Generate Wan 2.7 Videos on RunComfy
Short video generation needs precise model inputs and clear output controls. This skill helps Claude, Codex, and Claude Code prepare Wan 2.7 requests through the RunComfy CLI.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "wan-2-7" from https://skillstore.io/skills/agentspace-so-wan-2-7.md and its manifest at https://skillstore.io/api/skills/agentspace-so-wan-2-7/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "wan-2-7". A creator asks for a five second product video in landscape format.
Expected outcome:
The skill produces a RunComfy generation plan with Wan 2.7 selected, 1080p resolution, 16:9 framing, a single product action, and a named output folder.
Using "wan-2-7". A producer provides a voiceover URL and asks for a vertical spokesperson clip.
Expected outcome:
The skill maps the audio URL to lip-sync generation, sets vertical framing, matches duration, and recommends a close-up prompt with stable lighting.
Using "wan-2-7". A team wants brand-strict wording without automatic prompt changes.
Expected outcome:
The skill recommends disabling prompt expansion, using a precise negative prompt, and reusing a seed for controlled comparisons.
Most static backtick findings are Markdown formatting false positives, but the skill does document real RunComfy CLI execution and a hosted API workflow. I confirmed the external command and outbound network risks, found no prompt injection attempt, and found no malicious hidden-file behavior.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/agentspace-so-wan-2-7/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/agentspace-so-wan-2-7?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/agentspace-so-wan-2-7?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentspace-so-wan-2-7/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/agentspace-so-wan-2-7.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>agentspace-so. (2026). wan-2-7 security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/agentspace-so-wan-2-7/audits/8@techreport{agentspace-so-agentspace-so-wan-2-7-2026,
author = {agentspace-so},
title = {wan-2-7 security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/agentspace-so-wan-2-7/audits/8},
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: "wan-2-7 security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "agentspace-so"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/agentspace-so-wan-2-7/audits/8"
identifiers:
- type: other
value: "skillstore:agentspace-so-wan-2-7:audit:8"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-wan-2-7
2026-08-21
doany-ai-wan-2-7
2026-08-21
agentspace-so-wan-2-7
2026-08-21
Prepare concise Wan 2.7 prompts for short product videos with controlled camera motion, duration, and aspect ratio.
Use an audio URL with matching duration settings to create short spokesperson or localization clips.
Iterate negative prompts, prompt expansion, and seed values while keeping the RunComfy request structure consistent.
Create a Wan 2.7 request for a five second 1080p product video. Include camera motion, one main action, aspect ratio, and output directory guidance.
Prepare a Wan 2.7 lip-sync video request using this audio URL: [audio URL]. Match the duration, choose the aspect ratio, and include prompt details for a stable close-up shot.
Build a Wan 2.7 request that keeps my prompt literal. Disable prompt expansion, add a focused negative prompt, and explain which fields affect consistency.
Design three Wan 2.7 variants for the same concept. Keep the core prompt stable, vary seed and framing choices, and summarize expected tradeoffs for review.
Author
agentspace-soLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88
Maintenance freshness
7/18/2026
Usage
3 downloads · 94 views
File structure
📄 SKILL.md
Extend Images Beyond the Frame
Cropped images often need a wider canvas for banners, social posts, or product layouts. This skill guides Claude, Codex, and Claude Code to outpaint images with RunComfy models while preserving the original subject.
Edit Images with Flux Kontext Pro
Precise image edits need clear model routing and focused prompts. This skill helps Claude, Codex, and Claude Code call Flux 1 Kontext Pro through RunComfy with practical prompt patterns.
Edit video regions across frames
Removing or replacing a video region across frames can cause visual drift and broken motion. This skill selects a suitable RunComfy route and provides focused prompts for consistent edits.
Relight Images with RunComfy
Changing image lighting usually requires a new shoot or manual editing. This skill helps Claude, Codex, or Claude Code route still-image relighting requests through RunComfy models.
Generate AI Videos with RunComfy
Choosing a video model and its required inputs can slow production. This skill routes each request and prepares a focused RunComfy generation command.
Edit Videos with RunComfy Model Routing
Choosing the right video edit model is hard when each route has different strengths. This skill routes the request and prepares prompts for RunComfy video editing models.
Animate Images with RunComfy Video Models
by runcomfy-com
Still images need the right model and prompt to become useful video clips. This skill routes image-to-video requests to RunComfy models with matching settings and examples.
Create AI Avatar Videos with RunComfy
by runcomfy-com
Creating lip-synced avatar videos often requires choosing the right model and input format. This skill routes requests to RunComfy models and provides ready CLI invocations.
Create Seedance Video Prompts
by songguoxs
Video creators need structured Chinese prompts for Seedance workflows. This skill builds prompt plans for scenes, references, timing, sound, and extensions.
Create AI Video Plans for Marketing
by CleanExpo
Marketing teams need clear video plans before using generation tools. This skill turns campaign ideas into scripts, shot lists, platform notes, and edit guidance.
Generate ACE Step Music on RunComfy
by runcomfy-com
Creating affordable AI music often needs endpoint selection, structured lyrics, and repeatable CLI inputs. This skill guides ACE Step generation, inpainting, and outpainting through RunComfy.
Create Pose-Controlled Images and Videos
by doany-ai
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.