Not in the top 1,000 by GitHub stars
aiatelie/ai-atelie
Local-first, open-source alternative to Anthropic's Claude Design. MIT-licensed, BYO agent CLI — Claude Code, Kimi, Codex, or any SDK-compatible model. Composable skills · three edit paths · designs as plain HTML/JSX/CSS folders · run locally, no cloud round-trip. Generate banners, thumbnails, websites, animations, design systems.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/animated-video/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/create-design-system/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/design-aesthetic-presets/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/design-critique/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/design-md-author/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/export/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/frontend-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/handoff-to-claude-code/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/interactive-prototype/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/make-tweakable/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/save-as-standalone-html/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
skills/send-to-canva/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3175d46b9171
No earlier version was observed for comparison.
Verified commit 3175d46b9171edfabf4174c3227a67194b11eae3
git clone --filter=blob:none --no-checkout https://github.com/aiatelie/ai-atelie.git .hotskills/aiatelie-ai-atelie && git -C .hotskills/aiatelie-ai-atelie checkout --detach 3175d46b9171edfabf4174c3227a67194b11eae3
# Copy each selected skill directory from .hotskills/aiatelie-ai-atelie into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/aiatelie/ai-atelie.git .hotskills/aiatelie-ai-atelie && git -C .hotskills/aiatelie-ai-atelie checkout --detach 3175d46b9171edfabf4174c3227a67194b11eae3
# Copy each selected skill directory from .hotskills/aiatelie-ai-atelie into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/aiatelie/ai-atelie.git .hotskills/aiatelie-ai-atelie && git -C .hotskills/aiatelie-ai-atelie checkout --detach 3175d46b9171edfabf4174c3227a67194b11eae3
# Copy each selected skill directory from .hotskills/aiatelie-ai-atelie into .opencode/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- animated-video
skills/animated-video - create-design-system
skills/create-design-system - design-aesthetic-presets
skills/design-aesthetic-presets - design-critique
skills/design-critique - design-md-author
skills/design-md-author - export
skills/export - frontend-design
skills/frontend-design - handoff-to-claude-code
skills/handoff-to-claude-code - interactive-prototype
skills/interactive-prototype - make-tweakable
skills/make-tweakable - save-as-standalone-html
skills/save-as-standalone-html - send-to-canva
skills/send-to-canva
How it works
animated-video
When your agent uses it
Timeline-based motion design — animated explainer-style HTML artifacts where time advances and elements enter or exit on a schedule. Reach for this when motion IS the design, not a flourish on a static layout.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
1,660 tokensWhen the skill is activated
Reference documents
4,511 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- When this skill does NOT apply
- Setup
- Fallback
- Defaults
- Common patterns
- Anti-patterns
- Pairs naturally with
Files
SKILL.mdcore7,116 bytes../export/SKILL.mddoc8,852 bytes../interactive-prototype/SKILL.mddoc7,093 bytes../make-tweakable/SKILL.mddoc2,510 bytes
Read SKILL.md
# Animated video
Timeline-based motion design — animated explainer-style HTML artifacts where time advances and elements enter or exit on a schedule. Distinct from interactive prototypes (which are state-driven, not time-driven) and from CSS micro-interactions (which decorate a static layout instead of carrying it).
## When to use this skill
- The user asks for "an animated explainer", "a video", "an animation", "a sequence", "a kinetic title".
- The design's value is mostly in the *timing* (an idea unfolding over seconds, choreographed entries, scene transitions).
- The output will end up exported as a video clip (often via the `export` skill's video capability — MP4 / WebM / Lottie).
- 1920×1080 hero animations, lower-third graphics for video editing, intro/outro sequences, animated logos.
## When this skill does NOT apply
- **Static layout with hover/scroll micro-interactions** → use CSS transitions inside an interactive prototype (see [`interactive-prototype`](../interactive-prototype/SKILL.md)) or directly in the page's CSS.View the complete source on GitHubcreate-design-system
When your agent uses it
Skill to use if user asks you to create a design system or UI kit
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
277 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What we know about it
- Working theory of the body (to be replaced)
- TODO
Files
SKILL.mdcore1,235 bytes
Read SKILL.md
# Create design system
> ⚠<U+FE0F> **STUB** — this is a working theory of the skill body. Replace as the implementation is refined.
## What we know about it
- It's the skill to invoke when the user asks for a design system or UI kit.
- The skill pairs with an asset-registration mechanism that groups outputs into: **Type, Colors, Spacing, Components, Brand** — that's the section taxonomy this skill produces against.
## Working theory of the body (to be replaced)
1. Ask questions (typography direction, palette mood, scale, density, what components are in scope).
2. Produce a tokens file (`tokens.css` or similar) with CSS custom properties for: type scale, color ramps, spacing scale, radii, shadows.
3. Produce one HTML preview file per group (Type, Colors, Spacing, Components, Brand), each registered with `register_assets({ asset, group, viewport })`.View the complete source on GitHubdesign-aesthetic-presets
When your agent uses it
Pick one of eleven named aesthetic directions before writing any code, then execute it with discipline. Forces commitment to a specific look so output stops converging on the AI-default white-purple-Inter aesthetic.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
2,406 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to use
- The presets
- When this skill does NOT apply
- Anti-patterns
Files
SKILL.mdcore9,328 bytes
Read SKILL.md
# Aesthetic presets
A menu of eleven named aesthetic directions, each with concrete CSS hooks, font roles, and motion vocabulary. Use this skill when the user asks for "something distinctive" without naming the direction, or when `frontend-design` fired and you need to pin down which direction to execute.
## How to use
1. **Pick one preset** that fits the brief. State the choice in one sentence to the user before writing code. ("Going with brutalist — heavy black borders, cold neutrals, monospace display.")
2. **Don't blend.** Two presets at once dilutes both. If the brief seems to mix, ask which dominant.
3. **Execute the recipe.** Each preset below names the type vocabulary, palette spine, motion register, and detail moves. Apply them — don't shop around.
4. **Add one signature.** The list gives you the floor; pick one detail (a custom cursor, a specific micro-interaction, an unexpected proportion) that's yours.
## The presets
### 1. Swiss / Bauhaus minimalismView the complete source on GitHubdesign-critique
When your agent uses it
Run a structured anti-slop audit on the design just produced before declaring done. Catches the recognizable AI-default patterns (Tailwind indigo, two-stop trust gradients, emoji-as-icons, generic display fonts, rounded-card-with-left-border, and 20+ more) so they can be fixed before the user sees them.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
2,005 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- How the audit runs
- P0 — cardinal sins (must fix)
- P1 — soft tells (compounds; fix when ≥2)
- P2 — polish opportunities (mention but don't block)
- Reporting format
- Anti-patterns for this skill
Files
SKILL.mdcore8,000 bytes
Read SKILL.md
# Design critique
A structured audit pass run AFTER the design is generated, BEFORE declaring the work done. The goal: catch the recognizable AI-default patterns (purple gradients, Tailwind indigo, emoji-as-icons, container soup) before the user has to call them out.
## When to use
Run this skill at the end of any non-trivial design generation:
- After `frontend-design` produces a new page or component
- After applying an aesthetic preset and before showing the result
- When the user says "audit this", "is this slop?", "make it less generic"
- Before any final export from the canvas
Skip when:
- The design is a tiny tweak (single property, copy edit) — not worth the audit overheadView the complete source on GitHubdesign-md-author
When your agent uses it
Read or write a Google-spec DESIGN.md at the project root — the cross-tool aesthetic spec that grounds every prompt in this project. Use when the user asks to capture, update, or import a design system, or when starting a project that should have a documented aesthetic direction.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,871 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- The schema (Google spec)
- Authoring flows
- Reading flows
- Hard rules
- Compatibility
- Lint & validate
- Anti-patterns
Files
SKILL.mdcore7,649 bytesSKILL.mdcore7,649 bytesSKILL.mdcore7,649 bytes
Read SKILL.md
# DESIGN.md author
Read, write, or update a `DESIGN.md` at the project root. `DESIGN.md` is the Google-Labs-published cross-tool spec for documenting a design system: tokens, typography, components, motion, do's-and-don'ts. When present, it grounds every subsequent prompt in this project — the agent reads it as project-context before generating UI.
## When to use
- The user asks to "set up the design system", "create a DESIGN.md", "import this design system", "capture our look".
- A project doesn't have a `DESIGN.md` yet and the user wants to commit to a direction once instead of re-deciding per prompt.
- The user wants to import a DESIGN.md from elsewhere (a Stitch export, a community gallery, another project).
- The user wants to update tokens, typography rules, or component specs declared in the project's existing `DESIGN.md`.
Skip when:
- The user is generating a one-off design — `DESIGN.md` is for projects with continuity, not single artifacts.
- The change is implementation, not specification. (Component code changes go through `frontend-design`; the DESIGN.md only changes when the *spec* shifts.)View the complete source on GitHubexport
When your agent uses it
Export a selected element from the canvas as PNG, JPEG, OGraf bundle, Lottie, or video. Saves to the project's exports/ folder; the chat renders the result inline as an artifact card.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,205 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical: do not narrate file creation
- Capabilities
- Required args (every export)
- Naming
- Format picker — short rubric
- OGraf export — always elicit first
- Defaults
- Feedback loop
- When NOT to use this skill
- Tips
Files
SKILL.mdcore8,852 bytes
Read SKILL.md
# Export
The user wants to take an element from the active design canvas and save it for use in another tool — usually a video editor (DaVinci Resolve, FCP, Premiere, CapCut), sometimes a presentation tool. Pick the right format, call the matching capability, **then write a single short sentence**.
## Critical: do not narrate file creation
The host renders an **ArtifactCard** inline in the chat for every successful export — thumbnail + filename + size + Download / Preview / Discuss buttons. You don't need to tell the user what you saved or where it landed; the card already shows that. Your reply is a *one-sentence header* explaining the choice, not a status report.
**Bad** — narrates what the user can already see:
> I've saved the cat banner as a PNG file at exports/cat-banner.png. The file is 2.3MB and 3840×2160 pixels with a transparent background. You can download it using the link.
**Good** — confirms intent + invites iteration:
> Cat banner as a 2× transparent PNG — should work straight on a Resolve overlay track.
View the complete source on GitHubfrontend-design
When your agent uses it
Aesthetic direction for designs outside an existing brand system
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
1,056 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- Commit before coding
- Aesthetic guidelines
- What to avoid — and what to do instead
- Match the code to the vision
Files
SKILL.mdcore5,244 bytes
Read SKILL.md
# Frontend design
Build production-grade frontend interfaces with a bold, distinctive point of view. The user provides requirements — a component, a page, an interactive experience — and the job is to design and build something that's not just competent, but striking and memorable.
## When to use this skill
Use this when there's no existing brand or design system to defer to. Without explicit aesthetic direction the model converges on the same look every time: white background, purple gradient, Inter, rounded cards, system-blue accent. Break that default by committing to a clear direction up front and executing it with precision.
If the user has provided a `DESIGN.md` at the project root, follow that direction first. This skill is the fallback when no spec is present.
## Commit before coding
Before writing any code, decide:
View the complete source on GitHubhandoff-to-claude-code
When your agent uses it
Developer handoff package
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
244 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does
- Working theory of the body (to be replaced)
- TODO
Files
SKILL.mdcore1,042 bytes
Read SKILL.md
# Handoff to Claude Code
> ⚠<U+FE0F> **STUB** — this is a working theory of the skill body. Replace as the implementation is refined.
## What it does
Packages the current design + all its supporting files into a bundle a developer can drop into Claude Code (or any IDE/agent) to implement against.
## Working theory of the body (to be replaced)
1. Inventory: which HTML files, components, tokens, and assets are part of the deliverable.
2. Generate a `HANDOFF.md` at the project root summarizing:
- Scope of the design
- Tokens / variables in useView the complete source on GitHubinteractive-prototype
When your agent uses it
Build a clickable, hi-fi prototype of a product or flow — not a wireframe, not a static mock. The user can navigate, toggle states, and feel the interaction. Reach for this whenever the design has flows, multi-screen states, or many-option situations.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,713 tokensWhen the skill is activated
Reference documents
3,309 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- When this skill does NOT apply
- Build with React + Babel (inline JSX)
- Starter components to drop in
- Build process
- Defaults
- Anti-patterns
Files
../animated-video/SKILL.mddoc7,116 bytes../frontend-design/SKILL.mddoc5,244 bytesSKILL.mdcore7,093 bytes../make-tweakable/SKILL.mddoc2,510 bytes
Read SKILL.md
# Interactive prototype
A clickable, hi-fi prototype of a product or flow — not a wireframe, not a static mock. The user can navigate, toggle states, and feel the interaction. Use this whenever the design has flows, multi-screen states, or many-option situations.
## When to use this skill
- The user asks for "an app", "a flow", "a multi-step thing", "let me see it working", "let me click around".
- The design has stateful behavior (toggles, modals, multi-screen navigation, form validation flows).
- There are 3+ screens that connect.
- The user needs to demo interactions to a stakeholder.
## When this skill does NOT apply
- **Single static surface** (a banner, a poster, a thumbnail, a single-screen marketing page) → that's purely visual; use the existing DesignCanvas with one or more `<DCArtboard>` instead.View the complete source on GitHubmake-tweakable
When your agent uses it
Add in-design tweak controls
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
593 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Protocol
- Persisting state
- Tips
Files
SKILL.mdcore2,510 bytes
Read SKILL.md
# Tweaks
The user can toggle **Tweaks** on/off from the toolbar. When on, show additional in-page controls that let the user tweak aspects of the design — colors, fonts, spacing, copy, layout variants, feature flags, whatever makes sense. **You design the tweaks UI**; it lives inside the prototype. Title your panel/window **"Tweaks"** so the naming matches the toolbar toggle.
## Protocol
- **Order matters: register the listener before you announce availability.** If you post `__edit_mode_available` first, the host's activate message can land before your handler exists and the toggle silently does nothing.
- **First**, register a `message` listener on `window` that handles:
`{type: '__activate_edit_mode'}` → show your Tweaks panel
`{type: '__deactivate_edit_mode'}` → hide it
- **Then** — only once that listener is live — call:
`window.parent.postMessage({type: '__edit_mode_available'}, '*')`
This makes the toolbar toggle appear.View the complete source on GitHubsave-as-standalone-html
When your agent uses it
Single self-contained file that works offline
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
337 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does
- Required input
- Workflow
- Notes
- TODO
Files
SKILL.mdcore1,436 bytesSKILL.mdcore1,436 bytesSKILL.mdcore1,436 bytes
Read SKILL.md
# Save as standalone HTML
> ⚠<U+FE0F> **STUB** — this is a working theory of the skill body. The wrapped tool (`super_inline_html`) gives the contract.
## What it does
Bundles an HTML file and all its referenced assets (images, CSS, JS, fonts, `ext-resource-dependency` meta tags) into a single self-contained HTML file that works offline. Runs a deterministic browser-side bundler.
## Required input
The source HTML **must** contain a `<template id="__bundler_thumbnail">` with a simple, colorful, iconographic SVG preview (30% padding on each side). This is shown:
- as a splash while the bundle unpacks, and
- as the no-JS fallback.View the complete source on GitHubsend-to-canva
When your agent uses it
Export as an editable Canva design
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
225 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does
- Working theory of the body (to be replaced)
- TODO
Files
SKILL.mdcore983 bytes
Read SKILL.md
# Send to Canva
> ⚠<U+FE0F> **STUB** — this is a working theory of the skill body. The supporting tool `get_public_file_url` returns a short-lived (~1h) public URL for project files, useful when an external service (e.g. Canva import) needs to fetch a project file by URL.
## What it does
Hands the current design off to Canva as an editable design.
## Working theory of the body (to be replaced)
1. Identify the target HTML file (deck or design).
2. Get a public URL: `get_public_file_url({ project_relative_file_path })`.
3. Construct/open a Canva import URL pointing at it (the actual import endpoint is Canva-side; needs verification).
4. Show the user a download/open card.View the complete source on GitHubSkills included
- animated-video
- create-design-system
- design-aesthetic-presets
- design-critique
- design-md-author
- export
- frontend-design
- handoff-to-claude-code
- interactive-prototype
- make-tweakable
- save-as-standalone-html
- send-to-canva
Repository facts
- License
- MIT
- Created
- May 5, 2026
- Last pushed
- Jun 3, 2026
- Forks
- 0
- Open issues
- 40
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
skills/design-md-author/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-md-author/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/save-as-standalone-html/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/save-as-standalone-html/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 17 network referencesin 4 files: frontend-design/SKILL.md:6 skills/interactive-prototype/SKILL.md:32 design-md-author/SKILL.md:6 and 1 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 17 signals by file
skills/animated-video/SKILL.md
- Network accessline 52
Only fall back to a third-party motion library if the starter genuinely can't express the effect. The acceptable fallback is [Popmotion](https://unpkg.com/popmotion@11.0.5/dist/popmotion.min.js) — small, no dependencies, well-documented spr - Network accessline 52
Only fall back to a third-party motion library if the starter genuinely can't express the effect. The acceptable fallback is [Popmotion](https://unpkg.com/popmotion@11.0.5/dist/popmotion.min.js) — small, no dependencies, well-documented spr
skills/design-md-author/SKILL.md
skills/frontend-design/SKILL.md
- Network accessline 6
body_status: reconstructed sources: - https://claude.com/blog/improving-frontend-design-through-skills - Network accessline 6
body_status: reconstructed sources: - https://claude.com/blog/improving-frontend-design-through-skills - Network accessline 7
sources: - https://claude.com/blog/improving-frontend-design-through-skills --- - Network accessline 7
sources: - https://claude.com/blog/improving-frontend-design-through-skills --- - Network accessline 8
- https://claude.com/blog/improving-frontend-design-through-skills - Network accessline 8
- https://claude.com/blog/improving-frontend-design-through-skills
skills/interactive-prototype/SKILL.md
- Network accessline 32
<script src="https://unpkg.com/react@18.3.1/umd/react.development.js" integrity="sha384-hD6/rw4ppMLGNu3tX5cjIb+uRZ7UkRJ6BPkLpg4hAu/6onKUg4lLsHAs9EBPT82L" crossorigin="anonymous"></script> - Network accessline 32
<script src="https://unpkg.com/react@18.3.1/umd/react.development.js" integrity="sha384-hD6/rw4ppMLGNu3tX5cjIb+uRZ7UkRJ6BPkLpg4hAu/6onKUg4lLsHAs9EBPT82L" crossorigin="anonymous"></script> - Network accessline 33
<script src="https://unpkg.com/react-dom@18.3.1/umd/react-dom.development.js" integrity="sha384-u6aeetuaXnQ38mYT8rp6sbXaQe3NL9t+IBXmnYxwkUI2Hw4bsp2Wvmx4yRQF1uAm" crossorigin="anonymous"></script> - Network accessline 33
<script src="https://unpkg.com/react-dom@18.3.1/umd/react-dom.development.js" integrity="sha384-u6aeetuaXnQ38mYT8rp6sbXaQe3NL9t+IBXmnYxwkUI2Hw4bsp2Wvmx4yRQF1uAm" crossorigin="anonymous"></script> - Network accessline 34
<script src="https://unpkg.com/@babel/standalone@7.29.0/babel.min.js" integrity="sha384-m08KidiNqLdpJqLq95G/LEi8Qvjl/xUYll3QILypMoQ65QorJ9Lvtp2RXYGBFj1y" crossorigin="anonymous"></script> - Network accessline 34
<script src="https://unpkg.com/@babel/standalone@7.29.0/babel.min.js" integrity="sha384-m08KidiNqLdpJqLq95G/LEi8Qvjl/xUYll3QILypMoQ65QorJ9Lvtp2RXYGBFj1y" crossorigin="anonymous"></script>
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 17 facts
- Network access in prose of the SKILL.mdanimated-video/SKILL.md:52Low confidence
- Network access in prose of the SKILL.mdskills/animated-video/SKILL.md:52Low confidence
- Network access in the frontmatter of the SKILL.mddesign-md-author/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mddesign-md-author/SKILL.md:7Low confidence
- Network access in the frontmatter of the SKILL.mddesign-md-author/SKILL.md:8Low confidence
- Network access in the frontmatter of the SKILL.mdfrontend-design/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdskills/frontend-design/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdfrontend-design/SKILL.md:7Low confidence
- Network access in the frontmatter of the SKILL.mdskills/frontend-design/SKILL.md:7Low confidence
- Network access in the frontmatter of the SKILL.mdfrontend-design/SKILL.md:8Low confidence
- Network access in the frontmatter of the SKILL.mdskills/frontend-design/SKILL.md:8Low confidence
- Network access in code of the SKILL.mdskills/interactive-prototype/SKILL.md:32High confidence
- Network access in code of the SKILL.mdinteractive-prototype/SKILL.md:32High confidence
- Network access in code of the SKILL.mdskills/interactive-prototype/SKILL.md:33High confidence
- Network access in code of the SKILL.mdinteractive-prototype/SKILL.md:33High confidence
- Network access in code of the SKILL.mdskills/interactive-prototype/SKILL.md:34High confidence
- Network access in code of the SKILL.mdinteractive-prototype/SKILL.md:34High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/settings.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/animated-video/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/animated-video/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/animated-video/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Native | Manifest opencode.json | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.