📦
controlnet-pose
79Create Pose-Controlled Images and Videos
Pose-controlled generation often requires choosing the right model and input format. This skill routes image and video requests to RunComfy workflows.
Design & Creative View
Skills image-outpainting
📦
image-outpainting
Content revision r1 Safe ⚙️ External commands🌐 Network access📁 Filesystem access
Extend Images with RunComfy Outpainting
Cropped images often miss needed canvas for banners, reels, and product layouts. This skill routes outpainting requests to RunComfy edit models through the runcomfy CLI.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "image-outpainting" from https://skillstore.io/skills/runcomfy-com-image-outpainting.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-image-outpainting/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.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "image-outpainting". A square product photo must become a wide catalog banner.
Expected outcome:
The skill recommends Nano Banana 2 Edit, asks for a 16:9 extension, and preserves product placement and shadow direction.
Using "image-outpainting". A portrait crop needs more surrounding room for a poster layout.
Expected outcome:
The skill frames an uncrop prompt, keeps the visible face unchanged, and extends clothing, background, and lighting downward.
Using "image-outpainting". A historical photo extension needs period-accurate surroundings.
Expected outcome:
The skill recommends GPT Image 2 Edit with reference photos or a ComfyUI workflow if seams need precise control.
Security Audit
Safev4 • 7/5/2026 Open versioned report
The static scan mostly matched Markdown code fences, inline backticks, documentation links, and transparent CLI guidance. I found no prompt-injection attempt, hidden execution logic, or unauthorized data-exfiltration intent in SKILL.md. The skill still depends on the RunComfy CLI and external RunComfy processing, which users should understand before use.
1
Files scanned
194
Lines analyzed
0
Review items
0
False positives ignored
Risk Factors
⚙️ External commands (37)
SKILL.md:6 SKILL.md:32-43 SKILL.md:43-45 SKILL.md:45-53 SKILL.md:53-58 SKILL.md:58-63 SKILL.md:63-64 SKILL.md:64-68 SKILL.md:68 SKILL.md:69-75 SKILL.md:75-82 SKILL.md:82-90 SKILL.md:90-94 SKILL.md:94-101 SKILL.md:101-105 SKILL.md:105 SKILL.md:107-108 SKILL.md:108-116 SKILL.md:116-119 SKILL.md:119-120 SKILL.md:120-130 SKILL.md:130-133 SKILL.md:133 SKILL.md:145-146 SKILL.md:146-152 SKILL.md:152-153 SKILL.md:153 SKILL.md:173 SKILL.md:177 SKILL.md:178 SKILL.md:179-183 SKILL.md:183 SKILL.md:185-189 SKILL.md:189-190 SKILL.md:190-191 SKILL.md:191-192 SKILL.md:192-193
🌐 Network access (19)
📁 Filesystem access (2)
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/runcomfy-com-image-outpainting/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/runcomfy-com-image-outpainting?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/runcomfy-com-image-outpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-image-outpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/runcomfy-com-image-outpainting.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
runcomfy-com. (2026). image-outpainting security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-image-outpainting/audits/4BibTeX citation
@techreport{runcomfy-com-runcomfy-com-image-outpainting-2026,
author = {runcomfy-com},
title = {image-outpainting security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/runcomfy-com-image-outpainting/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "image-outpainting security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "runcomfy-com"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/runcomfy-com-image-outpainting/audits/4"
identifiers:
- type: other
value: "skillstore:runcomfy-com-image-outpainting:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
agentspace-so Recommended
agentspace-so-image-outpainting
Skillstore Score 79
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
runcomfy-com Current
runcomfy-com-image-outpainting
Skillstore Score 78
Evidence Confidence High
Skillstore usage 9
Updated
2026-08-21
doany-ai-image-outpainting
Skillstore Score 76
Evidence Confidence High
Skillstore usage 15
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance
What You Can Build
Create Campaign Banners
Extend a product or portrait image into a horizontal banner while preserving the original subject and lighting.
Adapt Social Assets
Convert square assets into vertical or wide formats for feeds, stories, and reels.
Prepare Product Catalog Frames
Use reference images or alternate routes when a simple extension needs closer style matching.
Try These Prompts
Basic Canvas Extension
Extend this image to 16:9. Keep the original subject unchanged. Match the background, lighting, and camera distance. Image URL: [URL].
Portrait Uncrop
Uncrop this head-and-shoulders portrait downward. Show more upper body and arms. Preserve the face, pose, clothing style, and existing background. Image URL: [URL].
Reference Style Match
Outpaint this image using the reference image for surrounding style. Choose the route that best preserves layout and style. Original URL: [URL]. Reference URL: [URL].
Advanced Route Recovery
Plan a multi-step outpaint for this image. Compare Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro, and ComfyUI. Explain when to retry or switch routes. Image URL: [URL].
Best Practices
- State the target aspect ratio and extension direction at the start of the prompt.
- Use image URLs that the user explicitly provided and has permission to process.
- Review seams, lighting, and subject preservation before using the final image.
Avoid
- Do not paste secrets, private tokens, or unrelated data into image prompts.
- Do not use arbitrary third-party image URLs without user approval.
- Do not expect general edit endpoints to fix pixel-perfect seams every time.
Frequently Asked Questions
Does this skill create images from scratch?
No. It extends an existing still image beyond its current canvas.
Which RunComfy model is the default?
It recommends Nano Banana 2 Edit for normal prompt-shaped outpainting.
Can it use reference images?
Yes. It points to GPT Image 2 Edit when style or layout references are needed.
Does it support private images?
Yes, if the image URL is reachable and the user accepts external processing by RunComfy.
Can it run ComfyUI workflows through the CLI?
No. The skill says dedicated ComfyUI workflows must be opened in RunComfy cloud.
What tools does it require?
It requires the runcomfy CLI, RunComfy authentication, and network access to RunComfy endpoints.
Developer Details
Author
runcomfy-comLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
4 downloads · 0 views
File structure
📄 SKILL.md
More from runcomfy-com
View all📦
ace-step
79Generate ACE Step Music on RunComfy
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.
Design & Creative View
📦
elevenlabs-music-generation
79Generate Music with ElevenLabs on RunComfy
Creating production-ready music prompts and CLI calls can be slow and error-prone. This skill guides Claude, Codex, and Claude Code through ElevenLabs Music generation on RunComfy with clear parameters and workflow advice.
Design & Creative View
📦
ai-avatar-video
79Create AI Avatar Videos with RunComfy
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.
Design & Creative View
📦
image-inpainting
79Inpaint Images with RunComfy
Mask-driven image edits can be slow when prompts, masks, and model choices are handled manually. This skill guides Claude, Codex, or Claude Code to run RunComfy inpainting with the right model and inputs.
Design & Creative View
📦
image-to-video
78Animate Images with RunComfy Video Models
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.
Design & Creative View
Related Skills
View all📦
flux-kontext
78Edit Images with Flux Kontext Pro
by agentspace-so
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.
Design & Creative View
📦
relight
78Relight Images with RunComfy
by agentspace-so
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.
Design & Creative View
📦
imagegen
82Create and Edit Project Images
by openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.
Design & Creative View
📦
ai-image-generation
78Generate AI Images With Inference.sh
by tool-belt
Teams need fast access to many hosted image models without learning each provider API. This skill guides Claude, Codex, and Claude Code through inference.sh CLI workflows for generation, editing, upscaling, and stitching.
Design & Creative View
📦
fal-image-edit
78Edit Images with AI Guidance
by sickn33
Image edit requests can be vague and hard to translate into model instructions. This skill helps Claude, Codex, and Claude Code shape clear guidance for style transfer, object removal, and image edits.
Design & Creative View
📦
qwen-image-2-pro
78Generate Professional Images with Qwen Image Pro
by inferen-sh
Text-heavy image prompts often produce weak layouts and unreadable lettering. This skill guides Qwen-Image-2.0-Pro generation and editing through inference.sh.
Design & Creative View