Agent skill

Excalidraw

by AlexAI-MCP in AlexAI-MCP/hermes-CCC

Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI.

MITAuto-check passedDevelopment

Install Excalidraw

skills CLI
$ npx skills add AlexAI-MCP/hermes-CCC --skill excalidraw -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AlexAI-MCP/hermes-CCC excalidraw --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/excalidraw .claude/skills/excalidraw && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
excalidraw
GitHub stars
135
Token cost
~2.3k tokens
SKILL.md length
1,145 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
MIT

At a glance

Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI.

  • Tasks that involve Diagrams
  • SKILL.md covers Purpose, Core Mental Model, MCP Integration and What To Ask For, plus 17 more sections
  • Reaches excalidraw.com

What it does

Excalidraw is an agent skill from AlexAI-MCP/hermes-CCC. Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Diagrams. It works with Excalidraw and Model Context Protocol. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

  • Tasks that involve Diagrams

Example prompts

  • “/excalidraw”

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • excalidraw.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Excalidraw loads about 2.3k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 1,145 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 1,145 words, ~2,346 tokens.

Download SKILL.mdSave it as .claude/skills/excalidraw/SKILL.md (or your agent's skills folder).
name
excalidraw
description
Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI.
version
1.0.0
author
hermes-CCC (ported from Hermes Agent by NousResearch)
license
MIT

Excalidraw

Purpose

  • Use this skill to create lightweight diagrams, sketches, and whiteboard-style visuals quickly.
  • Prefer Excalidraw when the output should feel hand-drawn, fast to edit, and easy to embed into notes or design docs.
  • This skill works well for architecture reviews, brainstorming, flowcharts, and teaching visuals.
  • In this environment, Excalidraw MCP tooling is already available.

Core Mental Model

  • Describe the diagram you want in plain language.
  • Claude can translate that description into an Excalidraw JSON scene specification.
  • The scene can then be rendered in a view, exported, saved as a checkpoint, or shared through Excalidraw.
  • Treat the JSON spec as the source of truth for reproducible diagram generation.

MCP Integration

  • Use mcp__claude_ai_excalidraw__create_view to generate or render a diagram view from a structured scene.
  • Use mcp__claude_ai_excalidraw__export_to_excalidraw to export the scene into a format compatible with Excalidraw workflows.
  • Use save_checkpoint to preserve an intermediate diagram state before large edits.
  • Use read_checkpoint to reload a previously saved scene when you need to continue, branch, or recover.
  • A good workflow is: describe -> generate JSON -> create view -> inspect -> checkpoint -> revise -> export.

What To Ask For

  • "Draw a system architecture diagram for a FastAPI app backed by Postgres and Redis."
  • "Create a flowchart for user sign-up with email verification."
  • "Sketch an ERD with users, teams, memberships, and permissions."
  • "Make a sequence diagram for browser -> API -> worker -> database."
  • "Turn this process into a whiteboard-style diagram with short labels and arrows."

Describe First, Then Refine

  • Start with the intent of the diagram, not low-level coordinates.
  • Include the major entities, the relationships, and the desired reading direction.
  • Mention whether you want a rough sketch, a cleaner box-and-arrow layout, or a board-like visual.
  • If the first result is too dense, ask for fewer labels or more spacing.
  • If the first result is too vague, specify grouping, order, and arrow directions.

Scene Building Blocks

  • rectangle: best for services, systems, containers, and grouped components.
  • ellipse: useful for external actors, start/end states, or soft conceptual nodes.
  • arrow: best for directional relationships, calls, control flow, and data movement.
  • line: useful for visual separators, boundaries, or non-directional links.
  • text: labels, notes, titles, annotations, and step numbers.
  • diamond: decision points in a flowchart or branching logic.

Common Diagram Types

System Architecture
  • Use rectangles for services, databases, queues, and external providers.
  • Use arrows to show request flow, event flow, and data movement.
  • Group related services into logical zones such as frontend, backend, storage, and third-party systems.
  • Add short text notes for protocols like HTTP, gRPC, Kafka, or WebSocket.
Flowchart
  • Use rectangles for actions.
  • Use diamonds for decisions.
  • Use arrows for the main control path.
  • Keep text short and action-oriented.
  • Prefer top-to-bottom or left-to-right consistency.
ERD
  • Use rectangles to represent tables or entities.
  • Put the entity name at the top and key fields below as text.
  • Use arrows or simple connecting lines to show relationships.
  • Label one-to-many or many-to-many edges with short text if needed.
  • Keep column lists focused on primary keys, foreign keys, and the fields relevant to the explanation.
Sequence Diagram
  • Use text labels for actors across the top.
  • Use vertical lines or repeated arrows to indicate message order.
  • Use arrows with labels like POST /login, enqueue job, or ACK.
  • Number key steps if the interaction is long.
  • Keep parallel flows separated visually rather than forcing too many crossing arrows.

Practical Prompt Patterns

  • "Create a whiteboard-style architecture diagram with six boxes and directional arrows."
  • "Make the frontend, API, and worker visually separated into columns."
  • "Use a decision diamond after payment validation."
  • "Add labels to arrows showing request type and payload."
  • "Keep the style sketchy and informal, suitable for an engineering design note."

Suggested JSON Planning

  • Think in terms of elements, labels, and relationships.
  • Define each node first.
  • Define the connectors second.
  • Add titles and notes last.
  • Keep IDs stable if you expect to revise the same diagram repeatedly.

Revision Workflow

  • Generate the initial scene from a natural-language description.
  • Render it with mcp__claude_ai_excalidraw__create_view.
  • Inspect for overlap, unclear labels, and missing relationships.
  • Save the working state with save_checkpoint.
  • Make incremental changes rather than regenerating from scratch if the structure is already mostly right.
  • If a revision goes sideways, recover the previous state using read_checkpoint.
Show full SKILL.md (459 more words)Show less

Checkpoints

  • Use save_checkpoint before major layout changes.
  • Use save_checkpoint before adding dozens of new elements.
  • Use read_checkpoint when you need to compare alternative diagram versions.
  • Use checkpoints to maintain a clean "baseline" for architecture documents.
  • Checkpoints are especially useful for iterative design sessions with multiple stakeholders.

Export Workflow

  • Use mcp__claude_ai_excalidraw__export_to_excalidraw when you want a portable Excalidraw artifact.
  • Export to Excalidraw format when the diagram should remain editable in the Excalidraw ecosystem.
  • Export as PNG when you need a static image for reports, PRs, slides, or issue comments.
  • Export as SVG when you need scalable vector output for documents or web embedding.
  • Prefer SVG when crisp text and resizable diagrams matter.

PNG vs SVG

  • PNG is easy to paste into chat, docs, and presentations.
  • PNG is better when consumers do not need to edit the figure.
  • SVG is better for documentation sites, architecture handbooks, and print-quality scaling.
  • SVG is easier to version in some documentation pipelines.
  • If unsure, export both.

Sharing

  • Excalidraw scenes can be shared via https://excalidraw.com/ workflows after export.
  • This is useful when collaborators want to tweak the drawing manually in the browser.
  • Excalidraw sharing is convenient for design reviews and async comments.
  • Keep exported scene files with the related document so the diagram is reproducible.

Style Guidance

  • Keep node labels short.
  • Avoid paragraphs inside shapes.
  • Use whitespace aggressively to reduce overlap.
  • Use consistent arrow direction when possible.
  • Put titles outside the main node grid.
  • Group annotations near the edge instead of in the center of the flow.

Good Defaults

  • System diagrams: left-to-right flow, clear zones, arrows labeled only when needed.
  • Flowcharts: top-to-bottom, one decision per diamond, one short phrase per node.
  • ERDs: entity name plus only important fields.
  • Sequence diagrams: ordered messages with minimal crossings.
  • Whiteboard sketches: rough but readable beats pixel-perfect precision.

Example Requests

text
Create a system architecture diagram for a RAG application with:
- Browser client
- FastAPI gateway
- Retrieval service
- Vector database
- Background worker
- External LLM API
Use rectangles for systems, arrows for data flow, and a handwritten whiteboard feel.
text
Create a flowchart for password reset:
- User requests reset
- System validates account
- If invalid, show error
- If valid, send email
- User clicks token link
- System verifies token
- If token expired, restart flow
- If valid, allow password update

When Excalidraw Fits Best

  • Early-stage architecture thinking
  • Fast diagrams during debugging
  • Design docs that need quick visuals
  • Workshop and brainstorming artifacts
  • Teaching and onboarding materials

When To Use Something Else

  • Use Mermaid when you need diagram-as-code in Markdown-first pipelines.
  • Use Graphviz when you need algorithmic layouts for large graphs.
  • Use presentation tools when heavy branding matters more than editability.
  • Use CAD or vector illustration tools when exact geometry matters.

Operational Tips

  • Keep diagram generation prompts close to the engineering language of the system.
  • Name services exactly as they appear in the codebase when possible.
  • Reuse checkpointed scenes for versioned architecture docs.
  • Export to SVG for stable documentation output.
  • Export to Excalidraw format when team members want browser editing.

Summary

  • Describe what you want as a diagram and Claude can generate the JSON spec.
  • Render scenes with mcp__claude_ai_excalidraw__create_view.
  • Export editable artifacts with mcp__claude_ai_excalidraw__export_to_excalidraw.
  • Save progress with save_checkpoint and recover with read_checkpoint.
  • Use Excalidraw for system architecture, flowcharts, ERDs, sequence diagrams, and sketch-style visuals.

© AlexAI-MCP, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/excalidraw of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Excalidraw next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Excalidraw compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Excalidraw this skillAlexAI-MCP/hermes-CCC135—~2.3kAutomated safety check: PassMIT
Excalidraw Skillyctimlin/mcp_excalidraw2.5k—~4.6kAutomated safety check: PassMIT
Excalidraw ArchitectBV-Venky/excalidraw-architect-mcp158—~2kAutomated safety check: PassMIT
Excalidraw Canvas Toolkitlingzhi227/agent-research-skills390—~3.8kAutomated safety check: PassNone
Excalidraw Diagram DesignBV-Venky/excalidraw-architect-mcp158—~1.6kAutomated safety check: PassMIT
Excalidraw MCP Diagrammingthomast1906/github-copilot-agent-skills202—~3.1kAutomated safety check: PassNone

Similar skills

  • Excalidraw Skill

    yctimlin/mcp_excalidraw

    Excalidraw canvas toolkit for creating, editing, and refining diagrams on a live canvas.

    2.5k GitHub stars~4.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Excalidraw Architect

    BV-Venky/excalidraw-architect-mcp

    Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more -…

    158 GitHub stars~2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Excalidraw Canvas Toolkit

    lingzhi227/agent-research-skills

    Draws and refines Excalidraw diagrams on a live canvas through MCP tools or a REST API, with screenshots, file import and export, snapshots and Mermaid conversion.

    390 GitHub stars~3.8k tokensUpdated 7 mo ago
    DevelopmentAuto-check passed
  • Excalidraw Diagram Design

    BV-Venky/excalidraw-architect-mcp

    Guide for structuring graph input (nodes and edges) for the Excalidraw Architect MCP tool to produce clean, readable diagrams.

    158 GitHub stars~1.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Excalidraw MCP Diagramming

    thomast1906/github-copilot-agent-skills

    Create and edit diagrams on a live Excalidraw canvas using the Excalidraw MCP server.

    202 GitHub stars~3.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Excalidraw Diagrams

    sammcj/agentic-coding

    A skill your agent uses when asked to create or update Excalidraw diagrams.

    162 GitHub stars~1.7k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from AlexAI-MCP/hermes-CCC

All 44 skills in this repo
  • GitHub Code Review

    AlexAI-MCP/hermes-CCC

    Review GitHub pull requests with a findings-first engineering mindset.

    135 GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • GitHub PR Workflow

    AlexAI-MCP/hermes-CCC

    Run a disciplined GitHub pull request workflow from branch creation through merge.

    135 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Memory

    AlexAI-MCP/hermes-CCC

    Manage durable project memory for Claude Code. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Route

    AlexAI-MCP/hermes-CCC

    Route Claude Code work by complexity, risk, and tool needs. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Skill

    AlexAI-MCP/hermes-CCC

    Create, improve, inventory, and audit Claude Code skills. An agent skill from AlexAI-MCP/hermes-CCC.

    135 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Hermes Traj

    AlexAI-MCP/hermes-CCC

    Capture Claude Code interaction trajectories in training-friendly formats.

    135 GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Excalidraw

What does Excalidraw do?

Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI. Excalidraw is an agent skill from AlexAI-MCP/hermes-CCC. Create and export diagrams with Excalidraw - whiteboard-style sketches, flowcharts, architecture diagrams via MCP or CLI.

When should I use Excalidraw?

Excalidraw fits situations like: tasks that involve Diagrams.

How do I install Excalidraw in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill excalidraw -a claude-code`. Or copy the skill folder (skills/excalidraw in AlexAI-MCP/hermes-CCC) into .claude/skills/excalidraw in your project. Claude Code loads it when a task matches its description.

How do I install Excalidraw in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill excalidraw -a codex`. Or copy the skill folder (skills/excalidraw in AlexAI-MCP/hermes-CCC) into .agents/skills/excalidraw in your project. Codex loads it when a task matches its description.

Can I use Excalidraw in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill excalidraw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/excalidraw, .gemini/skills/excalidraw, .github/skills/excalidraw and .opencode/skills/excalidraw in your project.

What does Excalidraw need to run?

SKILL.md names no scripts, command-line tools or credentials: Excalidraw is instructions for the agent only.

Does Excalidraw access the network?

SKILL.md names 1 domain. In commands or code: excalidraw.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Excalidraw safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Excalidraw use?

Excalidraw is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Excalidraw use?

About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Excalidraw?

Skills that share tags, products or a category with Excalidraw: Excalidraw Skill (yctimlin/mcp_excalidraw, 2.5k stars), Excalidraw Architect (BV-Venky/excalidraw-architect-mcp, 158 stars), Excalidraw Canvas Toolkit (lingzhi227/agent-research-skills, 390 stars) and Excalidraw Diagram Design (BV-Venky/excalidraw-architect-mcp, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Excalidraw?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.