Generate AI Videos with the Right RunComfy Model
Choosing among video models and parameter formats is difficult. This skill selects a suitable RunComfy route and prepares the generation request.
ArrĂȘtez-vous et demandez confirmation avant lâinstallation.
Examinez le plan et obtenez le consentement explicite de lâutilisateur avant de modifier des fichiers.
Copiez cette demande dans votre Agent. Elle contient la page Skill de référence et le manifeste.
Review the Skillstore skill "ai-video-generation" from https://skillstore.io/skills/prime-skills-ai-video-generation.md and its manifest at https://skillstore.io/api/skills/prime-skills-ai-video-generation/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.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 « ai-video-generation ». Create an eight-second beach scene with a kite, children, wind, and natural audio.
RĂ©sultat attendu:
Recommended route: HappyHorse text-to-video. It supports synchronized audio, short multi-shot scenes, 1080p output, and direct motion-focused prompting.
Utilisation de « ai-video-generation ». Animate a product photo with an exact 180-degree rotation and no background movement.
RĂ©sultat attendu:
Recommended route: Veo image-to-video. The prompt emphasizes the exact rotation, a fixed camera, and no movement outside the product.
Utilisation de « ai-video-generation ». Create a dialogue clip from a portrait and an existing voiceover.
RĂ©sultat attendu:
Recommended route: Wan text-to-video with the voiceover as the audio reference. The scene prompt describes the speaker and lighting without repeating the dialogue.
The analyzer substantially over-reported Markdown backticks, documentation links, model advice, and secure token-storage documentation as executable threats. Package installation commands create real supply-chain exposure, and the single-quoted shell examples lack a documented method for safely handling arbitrary user text. The intended workflow also sends generation inputs to RunComfy and downloads results.
Il sâagit de capacitĂ©s locales rĂ©elles qui peuvent ĂȘtre attendues pour cette compĂ©tence ; elles nĂ©cessitent donc un examen, mais ne sont pas comptabilisĂ©es comme comportement malveillant confirmĂ©.
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-ai-video-generation/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/prime-skills-ai-video-generation?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/prime-skills-ai-video-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-ai-video-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/prime-skills-ai-video-generation.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). ai-video-generation security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-ai-video-generation/audits/2@techreport{prime-skills-prime-skills-ai-video-generation-2026,
author = {prime-skills},
title = {ai-video-generation security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/prime-skills-ai-video-generation/audits/2},
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: "ai-video-generation security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
- name: "prime-skills"
date-released: "2026-08-14"
url: "https://skillstore.io/skills/prime-skills-ai-video-generation/audits/2"
identifiers:
- type: other
value: "skillstore:prime-skills-ai-video-generation:audit:2"
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-ai-video-generation
2026-09-09
inference-shell-ai-video-generation
2026-09-09
agentspace-so-ai-video-generation
2026-10-22
inferen-sh-ai-video-generation
2026-09-09
doany-ai-ai-video-generation
2026-09-09
halt-catch-fire-ai-video-generation
2026-09-09
inference-sh-skills-ai-video-generation
2026-09-09
skills-collective-ai-video-generation
2026-09-09
tool-belt-ai-video-generation
2026-09-09
skills-shell-ai-video-generation
2026-09-09
inference-skills-ai-video-generation
2026-09-09
qu-skills-ai-video-generation
2026-09-09
tul-sh-ai-video-generation
2026-09-09
toolshell-ai-video-generation
2026-09-09
infsh-skills-ai-video-generation
2026-09-09
skillssh-ai-video-generation
2026-09-09
101-skills-ai-video-generation
2026-10-12
danielgwilson-ai-video-generation
2026-09-09
genmedia-labs-ai-video-generation
2026-09-09
inference-sh-ai-video-generation
2026-09-09
inference-sh-9-ai-video-generation
2026-09-09
inference-sh-8-ai-video-generation
2026-09-09
prime-skills-ai-video-generation
2026-09-09
Turn a short concept or still image into a vertical clip with suitable motion, duration, and optional audio.
Select a model for realistic product rotation, controlled camera movement, or a polished advertising shot.
Compare model routes and prepare repeatable CLI requests for text, image, audio, or video-conditioned generation.
Create a [duration]-second [aspect ratio] video of [subject] performing [action] in [setting]. Choose a suitable RunComfy model and explain the choice.
Animate the image at [image URL]. Keep [elements] stable, add [motion], use [camera direction], and target [aspect ratio].
Create a speaking-subject video using [audio URL] and [scene description]. Select a lip-sync route and preserve the speaker's appearance.
Design a [duration]-second sequence using [image references], [video references], and [audio references]. Compare suitable models, then specify shots, transitions, camera language, and constraints.
Auteur
prime-skillsLicence
MIT
RĂ©vision Skillstore
r1
Avis de version
Lâauteur nâa dĂ©clarĂ© aucune version.
RĂ©f
5e24cda299fe1de022e0ea01edcc76817d9b7f9c
RĂ©cence de maintenance
15/08/2026
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.
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.
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.
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.
Expand Video Canvases with RunComfy
Changing video formats can crop important action or leave empty borders. This skill guides prompt-driven canvas expansion through RunComfy and recommends dedicated workflows for stricter quality needs.
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.
Créer des images et des vidéos contrÎlées par la pose
par runcomfy-com
La gĂ©nĂ©ration contrĂŽlĂ©e par la pose nĂ©cessite souvent de choisir le bon modĂšle et le bon format d'entrĂ©e. Cette skill dirige les requĂȘtes d'images et de vidĂ©os vers des workflows RunComfy.
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.
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.
Prolonger des vidéos avec RunComfy
par runcomfy-com
Les courts clips gĂ©nĂ©rĂ©s ont souvent besoin de plus de temps, de fins plus propres ou dâenchaĂźnements narratifs connectĂ©s. Cette compĂ©tence aide Claude, Codex et Claude Code Ă prolonger des vidĂ©os approuvĂ©es avec RunComfy.
Créer des prompts vidéo Seedance
par songguoxs
Les créateurs vidéo ont besoin de prompts chinois structurés pour les workflows Seedance. Cette compétence élabore des plans de prompts pour les scÚnes, les références, le timing, le son et les extensions.