Feishu Whiteboard Pro logo

Feishu Whiteboard Pro

Community
LcpMarvel
feishu-whiteboard-pro

Builds, revises, restyles, and critiques deliberate, editable Feishu / Lark whiteboards from content, references, existing SVGs, or live boards. Use for whiteboards, infographics, diagrams, system maps, timelines, decision boards, posters, and visual explainers that need factual fidelity, strong hierarchy, intentional composition, and evidence-based review rather than a generic grid of equal cards. Routes creation, revision, and critique through separate playbooks; commits to a content-and-design contract before drawing; validates deterministic SVG defects; renders and inspects the actual artifact; and uses an independent final reviewer for material deliveries.

Overview

PublisherLcpMarvel
Repositoryfeishu-whiteboard-pro
Skill namefeishu-whiteboard-pro
Stars
65
Forks
2
Bundled files
40
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 40 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by LcpMarvel on GitHub. Read the source before you install it.

Installation

Install the Feishu Whiteboard Pro AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LcpMarvel/feishu-whiteboard-pro/tree/master
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LcpMarvel/feishu-whiteboard-pro.git \
  .claude/skills/feishu-whiteboard-pro
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Feishu Whiteboard Pro in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Feishu Whiteboard Pro on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Feishu Whiteboard Pro is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Feishu Whiteboard Pro

Create real, editable Feishu SVG whiteboards with deliberate composition and verifiable content. The medium is intentionally narrow: one font, native rectangles/circles/connectors, no gradients, filters, opacity, or motion. Quality comes from truth, hierarchy, topology, rhythm, contrast, and air.

Core contract

  • The brief wins. Honor supplied brand, palette, reference, density, and style commitments. A default or anti-pattern warning cannot silently redirect a clear request.
  • Revision preserves; redesign replaces. A repair keeps content, relationships, geometry, and visual identity unless the user names an axis to change. A restyle changes the visual system, not the information architecture.
  • Visual authority is evidence. An existing board, SVG, screenshot, or explicit brief remains authoritative even without a separate design document.
  • Relationships are claims. Never invent an arrow, number, quotation, category, owner, status, or causal link to make the layout feel complete. Clearly label authored demonstration content.
  • Mechanical checks and design judgment stay separate. Scripts own measurable defects; the reviewer owns truth, reading path, hierarchy, balance, density, contrast in context, and alignment.
  • Verification is bounded. Inspect once, batch fixes, confirm once. Clear remaining deterministic failures, but do not reopen an unlimited taste loop.

Setup

Resolve <skill-dir> to the directory containing this SKILL.md; keep the working directory at the user's project. All bundled references and scripts resolve from <skill-dir>.

Run bash <skill-dir>/scripts/preflight.sh once before local rendering. Node 20+ is required. The whiteboard CLI runs through npx and may need network access on first use.

Feishu authentication is required only for publishing. Before writing a live board, run bash <skill-dir>/scripts/preflight.sh --publish. If publishing is unavailable, continue with the local SVG and tight PNG; do not discard a valid local deliverable.

Route the request

Read RULES.md for every build or edit, then load exactly one workflow:

RequestWorkflowDefault authority
New board or replacement compositionreferences/create.mdUser content, references, and the new board contract
Repair, restructure, restyle, or simplify an existing boardreferences/revise.mdExisting artifact plus the explicitly changed axes
Review, diagnose, or approve a boardreferences/critique.mdCurrent evidence; read-only unless fixes were requested

Load supporting references only when the selected workflow needs them:

If a request is ambiguous between creating and revising, inspect the supplied artifact first. Ask a question only when choosing the wrong authority would materially change the result.

Build and verify

For SVG work:

  1. Start from the matching examples/*.svg when its topology fits. Replace content and recheck old arrowheads and meta text rather than trusting the example blindly.

  2. Run the deterministic check:

    bash
    node <skill-dir>/scripts/fit-check.mjs <dir>/diagram.svg
  3. Render and inspect the tight local image:

    bash
    npx -y @larksuite/whiteboard-cli@^0.2.11 \
      -i <dir>/diagram.svg -o <dir>/diagram.png -f svg
  4. Batch visible fixes, rerun fit-check, and make one confirmation render. Use node <skill-dir>/scripts/fit-check.mjs --json <dir>/diagram.svg when passing evidence to another process.

  5. For a material delivery, use the fresh read-only reviewer in agents/whiteboard-finish-reviewer.md. Pass the original request, fact/design contract, SVG, local PNG, checker output, and any real Feishu evidence.

Publish and deliver

Follow RULES.md for exact Feishu creation, update, and query commands. Publishing changes external state, so do it only when the user requested a live board or supplied a target to update.

Deliver the Feishu document link when publishing succeeded, plus the local diagram.svg and tight diagram.png. The square Feishu export is verification evidence, not the share image. If publishing is unavailable, deliver the local artifacts and the precise authentication step still required.

Repository files

  • RULES.md — verified medium constraints and publish commands.
  • references/ — create, revise, and critique playbooks; load one per request.
  • COMPOSITION.md — spacing, type scale, archetypes, and anti-reflex guidance.
  • CRITIQUE.md — truth gate, five visual axes, and bounded review flow.
  • CATALOG.md — generated palette index.
  • templates/ — curated palettes and the optional generation recipe.
  • examples/ — editable gold-standard SVG starting points and renders.
  • scripts/fit-check.mjs — deterministic medium and untransformed-geometry checker with text and JSON output.
  • scripts/check-repo.mjs — offline repository regression check.
  • scripts/preflight.sh — local and publish readiness check.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Feishu Whiteboard Pro AI skill do?

Builds, revises, restyles, and critiques deliberate, editable Feishu / Lark whiteboards from content, references, existing SVGs, or live boards. Use for whiteboards, infographics, diagrams, system maps, timelines, decision boards, posters, and visual explainers that need factual fidelity, strong hierarchy, intentional composition, and evidence-based review rather than a generic grid of equal cards. Routes creation, revision, and critique through separate playbooks; commits to a content-and-design contract before drawing; validates deterministic SVG defects; renders and inspects the actual a...

Why use Feishu Whiteboard Pro on TypingMind?

Because you install it once and use it with any model. Feishu Whiteboard Pro is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Feishu Whiteboard Pro in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LcpMarvel/feishu-whiteboard-pro/tree/master. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Feishu Whiteboard Pro?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Feishu Whiteboard Pro?

As many as you like. As long as a model supports skills, you can use Feishu Whiteboard Pro with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Feishu Whiteboard Pro AI skill free?

It is published on GitHub by LcpMarvel. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇