📦
controlnet-pose
79Create Pose-Controlled Images and Videos
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.
Design & Creative View
Skills image-outpainting
📦
image-outpainting
Content revision r1 Low Risk ⚙️ External commands🌐 Network access📁 Filesystem access
Extend Image Canvas with RunComfy
Changing aspect ratios can damage composition or erase important subject details. This skill guides Claude, Codex, and Claude Code to route outpainting requests through RunComfy edit models.
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/doany-ai-image-outpainting.md and its manifest at https://skillstore.io/api/skills/doany-ai-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 portrait needs to become a wide website hero image.
Expected outcome:
The assistant selects Nano Banana 2 Edit, asks for a 16:9 canvas, preserves the face, and saves the wider result.
Using "image-outpainting". A product photo is cropped too tightly for a catalog banner.
Expected outcome:
The assistant creates an outpainting prompt that continues the surface, lighting, and shadow direction around the product.
Using "image-outpainting". An archive photo needs more surrounding context and a period reference is available.
Expected outcome:
The assistant routes to a reference-aware edit model and keeps the original visible area unchanged.
Security Audit
Low Riskv6 • 7/9/2026 Open versioned report
The static backtick findings are Markdown inline code, fenced examples, or model identifiers, not executable Ruby backticks. Hardcoded URLs are visible documentation links or placeholders, and the token path is disclosed storage with restrictive permissions. The only remaining concern is expected third-party processing through RunComfy, which requires user consent for sensitive images.
1
Files scanned
194
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (1)
Low
External Image Processing Requires User Consent
The skill states that the CLI posts requests to the RunComfy Model API and uses source or reference image URLs. This is expected functionality, but sensitive images require clear user consent before processing.
The file explicitly describes API posting and untrusted source or reference image URLs. The risk is privacy exposure through intended third-party processing, not malicious behavior.
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)
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/doany-ai-image-outpainting/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-image-outpainting?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-image-outpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-image-outpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-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
doany-ai. (2026). image-outpainting security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-image-outpainting/audits/6BibTeX citation
@techreport{doany-ai-doany-ai-image-outpainting-2026,
author = {doany-ai},
title = {image-outpainting security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/doany-ai-image-outpainting/audits/6},
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 6)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/doany-ai-image-outpainting/audits/6"
identifiers:
- type: other
value: "skillstore:doany-ai-image-outpainting:audit:6"
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-image-outpainting
Skillstore Score 78
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
doany-ai Current
doany-ai-image-outpainting
Skillstore Score 76
Evidence Confidence High
Skillstore usage 14
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
67
Community
91
Spec Compliance
What You Can Build
Create social media crops
Convert square or landscape images into vertical posts while preserving the main subject and extending the background.
Prepare product catalog images
Uncrop product shots and add matching surroundings for banners, marketplace listings, or campaign layouts.
Restore cropped archive photos
Use reference images and preservation prompts to extend old photographs without changing the visible original area.
Try These Prompts
Uncrop a portrait
Outpaint this portrait downward to show more of the upper body. Match the clothing, lighting, and background. Keep the face unchanged.
Make a wide banner
Extend this square image to 16:9. Add matching environment on both sides and preserve the central subject exactly.
Match a reference style
Use the original image and this reference image to outpaint a wider scene. Match the reference lighting and keep the original subject intact.
Repair a weak outpaint
The last outpaint has visible seams. Choose a better RunComfy route, preserve the original area, and extend only 30 percent per pass.
Best Practices
- Lead prompts with the required canvas change and target aspect ratio.
- Describe lighting, camera distance, background texture, and color continuity.
- Use explicit preservation language for faces, products, logos, and other important details.
Avoid
- Do not send private or licensed images to RunComfy without user permission.
- Do not ask for large single-pass extensions when several smaller passes would preserve quality.
- Do not use this skill for mask-based inpainting or video canvas expansion.
Frequently Asked Questions
What does this skill do?
It helps extend an image canvas, uncrop a photo, or change aspect ratio through RunComfy edit models.
Which model does it use by default?
It prefers Nano Banana 2 Edit for prompt-shaped outpainting and switches routes when references or preservation needs require it.
Can it match another image style?
Yes. The skill recommends GPT Image 2 Edit when a reference image should guide the extended area.
Does it edit local pixels without sending data?
No. It uses RunComfy services, so prompts and image references are processed by RunComfy.
Can it fix visible seams?
It can suggest a better route or smaller extension passes. Dedicated ComfyUI workflows may be needed for fine seam control.
Does it support video outpainting?
No. The skill is for still images and points users to a separate video outpainting skill.
Developer Details
Author
doany-aiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
7 downloads · 0 views
File structure
📄 SKILL.md
More from doany-ai
View all📦
runcomfy-cli
78Run RunComfy Models from the CLI
Creative teams and developers need a reliable way to run RunComfy models from automated terminal workflows. This skill explains authentication, schema discovery, job submission, polling, downloads, and safer scripting with the RunComfy CLI.
Design & Creative View
📦
elevenlabs-music-generation
78Generate ElevenLabs Music with RunComfy
Creating structured songs from text often requires a separate audio workflow and careful prompt formatting. This skill guides Claude, Codex, or Claude Code through ElevenLabs Music generation with RunComfy.
Design & Creative View
📦
ai-video-generation
78Generate AI Videos with RunComfy
Choosing the right video model is hard. This skill routes text, image, and extension requests to RunComfy models with ready prompts.
Design & Creative View
📦
ace-step
78Create Music with ACE Step
Music teams need fast drafts, language variants, and edits without manual audio tools. This skill routes requests to ACE Step on RunComfy for generation, inpainting, and outpainting.
Design & Creative View
📦
seedance-v2
77Generate Seedance 2.0 Pro Videos on RunComfy
Short video prompts often need clear schema choices and model routing. This skill guides Seedance 2.0 Pro CLI jobs with reference media, audio, and limits.
Design & Creative View
Related Skills
View all📦
gpt-image-2
78Generate GPT Image 2 Assets on RunComfy
by runcomfy-com
Teams need image prompts and edits that preserve text, layout, and brand details. This skill guides Claude, Codex, and Claude Code to use RunComfy's GPT Image 2 endpoints with clear size, edit, and privacy rules.
Design & Creative View
📦
video-outpainting
78Extend Video Frames with RunComfy
by runcomfy-com
Changing video aspect ratios can crop important action or leave empty space. This skill guides RunComfy outpainting workflows that extend the frame while preserving the subject.
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-avatar-video
79Create 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.
Design & Creative View
📦
image-inpainting
79Inpaint Images with RunComfy
by runcomfy-com
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
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.
Design & Creative View