메뉴
Render Mermaid diagrams as ASCII/Unicode art or SVG
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | mermaid |
| description | Render Mermaid diagrams as ASCII/Unicode art or SVG |
| execution | direct |
[mermaid] visualize→ASCII|SVG | via beautiful-mermaid
supported: flowchart, state, sequence, class, ER
output: terminal-friendly ASCII or SVG file
themes: 15 built-in (tokyo-night, github-dark, etc.)
When user asks for a diagram, architecture visualization, or flowchart:
graph TD
A[Start] --> B{Decision}
B -->|Yes| C[Action]
B -->|No| D[End]
sequenceDiagram
Alice->>Bob: Hello
Bob-->>Alice: Hi back
stateDiagram-v2
[*] --> Idle
Idle --> Processing: start
Processing --> Done: complete
Done --> [*]
classDiagram
Animal <|-- Duck
Animal <|-- Fish
Animal : +int age
Animal : +isMammal()
erDiagram
CUSTOMER ||--o{ ORDER : places
ORDER ||--|{ LINE-ITEM : contains
Use the mermaid-render script to render diagrams:
# ASCII output (terminal)
mermaid-render ascii "graph LR; A --> B --> C"
# SVG output (file)
mermaid-render svg "graph TD; A --> B" output.svg
# With theme
mermaid-render svg "graph TD; A --> B" output.svg --theme tokyo-night
User: "Show me the hook lifecycle"
graph TD
A[SessionStart] --> B[UserPromptSubmit]
B --> C{Tool Call?}
C -->|Yes| D[PreToolUse]
D --> E[Tool Executes]
E --> F{Success?}
F -->|Yes| G[PostToolUse]
F -->|No| H[PostToolUseFailure]
G --> I{More Tools?}
H --> I
I -->|Yes| C
I -->|No| J[Stop]
Then render as ASCII for terminal display.
Trigger autonomous curiosity-driven exploration. The soul picks a topic from memory gaps or curiosity seeds, searches the web, and stores what it finds as dream-tagged memories.
Fine-tune the Qwen3-0.6B hint model — corpus gen, LoRA/unsloth, GGUF export, Ollama
Review soul discoveries (fixes, improvements, corrections) one by one, accept or discard each, implement accepted ones, build chitta, and optionally release.
First-principles review — question requirements, delete unnecessary parts, simplify, optimize with evidence, automate last. Use for code review, refactor, performance, or architecture.
Token-savvy session continuation. Rebuilds working context from transcript + soul memories in ~1500 tokens instead of replaying full history. Use when starting a new session to continue previous work.
Resume a thread by loading its ~800-token context capsule