create-mermaid-visualization
Create any Mermaid diagram (flowchart, sequence, class, state, ER, C4, architecture, gantt, mindmap, timeline, pie, sankey, and 20+ more) from a description…
Skill by tomzx
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/tomzx-create-mermaid-visualization
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, data
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 and code. 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/create-mermaid-visualization
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,Edit,Grep,Glob,Bash
What's inside
- Skill name
create-mermaid-visualization- Description
- Create any Mermaid diagram (flowchart, sequence, class, state, ER, C4, architecture, gantt, mindmap, timeline, pie, sankey, and 20+ more) from a description or source material. Use when the user says "diagram", "visualize", "mermaid", "draw a flowchart", "sequence diagram", "ER diagram", "mindmap", "gantt chart", or asks to document architecture, processes, data flows, or relationships as a diagram. Covers selecting the right diagram type, correct syntax, validation, and delivery into Markdown or files.
- License
- MIT
- Allowed tools
- Read,, Write,, Edit,, Grep,, Glob,, Bash
- Instructions
- 185 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves any shell command
Files (8)
- SKILL.md
- architecture-diagrams.md · references/
- data-charts.md · references/
- flowchart.md · references/
- interaction-diagrams.md · references/
- planning-diagrams.md · references/
- specialized-diagrams.md · references/
- structure-diagrams.md · references/
SKILL.md (first lines)
# Create Mermaid Visualization
Produces correct, validated Mermaid diagrams for any of the 30+ diagram types Mermaid supports.
The skill selects the right diagram type from the user's intent, writes syntactically correct Mermaid using family-specific references, validates before delivering, and returns a diagram that renders in Markdown-aware viewers (GitHub, GitLab, VS Code, Obsidian, Notion).
## Prerequisites
- A subject to visualize: a description from the user, or source material (code, schema, process notes, data).
- The diagram catalog below and the matching file under `references/`.
- Optional: `@mermaid-js/mermaid-cli` (`mmdc`) for rendering validation.
Check with `command -v mmdc`; if absent, use `npx -y @mermaid-js/mermaid-cli` or fall back to careful review.
## Steps
### 1. Gather context
Ask for or infer:
- What the diagram should show (process, structure, interactions, data, planning).
- The audience and target (GitHub README, docs site, issue comment, presentation).
- Any entities, steps, actors, or data values already known.
- Layout preference if stated (top-down, left-right).
### 2. Select the diagram type
Match intent to type using the catalog below.
When two types fit, prefer the one that renders more reliably in the target (stable types over `-beta` types) and answers the user's actual question (who interacts when, how things are structured, what the data shows).
### 3. Load the family reference
Read only the `references/` file for the chosen family.
Follow its syntax exactly; do not mix syntax between families.
### 4. Write the diagram
- Declare the diagram type on the first line.
- Use the exact keyword from the catalog, including `-beta` and `-v2` suffixes.
- Keep one concept per diagram; split large subjects into multiple focused diagrams.
- Label nodes and edges in plain language, so the diagram needs no explanation.
### 5. Validate
Run validation before delivering.
If `mmdc` is available (or via `npx`):
```bash
mmdc -i diagram.mmd -o /tmp/opencode/diagram.svg
```
An exit code of 0 means the syntax parses.
A non-zero exit from a Puppeteer browser launch (missing `chrome-headless-shell` or `No usable sandbox`) is an environment problem, not a syntax error.
Diagrams that use icons, such as `architecture-beta` with `logos:` prefixes, only render them when the pack is installed (`npm install @iconify-json/logos`) and passed: `mmdc -i diagram.mmd -o /tmp/opencode/diagram.svg --iconPacks @iconify-json/logos`.
If `mmdc` is unavailable, re-read the diagram against the family reference line by line and check the pitfalls below.
Never add a diagram to a document until it passes validation.
### 6. Deliver
- Inline in Markdown: fenced code block with the `mermaid` language tag.
- As a file: `.mmd` file, with `.svg` or `.png` exported via `mmdc` when the target cannot render Mermaid (Confluence, Word, PDF, plain web pages).
- Note the rendering limits from the catalog when the target is GitHub (several `-beta` types do not render there).
## Diagram Catalog
Stable types render on GitHub and most Markdown viewers.
Types marked `beta` may not render on GitHub; check the target before using them.
| Intent | Type | Keyword | Since | Use for |
|---|---|---|---|---|
| Process or decision flow | Flowchart | `flowchart` (alias `graph`) | stable | Workflows, algorithms, decision trees, data flow |
| Interactions over time | Sequence | `sequenceDiagram` | stable | API calls, protocol steps, request/response chains |
| Interactions over time (code style) | ZenUML | `zenuml` | 11.0+ | Sequence diagrams written as pseudo-code |
| Code structure | Class | `classDiagram` | stable | Classes, interfaces, inheritance, domain models |
| State machines | State | `stateDiagram-v2` | stable | Lifecycle states, mode transitions |
| Database or data model | Entity Relationship | `erDiagram` | stable | Tables, keys, cardinality between entities |
| Software architecture | C4 | `C4Context`, `C4Container`, `C4Component`, `C4Dynamic`, `C4Deployment` | experimental | System context, containers, components, deployment |
| Cloud or CI/CD services | Architecture | `architecture-beta` | 11.1+ | Service and resource relationships in groups |
| Simple boxes and columns | Block | `block-beta` | 10.9+ | Layered component stacks, parent-child block layouts |
| Project schedule | Gantt | `gantt` | stable | Tasks, durations, dependencies, milestones |
| Chronology | Timeline | `timeline` | 10.3+ | Events over periods, roadmaps, history |
| Workflow board | Kanban | `kanban` | 11.3+ | Tasks across column stages |
| Idea hierarchy | Mindmap | `mindmap` | 10.3+ | Topic trees, brainstorming, concept breakdowns |
| Branching strategy | Git graph | `gitGraph` | 10.3+ | Commits, branches, merges, release flows |
| Experience over time | User journey | `journey` | stable | Satisfaction across steps of a user task |
| Two-axis positioning | Quadrant chart | `quadrantChart` | 10.3+ | Items plotted on two axes with four quadrants |
| Cross-team process | Swimlanes | `swimlane-beta` | 11.16+ | Steps grouped by owner, handoffs between lanes |
| Information flow over time | Event modeling | `eventmodeling` | 11.15+ | Commands, events, views, and processors on a timeline |
| Sense-making domains | Cynefin | `cynefin-beta` | 11.16+ | Items classified into five complexity domains |
| Strategy evolution | Wardley map | `wardley-beta` | 11.14+ | Components positioned by value chain and evolution |
| Proportions | Pie chart | `pie` | stable | Parts of a whole |
| Numeric series | XY chart | `xychart-beta` | 10.9+ | Line and bar plots over a numeric or category axis |
| Flow redistribution | Sankey | `sankey-beta` | 10.3+ | Quantities moving between sets of nodes |
| Nested proportions | Treemap | `treemap-beta` | 11.13+ | Hierarchy as sized rectangles |
| Multivariate comparison | Radar | `radar-beta` | 11.6+ | Several series scored over the same axes |
| Set relationships | Venn | `venn-beta` | 11.12+ | Overlapping sets and unions |
| Wire format layout | Packet | `packet-beta` | 11.0+ | Bit ranges of protocol headers and frames |
| Requirements and traces | Requirement | `requirementDiagram` | stable | SysML requirements linked to elements |
| Actors and use cases | Use case | `usecase-beta` | 12.0+ | Actors, system boundary, use cases |
| Cause analysis | Ishikawa | `ishikawa-beta` | 11.12+ | Fishbone causes of a problem |
| Grammar visualization | Railroad | `railroad-beta`, `railroad-ebnf-beta`, `railroad-abnf-beta`, `railroad-peg-beta` | 11.16+ | Context-free grammar rules as paths |
| Directory layout | Tree view | `treeView-beta` | 11.14+ | File trees, box-drawing input supported |
| Agentic workflow | Agentflow | `agentflow-beta` | 12.0+ | Agents, tasks, tools, and data contracts |
Reference files by family:
- `references/flowchart.md`: flowchart syntax, node shapes, edges, subgraphs, styling.
- `references/structure-diagrams.md`: class, state, entity relationship.
- `references/interaction-diagrams.md`: sequence, ZenUML.
- `references/architecture-diagrams.md`: C4, architecture, block.
- `references/planning-diagrams.md`: gantt, timeline, kanban, mindmap, git graph, user journey, quadrant, swimlanes, event modeling, Cynefin, Wardley.
- `references/data-charts.md`: pie, XY chart, sankey, treemap, radar, venn, packet.
- `references/specialized-diagrams.md`: requirement, use case, ishikawa, railroad, tree view, agentflow.
## Common Syntax Rules
- Comments start with `%%`.
Unknown words break the parse; misspelled keywords cause a parse error.
- Wrap labels containing special characters (`{}`, `[]`, `|`, `;`, quotes) in double quotes: `A["Label (with) chars"]`.
- Use HTML entities for angle brackets and ampersands inside labels (`<`, `&`), not raw `<` or `&`.From tomzx/agents, MIT.
More from tomzx/agents
- 0.639score
communication-guidelines
tomzx
Shared guidelines for writing concise, high-signal outbound communication the agent posts or drafts on the user's behalf, covering GitHub PR and issue…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-maintainability
tomzx
Audit the codebase for maintainability, the ISO/IEC 25010 characteristic covering modularity, reusability, analyzability, modifiability, and testability.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-attention
tomzx
Audit how your time splits between compounding and depreciating activities using the two-year test.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
create-article
tomzx
Write, update, or revise a high-quality article given a target audience and relevant sources.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-usability
tomzx
Audit the software's interfaces (CLI, API, and web UI) for usability, the ISO/IEC 25010 characteristic covering recognizability, learnability, operability…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-functional-suitability
tomzx
Audit whether the software actually does what it should, completely and correctly.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-compatibility
tomzx
Audit the codebase for compatibility, the ISO/IEC 25010 characteristic covering co-existence (running alongside other software without conflict) and…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
analyze-test-coverage
tomzx
Analyze a set of code changes (diff or files) and produce a structured test coverage report with three parts: introduced tests, change coverage, and uncovered…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
arxiv-article
tomzx
Downloads an arXiv HTML article, converts it to markdown with pandoc, archives it, and returns a structured summary.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
arxiv-catchup
tomzx
Fetches new arXiv cs.AI papers published since the last processed date, processes each paper's HTML version via the arxiv-article skill, and advances the date…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
attach-assets
tomzx
Upload files (images, logs, screenshots) to a dedicated orphan branch in the repository and embed them in a GitHub issue or PR comment or description, so…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-performance-efficiency
tomzx
Audit the codebase for performance efficiency, the ISO/IEC 25010 characteristic covering time behavior, resource utilization, and capacity.
SkillAFreshness: A★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 1
- Open issues
- 16
- Last commit (this folder)
- Oct 22, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tomzx/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tomzx
- 0.639score
communication-guidelines
tomzx
Shared guidelines for writing concise, high-signal outbound communication the agent posts or drafts on the user's behalf, covering GitHub PR and issue…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
arxiv-article
tomzx
Downloads an arXiv HTML article, converts it to markdown with pandoc, archives it, and returns a structured summary.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
analyze-test-coverage
tomzx
Analyze a set of code changes (diff or files) and produce a structured test coverage report with three parts: introduced tests, change coverage, and uncovered…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
create-article
tomzx
Write, update, or revise a high-quality article given a target audience and relevant sources.
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
audit-usability
tomzx
Audit the software's interfaces (CLI, API, and web UI) for usability, the ISO/IEC 25010 characteristic covering recognizability, learnability, operability…
SkillAFreshness: A★ 12Claude Code +9 - 0.634score
arxiv-catchup
tomzx
Fetches new arXiv cs.AI papers published since the last processed date, processes each paper's HTML version via the arxiv-article skill, and advances the date…
SkillAFreshness: A★ 12Claude Code +9
Cite this page
create-mermaid-visualization skill. Agent Mart. https://agentmart.dev/skills/tomzx-create-mermaid-visualization (last updated 2026-10-24)