convez.ai
SkillDesign & UIIntermediário
Xinyu-lumos

Fireworks Tech Graph

Xinyu-lumos/fireworks-tech-graph

Gere diagramas técnicos profissionais a partir de descrição em texto

Ver no GitHub
InicialPluginScore · de 0 a 100

Skill para Claude que transforma descrições em linguagem natural em diagramas técnicos SVG e PNG publication-ready. Oferece 7 estilos visuais (desde flat icon até glassmorphism) e 14 tipos de diagramas UML, com suporte específico para arquiteturas de IA (RAG, agentes, Mem0, multi-agent).

Instalação

$npx convez-ai Xinyu-lumos/fireworks-tech-graph

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Documentar arquiteturas de sistemas e microserviços
  • Visualizar fluxos de agentes de IA e pipelines RAG
  • Criar diagramas UML (classe, sequência, componentes, estado)
  • Gerar assets visuais para presentations e documentação técnica

Veredito

Ferramenta sólida que automatiza a geração de diagramas técnicos, economizando tempo na documentação. Particularmente útil para arquiteturas de IA/agentes, com 7 estilos profissionais e saída vetorial de qualidade. Recomendado para times que precisam manter diagramas em sync com mudanças de arquitetura.

README

A tradução para o português deste README ainda está na fila.

English | 中文

fireworks-tech-graph

Stop drawing diagrams by hand. Describe your system in English or Chinese — get publication-ready SVG + PNG technical diagrams in seconds.

License: MIT Claude Code Skill 7 Visual Styles 14 Diagram Types UML Support


Overview

fireworks-tech-graph turns natural language descriptions into polished SVG diagrams, then exports them as high-resolution PNG via rsvg-convert. It ships with 7 visual styles and deep knowledge of AI/Agent domain patterns (RAG, Agentic Search, Mem0, Multi-Agent, Tool Call flows), plus full support for all 14 UML diagram types.

User: "Generate a Mem0 memory architecture diagram, dark style"
  → Skill classifies: Memory Architecture Diagram, Style 2
  → Generates SVG with swim lanes, cylinders, semantic arrows
  → Exports 1920px PNG
  → Reports: mem0-architecture.svg / mem0-architecture.png

Showcase

All samples exported at 1920px width (2× retina) via rsvg-convert. PNG is lossless and the right choice for technical diagrams — sharp edges, no JPEG compression artifacts on text/lines.

Style 1 — Flat Icon (default)

Agentic RAG Pipeline — white background, colorful semantic arrows Style 1 — Flat Icon

Style 2 — Dark Terminal

Tool Call Flow — dark background, neon accents, monospace font Style 2 — Dark Terminal

Style 3 — Blueprint

Microservices Architecture — deep blue background, grid lines, cyan strokes Style 3 — Blueprint

Style 4 — Notion Clean

Agent Memory Types — minimal white, single accent color Style 4 — Notion Clean

Style 5 — Glassmorphism

Multi-Agent Collaboration — dark gradient background, s cards Style 5 — Glassmorphism

Style 6 — Claude Official

System Architecture — warm cream background (#f8f6f3), Anthropic brand colors, clean professional aesthetic Style 6 — Claude Official

Style 7 — OpenAI Official

API Integration Flow — pure white background, OpenAI brand palette, modern minimalist design Style 7 — OpenAI Official

AI Domain — Mem0 Memory Architecture

Full memory architecture with swim lanes, cylinders, and semantic read/write arrows Mem0 Architecture


Features

  • 7 visual styles — from clean white docs to dark neon to frosted glass to official brand styles
  • 14 diagram types — Full UML support (Class, Component, Deployment, Package, Composite Structure, Object, Use Case, Activity, State Machine, Sequence, Communication, Timing, Interaction Overview, ER Diagram) plus AI/Agent domain diagrams
  • AI/Agent domain patterns — RAG, Agentic Search, Mem0, Multi-Agent, Tool Call, and more built-in
  • Semantic shape vocabulary — LLM = double-border rect, Agent = hexagon, Vector Store = ringed cylinder
  • Semantic arrow system — color + dash pattern encode meaning (write vs read vs async vs loop)
  • Product icons — 40+ products with brand colors: OpenAI, Anthropic, Pinecone, Weaviate, Kafka, PostgreSQL…
  • Swim lane grouping — automatic layer labeling for complex architectures
  • SVG + PNG output — SVG for editing, 1920px PNG for embedding
  • rsvg-convert compatible — no external font fetching, pure inline SVG

Installation

claude skills install fireworks-tech-graph

Or clone directly:

git clone https://github.com/yizhiyanhua-ai/fireworks-tech-graph.git ~/.claude/skills/fireworks-tech-graph

Requirements

# macOS
brew install librsvg

# Ubuntu/Debian
sudo apt install librsvg2-bin

# Verify
rsvg-convert --version

Why Not Mermaid or draw.io?

Mermaiddraw.iofireworks-tech-graph
Natural language input✗✗✅
AI/Agent domain patterns✗✗✅
Multiple visual styles✗manual✅ 5 built-in
High-res PNG export✗manual✅ auto 1920px
Semantic arrow colors✗manual✅ auto
No online tool needed✅✗✅

Mermaid is great for quick inline diagrams in markdown. draw.io is great for manual polishing. fireworks-tech-graph is optimized for describing a system and getting a polished diagram immediately, without writing DSL syntax or clicking around a GUI.


Usage

Trigger phrases

The skill auto-triggers on:

generate diagram / draw diagram / create chart / visualize
architecture diagram / flowchart / sequence diagram / data flow

Basic usage

Draw a RAG pipeline flowchart
Generate an Agentic Search architecture diagram

Specify style

Draw a microservices architecture diagram, style 2 (dark terminal)
Draw a multi-agent collaboration diagram --style glassmorphism

Specify output path

Generate a Mem0 architecture diagram, output to ~/Desktop/
Create a tool call flow diagram --output /tmp/diagrams/

Example Prompts by Scenario

AI/Agent Systems

Compare Agentic RAG vs standard RAG in a feature matrix, Notion clean style

→ Comparison matrix: RAG vs Agentic RAG, covering retrieval strategy, agent loop, tool use

Generate a Mem0 memory architecture diagram with vector store, graph DB, KV store, and memory manager

→ Memory Architecture with swim lanes: Input → Memory Manager → Storage tiers → Retrieval

Draw a Multi-Agent diagram: Orchestrator dispatches 3 SubAgents (search / compute / code execution), results aggregated

→ Agent Architecture with hexagons, tool layers, and result aggregation

Visualize the Tool Call execution flow: LLM → Tool Selector → Execution → Parser → back to LLM

→ Flowchart with decision loop showing tool invocation cycle

Draw the 5 agent memory types: Sensory, Working, Episodic, Semantic, Procedural

→ Mind map or layered architecture showing memory tiers from sensory to procedural

Infrastructure & Cloud

Draw a microservices architecture: Client → API Gateway → [User Service / Order Service / Payment Service] → PostgreSQL + Redis

→ Architecture diagram with horizontal layers, swim lanes per service cluster

Generate a data pipeline diagram: Kafka → Spark processing → write to S3 → Athena query

→ Data flow diagram with labeled arrows (stream / batch / query)

Draw a Kubernetes deployment: Ingress → Service → [Pod × 3] → ConfigMap + PersistentVolume

→ Architecture with dashed containers per namespace, solid arrows for traffic flow

API & Sequence Flows

Draw an OAuth2 authorization code flow sequence diagram: User → Client → Auth Server → Resource Server

→ Sequence diagram with vertical lifelines and activation boxes

Draw the ChatGPT Plugin call sequence diagram

→ Sequence: User → ChatGPT → Plugin Manifest → API → Response chain

Decision & Process Flows

Draw a pre-launch QA flowchart for an AI app: Code Review → Security Scan → Performance Test → Manual Approval → Deploy

→ Flowchart with diamond decision nodes and parallel branches

Generate a feature comparison matrix: RAG vs Fine-tuning vs Prompt Engineering

→ Comparison matrix with checked/unchecked cells across cost, latency, accuracy, flexibility

Concept Maps

Visualize the LLM application tech stack: from foundation model to SDK to app framework to deployment

→ Layered architecture or mind map from model layer to product layer

Draw an AI Agent capability map: Perception / Memory / Reasoning / Action / Learning

→ Mind map with central "AI Agent" node and 5 radial branches


Styles

#NameBackgroundFontBest For
1Flat Icon (default)#ffffffHelveticaBlogs, slides, docs
2Dark Terminal#0f0f1aSF Mono / Fira CodeGitHub README, dev articles
3Blueprint#0a1628Courier Newure docs, engineering
4Notion Clean#ffffffsystem-uiNotion, Confluence, wikis
5Glassmorphism#0d1117 gradientInterProduct sites, keynotes
6Claude Official#f8f6f3system-uiAnthro diagrams, warm aesthetic
7OpenAI Official#ffffffsystem-uiOpenAI-style diagrams, clean modern look

Each style has a dedicated reference file in references/ with exact color tokens, SVG patterns, and templates.

Style Selection Guide

For UML Diagrams:

  • Class/Component/Package: Style 1 (Flat Icon) or Style 4 (Notion Clean) — clear structure, easy to read
  • Sequence/Timing: Style 2 (Dark Terminal) — monospace fonts help with alignment
  • State Machine/Activity: Style 3 (Blueprint) — engineering aesthetic fits process flows
  • Use Case/Interview: Style 1 (Flat Icon) — colorful, accessible

For AI/Agent Diagrams:

  • RAG/Agentic Search: Style 2 (Dark Terminal) or Style 5 (Glassmorphism) — tech-forward aesthetic
  • Memory Architecture: Style 3 (Blueprint) — emphasizes layered storage tiers
  • Multi-Agent: Style 5 (Glassmorphism) — frosted cards distinguish agent boundaries

For Documentation:

  • Internal docs: Style 4 (Notion Clean) — minimal, wiki-frieng posts**: Style 1 (Flat Icon) — colorful, engaging
  • GitHub README: Style 2 (Dark Terminal) — matches dark theme
  • Presentations: Style 5 (Glassmorphism) or Style 6 (Claude Official) — polished

Brand-Specific:

  • Anthropic/Claude projects: Style 6 (Claude Official) — warm cream background, brand colors
  • OpenAI projects: Style 7 (OpenAI Official) — clean white, OpenAI palette

Diagram Types

TypeDescriptionKey Layout Rule
ArchitectureServices, components, cloud infraHorizontal layers top→bottom
Data FlowWhat data moves whereLabel every arrow with data type
FlowchartDecisions, process stepsDiamond = decision, top→bottom
Agent ArchitectureLLM + tools + memory5-layer model: Input/Agent/Memory/Tool/Output
Memory ArchitectureMem0, MemGPT-styleSeparate read/write paths, memory tiers
SequenceAPI call chains, time-orderedVertical lifelines, horizontal messages
ComparisonFeature matrix, side-by-sideColumn = system, row = attribute
Mind MapConcept maps, radialCentral node, bezier branches

UML Diagram Support (14 Types)

UML TypeDescriptionBest Style
Class DiagramClasses, attributes, methods, relationshipsStyle 1, 4
Component DiagramSoftware components and dependenciesStyle 1, 3
Deployment DiagramHardware nodes and software deploymentStyle 3
Package DiagramPackage organization and dependenciesStyle 1, 4
Composite StructureInternal structure of classes/componentsStyle 1, 3
Object DiagramObject instances and relationshipsStyle 1, 4
Use Case DiagramActors, use cases, system boundariesStyle 1
Activity DiagramWorkflows, parallel processesSty3
State MachineState transitions and eventsStyle 2, 3
Sequence DiagramMessage exchanges over timeStyle 2
Communication DiagramObject interactions and messagesStyle 1, 2
Timing DiagramState changes over timeStyle 2
Interaction OverviewHigh-level interaction flowStyle 1, 2
ER DiagramEntity-relationship data modelsStyle 1, 3

AI/Agent Domain Patterns

Built-in pattern knowledge:

RAG Pipeline         → Query → Embed → VectorSearch → Retrieve → LLM → Response
Agentic RAG          → adds Agent loop + Tool use
Agentic Search       → Query → Planner → [Search/Calc/Code] → Synthesizer
Mem0 Memory Layer    → Input → Memory Manager → [VectorDB + GraphDB] → Context
Agent Memory Types   → Sensory → Working → Episodic → Semantic → Procedural
Multi-Agent          → Orchestrator → [SubAgent×N] → Aggregator → Output
Tool Call Flow       → LLM → Tool Selector → Execution → Parser → LLM (loop)

Shape Vocabulary

Shapes encode semantic meaning consistently across all styles:

ConceptShape
User / HumanCircle + body
LLM / ModelRounded rect, double border, ⚡
Agent / OrchestratorHexagon
Memory (short-term)Dashed-border rounded rect
Memory (long-term)Solid cylinder
Vector StoreCylinder with inner rings
Graph DB3-circle cluster
Tool / FunctionRect with ⚙
API / GatewayHexagon (single border)
Queue / StreamHorizontal pipe/tube
Document / FileFolded-corner rect
Browser / UIRect with 3-dot titlebar
DecisionDiamond
External ServiceDashed-border rect

Arrow Semantics

Flow TypeStrokeDashMeaning
Primary data flow2px solid—Main request/response
Control / trigger1.5px solid—System A triggers B
Memory read1.5px solid—Retrieve from store
Memory write1.5px5,3Write/store operation
Async / event1.5px4,2Non-blocking
Feedback / loop1.5px curved—Iterative reasoning

File Structure

fireworks-tech-graph/
├── SKILL.md                      # Main skill — diagram types, layout rules, shape vocab
├── README.md                     # This file (English)
├── README.zh.md                  # Chinese version
├── references/
│   ├── style-1-flat-icon.md      # White background, colored accents
│   ├── style-2-dark-terminal.md  # Dark bg, neon accents, monospace
│   ├── style-3-blueprint.md      # Blueprint grid, cyan lines
│   ├── style-4-notion-clean.md   # Minimal, white, single arrow color
│   ├── style-5-glassmorphism.md  # Dark gradient, frosted glass cards
│   ├── style-6-claude-official.md # Warm cream background, Anthropic brand
│   ├── style-7-openai-official.md # Clean white, OpenAI brand palette
│   └── icons.md                  # 40+ product icons + semantic shapes
├── scripts/
│   ├── generate-diagram.sh       # Generate SVG + PNG with validation
│   ├── validate-svg.sh           # Validate SVG syntax
│   └── test-all-styles.sh        # Batch test all styles
└── assets/
    └── samples/                  # Showcase diagram PNGs

Product Icon Coverage

AI/ML: OpenAI, Anthropic/Claude, Google Gemini, Meta LLaMA, Mistral, Cohere, Groq, Hugging Face

AI Frameworks: Mem0, LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen, DSPy, Haystack

Vector DBs: Pinecone, Weaviate, Qdrant, Chroma, Milvus, pgvector, Faiss

Databases: PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch, Neo4j, Cassandra

Messaging: Kafka, RabbitMQ, NATS, Pulsar

Cloud: AWS, GCP, Azure, Cloudflare, Vercel, Docker, Kubernetes

Observability: Grafana, Prometheus, Datadog, LangSmith, Langfuse, Arize


Troubleshooting

SymptomCauseFix
PNG is blank or all-black@import url() in SVG — rsvg-convert can't fetch fontsRemove @import, use system font stack
PNG not generatedrsvg-convert not installedbrew install librsvg (macOS) or apt install librsvg2-bin
Diagram cut off at bottomViewBox height too shortIncrease height in viewBox="0 0 960 <height>"
Text overflowing boxesLabels too longAdd text-anchor="middle" + <clipPath> or shorten label
Icons not renderingExternal CDN URL in rsvg-convert contextUse inline SVG paths from references/icons.md

License

MIT © 2025 fireworks-tech-graph contributors

Ver o original no GitHub

Bom para

Relacionados