design-canvas-artifact
Generate Claude Design-style HTML design artifacts with visible sections, artboards, screen states, and visual variants for design review and AI iteration.
Skill by pipixia-labs
Chalk Labs
Need help deploying design-canvas-artifact?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pipixia-labs-design-canvas-artifact
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/design-canvas-artifact
What's inside
- Skill name
design-canvas-artifact- Description
- Generate Claude Design-style HTML design artifacts with visible sections, artboards, screen states, and visual variants for design review and AI iteration.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Design Canvas Artifact Use this private product-design skill when the user asks for UI design, product design, mobile app screens, web design mockups, dashboard design, visual variants, HTML design prototypes, or iterative design edits from screenshots/sketch annotations. ## Intent The deliverable is a reviewable design artifact, not a production application. The output should make design decisions visible: screens, states, variants, assumptions, visual systems, and tradeoffs should be placed on a canvas where the user and AI can compare them. ## Output Contract Generate one standalone HTML file that: - Embeds its own design canvas structure with sections and fixed-size artboards. - Defines clear local primitives such as `DesignCanvas`, `DCViewport`, `DCSection`, and `DCArtboard`, or equivalent names with the same meaning. - Uses transform-based canvas navigation for the main board: `translate3d(x, y, 0) scale(scale)`. - Supports trackpad pinch zoom, two-finger pan, and blank-space drag pan without browser-window scrollbars. - Posts host synchronization messages when JavaScript is enabled: `__dc_present` on mount and `__dc_zoom` when scale changes; listens for `__dc_set_zoom`. - Shows important screens and states side by side. - Uses stable section ids, artboard ids, labels, and component names. - Keeps visual variants aligned by information architecture while changing visual language. - Includes a compact brief or design-system artboard when useful. - Runs locally in a browser without backend services. - Avoids local absolute file paths. ## Design Rules - For mobile app work, prefer phone artboards around `393x852` unless the brief names another device. - For web or dashboard work, use explicit desktop/tablet/mobile artboards when responsive decisions matter. - Do not hide key states behind routing or tabs. The artifact should support design review at a glance. - Use lightweight demo interactions only when they clarify a state. Do not build complete business logic. - Hide scrollbars on the main canvas and artboards. Only keep internal scrolling when the designed screen itself needs to demonstrate scroll behavior. - Prefer structured reusable components for repeated screens so later AI edits can target the design cleanly. - If sketch annotations, screenshots, or exported tldraw images are present, interpret them as design feedback and modify the corresponding artboards. ## Code Generation Handoff When invoking the private design code generation agent, include: - The user request and selected assumptions. - The target surface and artboard sizes. - Required screens, states, and variants. - Selected visual direction or design system. - Relevant uploaded files, screenshots, sketch exports, or annotation notes. - Validation expectations such as "standalone HTML", "visible text", and "no local absolute paths".
From pipixia-labs/creative-claw, MIT.
More from pipixia-labs/creative-claw
- 0.569score
opencv
pipixia-labs
Use OpenCV for Python image processing, contour analysis, thresholding, filtering, geometric transforms, and basic video I/O.
SkillCFreshness: C★ 37Claude Code +9 - 0.569score
ui-ux-pro-max
pipixia-labs
UI/UX design intelligence.
SkillCFreshness: C★ 37Claude Code +9 - 0.569score
planning-with-files
pipixia-labs
Implements Manus-style file-based planning to organize and track progress on complex tasks.
SkillCFreshness: C★ 37Claude Code +9 - 0.566score
guizang-ppt-skill
pipixia-labs
生成"电子杂志 × 电子墨水"风格的横向翻页网页 PPT(单 HTML 文件),含 WebGL 流体背景、衬线标题 + 非衬线正文、章节幕封、数据大字报、图片网格等模板。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"horizontal swipe…
SkillCFreshness: C★ 37Claude Code +9 - 0.566score
imap-smtp-email
pipixia-labs
Read and send email via IMAP/SMTP.
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
style-brief-to-prompt
pipixia-labs
Use when the user describes a look, atmosphere, or aesthetic direction in natural language and needs it converted into a clean English prompt fragment or…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
expert-usage-guide
pipixia-labs
Use when the task depends on choosing the right Creative Claw expert, composing expert calls, or explaining the usage strategy for image, video, search…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
asset-to-script
pipixia-labs
Use when the user already has images or videos and wants a script, scene plan, or edit-ready narrative built around those existing assets instead of…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
creative-brief-to-storyboard
pipixia-labs
Use when the user gives a topic, campaign idea, product angle, or raw creative brief and needs it turned into a structured storyboard with hooks, scene beats…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
creative-workflow-router
pipixia-labs
Use when a creative request could map to several different skills or experts and you need to choose the smallest correct workflow, required inputs, and next…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
narration-to-visual-prompts
pipixia-labs
Use when the user already has script, narration, or storyboard text and needs aligned image or video prompts that are generation-ready and mapped one-to-one…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
pptx
pipixia-labs
Use this private PPT product skill when a .pptx/.potx PowerPoint file is involved as input, output, or user-uploaded template.
SkillCFreshness: C★ 37Claude Code +9
Signals
- Stars
- 37
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- May 9, 2026 (5 months ago)
- Last release
- Jun 2, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/pipixia-labs/creative-claw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pipixia-labs
- 0.569score
opencv
pipixia-labs
Use OpenCV for Python image processing, contour analysis, thresholding, filtering, geometric transforms, and basic video I/O.
SkillCFreshness: C★ 37Claude Code +9 - 0.569score
ui-ux-pro-max
pipixia-labs
UI/UX design intelligence.
SkillCFreshness: C★ 37Claude Code +9 - 0.569score
planning-with-files
pipixia-labs
Implements Manus-style file-based planning to organize and track progress on complex tasks.
SkillCFreshness: C★ 37Claude Code +9 - 0.566score
imap-smtp-email
pipixia-labs
Read and send email via IMAP/SMTP.
SkillCFreshness: C★ 37Claude Code +9 - 0.566score
guizang-ppt-skill
pipixia-labs
生成"电子杂志 × 电子墨水"风格的横向翻页网页 PPT(单 HTML 文件),含 WebGL 流体背景、衬线标题 + 非衬线正文、章节幕封、数据大字报、图片网格等模板。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"horizontal swipe…
SkillCFreshness: C★ 37Claude Code +9 - 0.564score
asset-to-script
pipixia-labs
Use when the user already has images or videos and wants a script, scene plan, or edit-ready narrative built around those existing assets instead of…
SkillCFreshness: C★ 37Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get design-canvas-artifact running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
design-canvas-artifact skill. Agent Mart. https://agentmart.dev/skills/pipixia-labs-design-canvas-artifact (last updated 2026-10-24)