xiangyu-cas/codex-canvas/canvas-quick-edit
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Run a user-described Quick Edit on a selected Codex-Canvas image and collect the result back onto the canvas.
Install
npx vskill@latest install xiangyu-cas/codex-canvas/canvas-quick-editSKILL.md
Codex-Canvas Quick Edit
Use this skill when the user invokes Quick Edit from Codex-Canvas or asks to perform an open-ended edit on a selected canvas image.
Behavior
- Treat the selected canvas image as the edit target.
- Quick Edit may provide one clean source image or two images. When two are attached, image 1 is the clean source and image 2 is an annotation board containing temporary arrows, masks, and edit notes around the source.
- Always use the clean source as the visual base. Use the annotation board only to locate regions and interpret the edit intent; do not preserve its surrounding board background or annotation UI.
- Use the user's optional Quick Edit text together with every arrow label, pencil mask, text note, color, and source-pixel location listed in the prompt. Arrow labels are explicit instructions for their arrow targets.
- Apply the requested edit according to the annotations, then remove all temporary arrows, strokes, boxes, label bubbles, and note text from the final image.
- Preserve the source image's aspect ratio, subject identity, layout, unmentioned visible text, and design intent unless an instruction explicitly asks to change them.
- If the source is a transparent layer, preserve native alpha, fine edges, partial opacity, and all subject colors. Inspect the actual imagegen schema and set
transparent_background: trueonly when that boolean argument is exposed. Never guess atransparentparameter or paint a checkerboard. If unsupported, report the limitation. Only an explicitly configuredCODEX_CANVAS_TRANSPARENCY_MODE=chroma-keyjob may use a uniform #ff00ff background; stop if the key conflicts with the subject instead of recoloring it. - Generate exactly one revised clean bitmap. Save the final selected output as a PNG under the job output directory provided by Codex-Canvas.
- Codex-Canvas will collect the output, verify real alpha and preserve native pixels (keying only in explicit compatibility mode), and replace the running placeholder to the right of the source image. It will preserve the original image and its annotation objects.
Do not ask follow-up questions from a background Quick Edit job. Make the most reasonable edit from the provided instruction.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/canvas-quick-edit/SKILL.md
Popularity
- 7-day trend score
- 0
Refreshed 3 Oct 2026, 25 days ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/xiangyu-cas/codex-canvas/canvas-quick-edit)