30-SECOND BRIEF
What it does—and when it fits
Nano Banana Edit is a RunComfy guide for Google Nano Banana 2's image-edit endpoint. It supports one to twenty publicly fetchable input images, preservation-first instructions, spatially scoped changes, locked aspect and resolution for batch consistency, and one to four outputs per call.
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/nano-banana-edit/~/.claude/skills/nano-banana-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 nano-banana-edit --agent claude-codeClaude Code discovers custom Skill folders automatically at project or personal scope.
View path evidence ↗TYPICAL WORKFLOW
A practical workflow
Preserve identity while editing
Swap backgrounds or clothing while explicitly protecting face, pose, brand, and framing.
Edit a batch consistently
Apply one scoped change across up to twenty inputs with locked framing.
Target a spatial region
Describe the exact object or area to add, remove, or replace.
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
- Inputs must be remotely fetchable URLs, and batch consistency or preservation can still fail.
- Multilingual text rewriting and single-reference precision may be better served by other documented routes.
BEST FIT
Who it is for
Teams editing product or campaign image batches
Creators needing identity-aware image changes
BEFORE YOU USE IT
Risks to review before use
Private images exposed through fetchable URLs
The remote service must fetch every input URL, and generated edits can misrepresent people or products. Use short-lived access, obtain consent, avoid confidential assets, monitor cost, and inspect each output.
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.