30-SECOND BRIEF
What it does—and when it fits
Image Edit is a RunComfy intent router for existing images. It defaults to Nano Banana Edit for general and batch work, selects GPT Image Edit for multilingual typography and multi-reference composition, Flux Kontext for a single precise local change, or mask-driven inpainting for a bounded region.
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/image-edit/~/.claude/skills/image-edit/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 image-edit --agent claude-codeClaude Code discovers custom Skill folders automatically at project or personal scope.
View path evidence ↗TYPICAL WORKFLOW
A practical workflow
Route an image-edit request
Match batch, text, local, or mask-driven intent to one model endpoint.
Preserve subjects across variants
Choose the route and prompting pattern most suited to identity or product consistency.
Handle precise text or layout
Use the GPT route for multilingual embedded text and directional layout changes.
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
- It chooses one route per call and inherits that model's input, mask, resolution, and output limits.
- Routing guidance reduces mismatches but does not guarantee visual fidelity, text accuracy, or stable identity.
BEST FIT
Who it is for
Creators unsure which hosted edit model to use
Teams standardizing image-edit workflows
BEFORE YOU USE IT
Risks to review before use
External upload and unintended manipulation
Input URLs and prompts leave the local environment, calls may be billable, and subtle model changes can alter identity, labels, or claims. Protect inputs, review permissions, and compare every result with the source.
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.