Extend Video Clips with Veo
Short video clips often end before a scene or narrative is complete. This skill sends an existing clip and a continuation prompt to Veo through RunComfy, then returns the next segment.
Copiez cette demande dans votre Agent. Elle contient la page Skill de référence et le manifeste.
Review the Skillstore skill "video-extend" from https://skillstore.io/skills/prime-skills-video-extend.md and its manifest at https://skillstore.io/api/skills/prime-skills-video-extend/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Votre Agent doit toujours présenter son plan et demander toute confirmation exigée par la politique de sécurité.
Utilisez ces liens lorsquâun Agent IA, un crawler ou un script a besoin dâun contexte propre au lieu de lire toute la page.
Utilisation de « video-extend ». An 8-second clip shows a cyclist approaching a bridge at sunrise. Continue the shot for 4 seconds.
RĂ©sultat attendu:
A continuation plan that keeps the sunrise lighting and camera direction, then has the cyclist begin crossing the bridge.
Utilisation de « video-extend ». Use Fast Extend to prototype the next story beat after a character opens a workshop door.
RĂ©sultat attendu:
All 52 static findings concern Markdown formatting, documented service links, standard credential storage, or endpoint recommendations rather than demonstrated malicious behavior. One semantic issue concerns misleading shell-safety guidance: JSON serialization alone does not safely quote arbitrary prompts for the illustrated Bash commands. No evidence found of credential exfiltration or instructions attempting to override the audit.
Partagez le rapport dâĂ©valuation versionnĂ©, le badge neutre, la carte intĂ©grable et les citations. Skillstore prĂ©sente les preuves sans dĂ©cider si ce Skill est sĂ»r.
https://skillstore.io/skills/prime-skills-video-extend/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/prime-skills-video-extend?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/prime-skills-video-extend?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-video-extend/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/prime-skills-video-extend.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>prime-skills. (2026). video-extend security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-video-extend/audits/1@techreport{prime-skills-prime-skills-video-extend-2026,
author = {prime-skills},
title = {video-extend security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/prime-skills-video-extend/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "video-extend security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "prime-skills"
date-released: "2026-11-01"
url: "https://skillstore.io/skills/prime-skills-video-extend/audits/1"
identifiers:
- type: other
value: "skillstore:prime-skills-video-extend:audit:1"
description: "Skillstore immutable audit report identifier"
Chaque auteur reste un skill installable distinct. La variante recommandée est classée selon les preuves Skillstore.
Pourquoi cette variante est premiĂšre
runcomfy-com-video-extend
2026-09-09
prime-skills-video-extend
2026-11-01
doany-ai-video-extend
2026-09-09
agentspace-so-video-extend
2026-10-22
Extend an existing Veo clip so a camera move, character action, or visual beat reaches a complete ending.
Chain short extensions to turn one seed clip into a longer narrative with planned beats and consistent visual direction.
Use Fast Extend for lower-cost drafts, compare continuation prompts, and reserve standard Extend for final delivery.
Extend this video by 4 seconds. Continue the existing motion naturally, keep the same subject and lighting, and describe only what happens next: [next action].
Continue the existing scene for 4 seconds. The camera [camera movement], while [subject action]. Preserve the current framing, lighting, environment, and subject identity.
Extend the previous shot for 5 seconds. Beat: [single story beat]. Keep the established visual style and physics. End with [clear transition state] for the next shot.
Create a continuation plan for this source clip. Propose three separate 3 to 5 second extensions, each with one action, camera anchors, and continuity constraints. Identify where a new image-to-video anchor may be needed.
Auteur
prime-skillsLicence
MIT
RĂ©vision Skillstore
r1
Avis de version
Lâauteur nâa dĂ©clarĂ© aucune version.
RĂ©f
1b490cbb10be886b70e8125cd28dc0c157f41a3c
RĂ©cence de maintenance
01/11/2026
Utilisation
0 téléchargements · 0 vues
Structure de fichiers
đ SKILL.md
Create and Edit AI Music with RunComfy
Choosing a suitable music model and request format can require detailed platform knowledge. This skill routes each request and prepares the correct RunComfy workflow.
Relight Still Images with RunComfy
Existing photos may have lighting that does not match the desired mood or product presentation. This skill guides RunComfy relighting with model selection and precise lighting prompts.
Animate Images with RunComfy Video Models
Different video requests require different models, media inputs, and prompt settings. This skill guides RunComfy model selection and CLI calls for animation, voiceover lip-sync, and combined references.
Edit Images with GPT Image on RunComfy
Targeted image edits can change details you want to preserve. This skill provides RunComfy commands and focused prompts for background changes, text replacement, and reference-based composition.
Edit Images with Intent-Based RunComfy Routing
Different image edits require different models and input formats. This skill selects a RunComfy route and prepares model-specific prompts and CLI requests.
Edit Image Regions with Masks or Descriptions
Local image edits need clear targeting and preservation constraints. This skill guides RunComfy model selection and CLI requests for masked inpainting or description-based edits.
CrĂ©er des vidĂ©os dâavatar IA avec RunComfy
par runcomfy-com
La crĂ©ation de vidĂ©os dâavatar avec synchronisation labiale nĂ©cessite souvent de choisir le bon modĂšle et le bon format dâentrĂ©e. Cette skill achemine les demandes vers les modĂšles RunComfy et fournit des invocations CLI prĂȘtes Ă lâemploi.
Modifier des vidéos avec le routage de modÚles RunComfy
par runcomfy-com
Les modifications vidĂ©o Ă©chouent souvent lorsque le mauvais modĂšle traite la tĂąche. Cette compĂ©tence achemine chaque requĂȘte vers un modĂšle RunComfy avec des prompts et des limites adaptĂ©s.
Exécuter des modÚles RunComfy depuis la CLI
par runcomfy-com
Les Ă©quipes ont besoin dâun moyen reproductible dâexĂ©cuter des modĂšles mĂ©dias RunComfy depuis des scripts. Cette skill guide lâinstallation de la CLI, lâauthentification, les exĂ©cutions de modĂšles, le polling et les tĂ©lĂ©chargements.
Générer des vidéos Wan 2.7 sur RunComfy
par runcomfy-com
Les Ă©quipes ont besoin de prompts text-to-video reproductibles sans devoir deviner chaque option de RunComfy. Cette skill donne Ă Claude, Codex et Claude Code un workflow Wan 2.7 ciblĂ© pour les prompts, les URL audio, les durĂ©es, les ratios dâaspect et les sorties.
Générer des vidéos IA avec RunComfy
par runcomfy-com
Choisir le bon modĂšle vidĂ©o et le bon format de prompt peut ralentir le travail de production. Cette compĂ©tence sĂ©lectionne une route RunComfy et prĂ©pare des instructions de gĂ©nĂ©ration claires, prĂȘtes pour la CLI.
Plan and Review Family Travel Films
par denyakortunov
Travel footage often lacks a clear story, reliable source notes, and organized feedback. This skill combines scene-planning guidance with local cataloguing and limited video helpers.