skills/mermaid-creator/SKILL.md
Use proactively whenever generating Mermaid diagram code in any context (markdown blocks, .md files, docs). Covers flowcharts, sequence, class, state, ER, gantt, pie, mindmaps, timelines, and all Mermaid types. Applies strict syntax rules to prevent rendering errors (HTML tags, style directives, invalid escapes). No explicit request needed — load automatically when Mermaid syntax is being produced.
npx skillsauth add takazudo/claude-resources mermaid-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate valid, error-free Mermaid diagrams following strict syntax rules and best practices.
<br/>, <br>, or any HTML in any part of the diagramstyle, fill, stroke, classDef, or color specificationsWhen generating any Mermaid diagram:
These ALWAYS cause errors - never use:
❌ participant User<br/>Browser (HTML tags)
❌ A[Label<br/>with breaks] (HTML in labels)
❌ style A fill:#ff0000 (Style directives)
❌ classDef myClass fill:#f9f (Color definitions)
❌ A --> B: Very long message<br/>text (Line breaks in text)
Use these instead:
✅ participant UserBrowser as User Browser (Aliases)
✅ A[Short label] (Concise text)
✅ A --> B: Concise message (Single-line text)
✅ Note over A,B: Descriptive note (Notes for details)
Choose based on use case:
Use for showing interactions over time (auth flows, API calls):
sequenceDiagram
participant Client
participant Auth0
participant Backend
Client->>Auth0: Login request
Auth0-->>Client: Authorization code
Client->>Backend: POST /create-session
Backend-->>Client: Set-Cookie (session)
Key rules:
participant X as Long Name for readable labels->, -->, ->>, -->> (solid/dotted, with/without arrow)Note over X,Y: Text for additional contextSee syntax-guide.md for complete sequence diagram syntax.
Use for decision trees and processes:
flowchart TD
A[Start]
B{Authenticated?}
C[Call API]
D[Redirect to login]
A --> B
B -->|Yes| C
B -->|No| D
Key rules:
TD (top-down), LR (left-right), BT (bottom-top), RL (right-left)[] rectangle, () rounded, {} diamond, [[]] subroutineA["Label: special"]See syntax-guide.md for complete flowchart syntax.
Use for object-oriented design:
classDiagram
class User {
+String id
+String email
+login()
+logout()
}
class Session {
+String token
+Date expires
+validate()
}
User --> Session
Key rules:
+ public, - private, # protected<|-- inheritance, *-- composition, --> associationSee syntax-guide.md for complete class diagram syntax.
Use for state machines and lifecycles:
stateDiagram-v2
[*] --> Idle
Idle --> Processing
Processing --> Success
Processing --> Failed
Success --> [*]
Failed --> [*]
Key rules:
stateDiagram-v2 (v2 is current version)[*] represents start/end statesSee syntax-guide.md for complete state diagram syntax.
Use for database schemas:
erDiagram
USER ||--o{ ORDER : places
ORDER ||--|{ LINE-ITEM : contains
USER {
string id
string email
}
ORDER {
string id
date created_at
}
Key rules:
||--|| one-to-one, ||--o{ one-to-many, }o--o{ many-to-manyUSER-ACCOUNTSee syntax-guide.md for complete ER diagram syntax.
Before finalizing any Mermaid diagram:
<br, <div, or any < characterstyle, fill:, stroke::, #, {}, [], ()| Error Pattern | Fix |
|--------------|-----|
| participant A<br/>B | participant AB as A B |
| A->>B: Long<br/>text | A->>B: Long text (keep single line) |
| style A fill:#f00 | Delete entirely (no styling) |
| A[Label #1] | A["Label #1"] (quote special chars) |
| A --> B: text<br/>more | Split into two arrows or use Note |
Comprehensive syntax reference with:
Load this file when encountering syntax questions or edge cases.
development
Link Claude Code skill names mentioned in a CodeGrid article (data/{series}/{n}.md) to the author's public claude-resources repo, pinned to the latest commit hash so links don't rot. Use when: (1) user says 'linkify cc resources', 'link the skills', 'link skill names', or invokes /dev-linkify-cc-resources; (2) editing a CodeGrid article that mentions `/commits`, `/pr-complete`, `/skill-creator` or other Claude Code skills and they should point to claude-resources. Only links skills that actually exist in the public repo; skips hypothetical examples and code blocks.
development
Second opinion from Claude Opus on a plan or approach. Use when: (1) Planning phase of /big-plan needs a higher-quality review than /codex-2nd / /gco-2nd, (2) User says 'opus 2nd' or 'opus opinion', (3) Wanting Anthropic's larger model to critique a plan. Spawns a general-purpose Agent with model: opus that reads the plan file and returns structured feedback. Anthropic quota — not free.
tools
AI-based testing via subagent + a per-task test-flow skill. Use when the user wants to verify something that mechanical assertions can't fully capture — image recognition, visual size/position comparison, animation smoothness, multi-step manual flows that need AI judgment. Triggers: 'AI-based test', 'AI test', 'visual verify', 'image recognition test', 'manual operation test', 'human-eye check', 'verify visually', 'compare screenshots', 'looks the same', 'looks correct'. The skill's job is to (1) author a focused test-flow skill that captures the exact procedure + verdict criteria, then (2) dispatch a verification subagent via the Agent tool that loads BOTH the test-flow skill AND a browser-driving skill (/verify-ui primary, /headless-browser fallback) so the subagent has clear context and consistent verdicts. NEVER uses `claude -p` — subagent dispatch goes through the Agent tool exclusively.
development
End-of-workflow audit of touched GitHub issues, PRs, and branches via a Sonnet subagent. Use when: (1) /big-plan, /x-as-pr, or /x-wt-teams finishes its main work and needs to verify every touched resource is in the right state (closed when done, kept when ongoing, deleted when dead), (2) User says 'cleanup resources', 'audit cleanup', or 'check what should be closed', (3) A long workflow ends and the manager wants a structured paper trail of what it closed/kept/deleted. Auto-execute by default — the Sonnet agent proposes, the manager (you) executes safe actions and prints a final report.