Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 12+ diagram types with fully automatic layout.
npx skills add https://github.com/Agents365-ai/mermaid-skill --skill mermaid-skill
Generate .mmd text files and export to PNG/SVG/PDF using mmdc (local) or Kroki API (no install).
Key advantage: Text-based syntax with fully automatic layout — no x/y coordinates needed.
Use this skill for: diagrams-as-code with automatic layout (flowchart, sequence, class, state, ER, gantt, mindmap, architecture) — text source that lives in git and embeds in Markdown.
Do NOT use it — route elsewhere — for:
Option A: Local (mmdc) — also needs a headless Chrome (mmdc renders via Puppeteer)
npm install -g @mermaid-js/mermaid-cli
npx puppeteer browsers install chrome-headless-shell # required — mmdc has no bundled browser
mmdc --version
> mmdc --version succeeds even with no Chrome installed, but every export then fails with Could not find Chrome. Install the browser above (or set PUPPETEER_EXECUTABLE_PATH to a system Chrome). If you can't, use Kroki (Option B) — it needs no browser.
Option B: Kroki API (no install)
curl --version # Just need curl
mmdc --version and confirm a headless Chrome is installed (a bare --version pass does NOT mean export works); fall back to Kroki if either is missing.mmd file to diskmmdc or Kroki API to produce PNG/SVG/PDF.mmd edit per request, re-export until approved (5-round safety valve). See Review Loop below.NEVER export a diagram without validating first.
# Validate with mmdc (local)
mmdc -i diagram.mmd -o /tmp/test.png 2>&1
# Validate with Kroki (if mmdc unavailable)
curl -s -X POST -H "Content-Type: text/plain" --data-binary @diagram.mmd https://kroki.io/mermaid/svg -o /tmp/test.svg && echo "Valid" || echo "Invalid"
# If error, fix the .mmd file and validate again
# Only proceed to export after validation passes
Common validation errors:
->> for sequence, --> for flowchart)> A Could not find Chrome (or puppeteer) error from mmdc is a setup problem, not a diagram error — the .mmd may be perfectly valid. Install the browser (see Prerequisites) or validate via Kroki instead of "fixing" correct syntax.
Validation (above) only proves the syntax is legal — it says nothing about whether the rendered diagram is readable. After exporting, use the agent's vision capability to read the PNG and catch what automatic layout can't prevent. Mermaid positions everything itself, so the failures here are about content and readability, not overlaps:
| Check | What to look for | Fix |
|---|---|---|
| Label truncation | Node / edge text clipped or cut off | Shorten the label, or wrap it with <br/> |
| Cramped, unreadable density | Too many nodes crammed together; tangled lines | Flip direction (TD↔LR), split into subgraphs, or reduce nodes |
| Wrong orientation / aspect | Diagram far too wide or too tall to read | Change flowchart TD↔LR (or set direction in class/state) |
| Edge spaghetti | Many edges crossing, hard to follow | Reorder node declarations so connected nodes sit adjacent; group with subgraph |
| Wrong diagram type | Type doesn't suit the content (e.g. flowchart for a timeline) | Switch type (gantt, sequenceDiagram, stateDiagram-v2, …) |
| Low contrast | Text blends into the node fill | Adjust classDef / theme so text contrasts the fill |
After self-check, show the exported image and collect feedback. Apply the minimal .mmd edit for each request, then re-validate and re-export:
| User request | Edit action |
|---|---|
| Change a label | Edit the node / edge text in the .mmd |
| Add / remove a node or edge | Add or delete the matching line |
| Change a color | Add / adjust a classDef and class <node> <className> |
| Change layout direction | Swap TD↔LR (flowchart) or set direction (class / state) |
| Restructure / group | Wrap related nodes in a subgraph, or regenerate |
diagram.mmd / diagram.png each round — don't create v1, v2, …| Type | Keyword | Use for |
|------|---------|---------|
| Flowchart | flowchart TD/LR | processes, pipelines, decisions |
| Sequence | sequenceDiagram | API calls, message passing |
| Class | classDiagram | OOP models, data structures |
| ER | erDiagram | database schemas |
| State | stateDiagram-v2 | state machines, lifecycle |
| Gantt | gantt | project timelines |
| Pie | pie | proportions |
| Git Graph | gitGraph | branch strategies |
| C4 Context | C4Context | high-level system context |
| Architecture | architecture-beta | cloud / CI/CD service layouts |
| Mind Map | mindmap | topic breakdowns |
| User Journey | journey | user-experience flows |
Flowchart: See reference/FLOWCHART.md
Sequence: See reference/SEQUENCE.md
Class & ER: See reference/CLASS-ER.md
Architecture: See reference/ARCHITECTURE.md
Other types: See reference/OTHER-TYPES.md
User prompt:
> Create a sequence diagram for JWT authentication
Generated .mmd:
sequenceDiagram
participant C as Client
participant G as API Gateway
participant A as Auth Service
participant D as Database
C->>G: POST /login {email, password}
G->>A: validate(credentials)
A->>D: SELECT user WHERE email=?
D-->>A: user record
A-->>A: verify password hash
A-->>G: 200 OK + JWT token
G-->>C: {token: "eyJhbG..."}
Output files: auth-flow.mmd + auth-flow.png
User prompt:
> Draw an e-commerce microservices architecture
Generated .mmd:
flowchart TD
subgraph Clients
M[Mobile App]
W[Web App]
end
GW[API Gateway]
subgraph Services
US[User Service]
OS[Order Service]
PS[Product Service]
PAY[Payment Service]
end
subgraph Data
UDB[(User DB)]
ODB[(Order DB)]
PDB[(Product DB)]
REDIS[(Redis Cache)]
end
M & W --> GW
GW --> US & OS & PS & PAY
US --> UDB
OS --> ODB
PS --> PDB
PAY --> REDIS
Output files: ecommerce-arch.mmd + ecommerce-arch.png
User prompt:
> Show order lifecycle states
Generated .mmd:
stateDiagram-v2
[*] --> Pending : order created
Pending --> Confirmed : payment success
Pending --> Cancelled : timeout/cancel
Confirmed --> Shipped : dispatched
Shipped --> Delivered : received
Delivered --> [*]
Cancelled --> [*]
Output files: order-states.mmd + order-states.png
User prompt:
> Draw a simple service architecture for an API
Generated .mmd:
architecture-beta
group api(cloud)[API]
service gateway(internet)[Gateway] in api
service db(database)[Database] in api
service cache(disk)[Cache] in api
gateway:R --> L:db
gateway:B --> T:cache
Output files: api-architecture.mmd + api-architecture.png
Requires mmdc installed locally. Best for offline use.
# PNG (recommended: 2048px wide, white background)
mmdc -i diagram.mmd -o diagram.png -w 2048 --backgroundColor white
# PNG with theme — valid -t values: default | dark | neutral | forest
# (`base` is NOT a valid -t value; it only works inside a %%{init: {'theme':'base'}}%% directive)
mmdc -i diagram.mmd -o diagram.png -w 2048 --backgroundColor white --theme neutral
# SVG
mmdc -i diagram.mmd -o diagram.svg
# PDF
mmdc -i diagram.mmd -o diagram.pdf
Use Kroki when mmdc is not available. No local dependencies needed.
# SVG via Kroki
curl -X POST -H "Content-Type: text/plain" --data-binary @diagram.mmd https://kroki.io/mermaid/svg -o diagram.svg
# PNG via Kroki
curl -X POST -H "Content-Type: text/plain" --data-binary @diagram.mmd https://kroki.io/mermaid/png -o diagram.png
# PDF is NOT supported by Kroki for Mermaid — POSTing to /mermaid/pdf returns
# HTTP 400 ("Unsupported output format: pdf for mermaid. Must be one of png or svg").
# For PDF, use the local mmdc path instead: mmdc -i diagram.mmd -o diagram.pdf
Kroki advantages:
curlWhen to use Kroki:
mmdc installation fails| Mistake | Fix |
|---------|-----|
| mmdc not found | npm install -g @mermaid-js/mermaid-cli |
| mmdc error Could not find Chrome | Install the headless browser: npx puppeteer browsers install chrome-headless-shell (or use Kroki) |
| Kroki PDF fails with HTTP 400 | Kroki does PNG/SVG only for Mermaid; use local mmdc for PDF |
| Valid diagram reported "invalid" by mmdc | The error is a Chrome/puppeteer setup failure, not a syntax error — don't rewrite correct .mmd; fix the browser or validate via Kroki |
| Wrong arrow in sequence | Use ->> for request, -->> for response |
| Special chars in label | Wrap in quotes: A["Label: value"] |
| Blank/small output | Add -w 2048 flag |
| Participant order wrong | Declare participant explicitly at top |
| Subgraph name with spaces | Wrap in quotes: subgraph "My Layer" |
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag
| Build Shopify apps, extensions, themes using GraphQL Admin API, Shopify CLI, Polaris UI, and Liquid. "shopify theme", "liquid template", "polaris", "shopify graphql", "shopify webhook", "shopify billing", "app subscription", "metafields", "shopify functions"
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).
Take agents365-ai/mermaid-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm, npx.
Without those the skill loads but fails at the first command.