Image Editing

Edit images with AI inpainting, outpainting, background removal, upscaling, and restoration tools.

MIT-0 · Free to use, modify, and redistribute. No attribution required.
4 · 4.4k · 51 current installs · 55 all-time installs
byIván@ivangdavila
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description align with the contents: all technique files (inpainting, outpainting, background removal, upscaling, restoration, style-transfer) and the tools list support image editing workflows.
Instruction Scope
SKILL.md itself restricts scope to image edits and preserving originals. Technique files explicitly show how to call cloud APIs and local tools. Those instructions involve uploading user images to third‑party endpoints (OpenAI, Stability, ClipDrop, remove.bg, Replicate, Magnific, etc.), which is expected for cloud-based editing but is a privacy/flow consideration the user must accept.
Install Mechanism
No install spec and no code files — instruction-only skill. Technique docs show pip/npm/CLI installs for optional local tools, which is reasonable and low-risk because nothing is automatically downloaded or executed by the skill itself.
!
Credentials
Technique files repeatedly reference API keys/environment variables (OPENAI_API_KEY, API_KEY, YOUR_API_KEY) and provider credentials but the skill metadata declares no required env vars or primary credential. This inconsistency is notable: the skill will expect you to supply multiple unrelated API keys to use cloud providers, and images will be sent to those services. The number of external services referenced is high relative to the simple description; ensure you only provide credentials for providers you trust and that you understand privacy/cost implications.
Persistence & Privilege
always is false and the skill is user-invocable; it requests no system-wide config or special persistent privileges. There is no evidence it attempts to modify other skills or system settings.
What to consider before installing
This skill appears to be a normal, instruction-only image-editing guide, but it shows many examples that upload images to third-party APIs (OpenAI, Stability AI, remove.bg, ClipDrop, Replicate, Magnific, etc.). The metadata does not declare any required API keys even though the examples require them — that mismatch is likely an oversight but worth noting. Before installing or using it: (1) Decide whether you're comfortable having your images sent to external services and review their privacy/retention policies; (2) Only provide API keys for providers you trust and avoid pasting broad-scope credentials; (3) Prefer local/open-source tools (rembg, IOPaint, Real-ESRGAN, GFPGAN) if you need offline processing; (4) Check costs for cloud APIs to avoid unexpected charges; (5) If you need the agent to call cloud APIs automatically, verify which provider(s) you want and supply only those credentials — the skill won't, by itself, restrict which third‑party endpoints you might use in its examples.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
latestvk970yy99qgtcc3dm7we9pyamzh810bta

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

✂️ Clawdis
OSLinux · macOS · Windows

SKILL.md

AI Image Editing

Help users edit and enhance images with AI tools.

Rules:

  • Ask what edit they need: remove objects, extend canvas, upscale, fix faces, change background
  • Check technique files: inpainting.md, outpainting.md, background-removal.md, upscaling.md, restoration.md, style-transfer.md
  • Check tools.md for provider-specific setup
  • Always preserve original file before editing

Edit Type Selection

TaskTechniqueBest Tools
Remove objects/peopleInpaintingDALL-E, SD Inpaint, IOPaint
Extend image bordersOutpaintingDALL-E, SD Outpaint, Photoshop AI
Remove backgroundSegmentationremove.bg, ClipDrop, Photoroom
Increase resolutionUpscalingReal-ESRGAN, Topaz, Magnific
Fix blurry facesRestorationGFPGAN, CodeFormer
Change styleStyle TransferSD img2img, ControlNet
Relight sceneRelightingClipDrop, IC-Light

Workflow Principles

  • Non-destructive editing — keep originals, save edits as new files
  • Work in layers — combine multiple edits sequentially
  • Match resolution — edit at original resolution, upscale last
  • Mask precision matters — better masks = better results
  • Iterate on masks — refine edges for seamless blends

Masking Basics

Masks define edit regions:

  • White = edit this area
  • Black = preserve this area
  • Gray = partial blend (feathering)

Mask creation methods:

  • Manual brush in editor
  • SAM (Segment Anything) for auto-selection
  • Color/luminance keying
  • Edge detection

Common Workflows

Object Removal

  1. Create mask over unwanted object
  2. Run inpainting with context prompt (optional)
  3. Blend edges if needed
  4. Touch up artifacts

Background Replacement

  1. Remove background (get transparent PNG)
  2. Place on new background
  3. Match lighting/color
  4. Add shadows for realism

Enhancement Pipeline

  1. Restore faces (if present)
  2. Remove artifacts/noise
  3. Color correct
  4. Upscale to final resolution

Quality Tips

  • Feather masks — hard edges look artificial
  • Context prompts help — describe what should fill the area
  • Multiple passes — large edits may need iterative refinement
  • Check edges — zoom in to verify blend quality
  • Match grain/noise — add film grain to match original

Current Setup

<!-- Tool: status -->

Projects

<!-- What they're editing -->

Preferences

<!-- Preferred tools, quality settings -->

Check technique files for detailed workflows.

Files

8 total
Select a file
Select a file to preview.

Comments

Loading comments…