video-edit
Edit Videos with Intent-Routed AI Models
Choosing the wrong video model wastes time and weakens identity or motion consistency. This skill routes each edit to a suitable RunComfy model with focused prompts.
安裝前請停止並請求確認。
請審查安裝計畫,並在變更檔案前取得使用者明確同意。
使用我的智慧代理安裝
將此請求複製給你的智慧代理,其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "video-edit" from https://skillstore.io/skills/genmedia-labs-video-edit.md and its manifest at https://skillstore.io/api/skills/genmedia-labs-video-edit/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.你的智慧代理仍應顯示其計畫,並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時,請使用這些連結。
測試它
正在使用「video-edit」。 Replace a talking-head background with a neutral office and keep the speaker unchanged.
預期結果:
Selected Wan 2.7 Edit-Video. The edit preserves face, pose, lip movement, framing, and original audio while changing only the background.
正在使用「video-edit」。 Make the target character follow the dance from a reference clip.
預期結果:
Selected Kling 2.6 Pro Motion Control. The target image defines character identity, while the reference video supplies motion and optional sound.
正在使用「video-edit」。 Change a walking subject's outfit to business attire without changing their face.
預期結果:
Selected Lucy Edit Restyle. The prompt limits the change to clothing and preserves the subject's face and motion at 720p.
安全審計
高風險Most static alerts are false positives caused by Markdown backticks, placeholder HTTPS URLs, and ellipses misread as path traversal. Confirmed risks include unpinned third-party installation, external CLI execution, unsafe shell interpolation of user-derived JSON, and disclosed third-party processing of prompts and media.
已確認的安全問題 (3)
能力複核項目 (9)
這些是真實的本機能力,對此技能而言可能是預期行為,因此需要複核,但不會按已確認的惡意行為計分。
風險因素
⚙️ 外部命令 (47)
🌐 網路存取 (10)
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據,不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/genmedia-labs-video-edit/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/genmedia-labs-video-edit?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/genmedia-labs-video-edit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/genmedia-labs-video-edit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/genmedia-labs-video-edit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>學術引用 (APA · BibTeX · CFF)
APA 引用
genmedia-labs. (2026). video-edit security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/genmedia-labs-video-edit/audits/1BibTeX 引用
@techreport{genmedia-labs-genmedia-labs-video-edit-2026,
author = {genmedia-labs},
title = {video-edit security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/genmedia-labs-video-edit/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "video-edit security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "genmedia-labs"
date-released: "2026-08-13"
url: "https://skillstore.io/skills/genmedia-labs-video-edit/audits/1"
identifiers:
- type: other
value: "skillstore:genmedia-labs-video-edit:audit:1"
description: "Skillstore immutable audit report identifier"
比較變體
6 個可安裝變體每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。
為何此變體排名第一
skills-collective-video-edit
2026-09-09
Skillstore 評分
評分依據 證據置信度: 中你可以打造什麼
Polish Product Videos
Replace packaging or backgrounds while preserving framing, hand movement, camera motion, and source audio.
Transfer Character Motion
Map movement from a reference clip onto a target character while maintaining visual identity.
Restyle Short Social Clips
Change outfits, lighting, or atmosphere while preserving faces, poses, and motion.
試試這些提示
Edit {video_url}. Preserve the subject's face, pose, motion, and audio. Change only the background to {background_description}.Use {reference_image_url} to replace the package design in {video_url}. Preserve framing, hand movement, camera motion, and original audio.Transfer motion from {motion_video_url} to the character in {character_image_url}. Keep the character identity and {sound_preference}.Restyle {video_url} with {single_visual_change}. Preserve {identity_features}, {motion_features}, framing, and aspect ratio. Use {resolution} and seed {seed}.最佳實務
- State preservation requirements before the requested visual change.
- Request one edit direction per run to reduce temporal drift.
- Use reference media only when a specific appearance or motion must transfer.
避免
- Do not combine unrelated outfit, background, lighting, and character changes in one request.
- Do not send confidential media without approval for third-party processing.
- Do not interpolate untrusted prompts or URLs directly into shell command strings.
常見問題
Which model handles general video edits?
Which model transfers motion from another video?
Which model is suitable for outfit swaps?
Can the skill preserve source audio?
Does processing occur locally?
What output limits apply?
開發者詳細資訊
授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
儲存庫
https://github.com/genmedia-labs/skills/tree/9f1b4c229cb9e0c962f11ef24c8c87d5f004f393/video-edit引用
68046dfc1c93b48a04e43344644ad77d3a895012
維護新鮮度
2026/8/13
使用量
0 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md