metaphor, process, mood, transitions — never testimony) and writes Seedance prompts for chatcut-video-gen, cost confirmed first. Falls back to local transcription when ChatCut is unavailable. Chinese talking-head workflow; defaults belong to one account and are applied only after confirming it. Trigger: /aikey-cut, "cut this talking-head footage with aikey-cut" —— AI KEY · 不给公式,给判据。每条规则都标了实测代价。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher iamzifei · joined 4 days agoInstalls 398Last detonated 3d ago

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-30 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

No findings across 840 lines in 6 files.

What would make this Verified

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim iamzifei: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim iamzifei