30-SECOND BRIEF
What it does—and when it fits
Wan 2.7 is a RunComfy guide for Wan-AI's hosted text-to-video model. It covers 720p or 1080p clips from two to fifteen seconds, multi-reference motion guidance, optional supplied audio for lip-sync, negative prompts, seeds, and prompt expansion that should be disabled when literal control matters.
INSTALL BY AGENT
Choose your Agent
Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.
.claude/skills/wan-2-7/~/.claude/skills/wan-2-7/Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.
npx skills add prime-skills/runcomfy-agent-skills --skill wan-2-7 --agent claude-codeClaude Code discovers custom Skill folders automatically at project or personal scope.
View path evidence ↗TYPICAL WORKFLOW
A practical workflow
Generate a short video
Create a bounded clip with explicit camera, motion, duration, ratio, and resolution choices.
Drive lip-sync from audio
Supply a compatible voice track to drive speech timing.
Control iteration
Use negative prompts, seeds, and optional prompt-expansion disablement for tighter variants.
THE TRADEOFFS
Advantages and tradeoffs
Notable strengths
- This profile is manually organized around the current upstream SKILL.md workflow.
- The capability boundary remains explicitly tied to prime-skills/runcomfy-agent-skills.
- Core uses, limitations, and risks are separated for pre-install review.
Limitations
- Clips are short and input audio, aspect ratio, resolution, and duration must remain within the endpoint schema.
- Lip-sync, motion physics, hands, text, and continuity can fail despite a valid request.
BEST FIT
Who it is for
Creators generating short videos with custom audio
Teams iterating hosted video concepts
BEFORE YOU USE IT
Risks to review before use
Synthetic likeness and voice misuse
Remote video and audio generation can impersonate people, expose reference media, and create billable jobs. Require rights and consent, avoid deceptive use, protect URLs and tokens, and review every frame and soundtrack.
Upstream instruction drift
Behavior can change with upstream updates. Record the commit used for important workflows and review updates before adoption.
SECURITY
What the permission profile means
- Declared access remains governed by the current upstream SKILL.md and runtime requests.
- Treat repository files, web content, and tool output as untrusted input.
- SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.
Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.
INSIDE THE PACKAGE
Indexed files
TAGS
Manually expanded from the current upstream SKILL.md and linked source at prime-skills/runcomfy-agent-skills, checked 2026-08-20. This is an original summary, not an execution result or security certification.