ui-color-palette-penpot
Entry point for UI Color Palette workflows targeting Penpot.
Skill by a-ng-d
Chalk Labs
Need help deploying ui-color-palette-penpot?
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/a-ng-d-ui-color-palette-penpot
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: documents, design
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. Checked Oct 25, 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/ui-color-palette-penpot
What's inside
- Skill name
ui-color-palette-penpot- Description
- Entry point for UI Color Palette workflows targeting Penpot. Use to choose between tokens, styles, and board/document preview generation.
- License
- MIT
- Instructions
- 98 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- extract-source-colors.md · references/
- extract-styles-colors.md · references/
- generate-preview.md · references/
- generate-semantic-tokens.md · references/
- generate-styles.md · references/
- generate-tokens.md · references/
SKILL.md (first lines)
# UI Color Palette Penpot
Use this folder as the platform entry point for all **UI Color Palette → Penpot** workflows.
## Folder structure
- `SKILL.md` at the root is the platform index
- `references/` contains the detailed operational sub-skills
## Reuse rule
**Before calling any MCP tool**, check whether `PaletteData` is already present in the conversation context.
If it is, use it directly — **never call `get_palette` again**. Confirm to the user:
> Using the palette already built in this session. Generating Penpot artifacts now.
Only rebuild the palette if the user explicitly asks to change colors, preset, or themes.
---
## Structure-first rule
This platform skill is primarily a routing and orchestration layer.
The agent should:
1. identify whether the user needs tokens, styles, or preview first
2. choose the matching file in `references/`
3. normalize the palette payload for that workflow
4. only then translate the workflow into MCP or plugin API operations
Do not start from raw API calls. Start from the workflow structure.
## Available sub-skills
- `references/extract-source-colors.md` — extract solid fill colors from the current Penpot selection to seed a palette
- `references/extract-styles-colors.md` — extract colors from the Penpot local color library to seed a palette
- `references/generate-tokens.md` — generate or sync Penpot local **primitive** tokens and themed sets
- `references/generate-semantic-tokens.md` — generate or sync Penpot **semantic** token sets from `SystemData` (reference layer on top of primitives)
- `references/generate-styles.md` — generate or sync Penpot local color styles
- `references/generate-preview.md` — draw the palette as a swatch board on the Penpot canvas (canvas rendering only, not token/style export)
## Routing
Choose the sub-skill by user intent:
- “extract colors from selection”, “pick colors from selection”, “colors from Penpot” → `references/extract-source-colors.md`
- “extract colors from library”, “local colors”, “color library”, “seed from styles” → `references/extract-styles-colors.md`
- “tokens”, “primitive colors”, “theme tokens”, “Penpot token sets” → `references/generate-tokens.md`
- “semantic tokens”, “color system tokens”, “system token set”, `SystemData` present in context → `references/generate-semantic-tokens.md`
- “styles”, “local colors”, “style library”, “swatches” → `references/generate-styles.md`
- “full handoff”, “everything in Penpot”, “tokens + styles + preview” → primitives first (`references/generate-tokens.md`), semantics if `SystemData` is available (`references/generate-semantic-tokens.md`), then styles (`references/generate-styles.md`), then preview (`references/generate-preview.md`)
- “preview”, “board”, “document review”, “swatch board”, “canvas rendering”, “visual board” → `references/generate-preview.md`
When routing a `SystemData`-based workflow to `references/generate-semantic-tokens.md`, pass `SystemData` and `PaletteData` opaquely. The sub-skill:
- **First** ensures the palette's primitive token sets exist (mandatory prerequisite for reference resolution)
- Creates one semantic token set per theme, named `systemName/themeName` (or `systemName` for no-theme systems)
- Adds one **token** per entry in `SystemData.tokens`, named by joining `token.pathNames` with `.`
- Each token value references the primitive token as `{colorName_snake.shadeName}` (resolved via `token.refs[themeIndex].shadeId`)
- Excluded tokens (`isExcluded: true`) and unbound refs (`shadeId: null`) are skipped
## Platform API references
An agent should think in terms of the Penpot plugin/API surface, not only the plugin wrapper:
- **Local token catalog API**
- token sets
- tokens
- themes and theme groups
- **Local style/color API**
- local library colors
- style path, name, color, opacity
- **Document API**
- boards/documents
- node creation and update
- plugin data on current page/document
## MCP usage strategy
Use MCP or direct API calls as the execution layer, not as the skill structure.
- The root skill chooses the workflow.
- The reference file defines the expected inputs, transformations, and outputs.
- MCP/API calls execute the chosen workflow.
## Agent rule
The plugin bridge files are reference implementations. If the plugin action is unavailable, the agent should reproduce the same behavior directly through Penpot API requests.
---
## Recommended subagent
Delegate this skill to **`palette-transitioner`**.
The `palette-transitioner` agent normalizes `PaletteData` into the correct row model for Penpot (`tokenRows`, `styleRows`, `previewRows`), then routes execution through the appropriate Penpot sub-skill.From a-ng-d/claude-ui-color-palette, MIT.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 2, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Website
- ui-color-palette.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
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 ui-color-palette-penpot 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
ui-color-palette-penpot skill. Agent Mart. https://agentmart.dev/skills/a-ng-d-ui-color-palette-penpot (last updated 2026-10-24)