orchestra-uml

Included with Lifetime

$97 forever

Generate UML diagrams as Mermaid code and save them to .orchestra/uml/. Supports sequence, class, deployment, component, and state diagram types.

Design

What this skill does


# Generate UML Diagram

Produce a Mermaid diagram that documents system structure or behavior. Output goes to `.orchestra/uml/`.

## Diagram Types

Choose the type that matches what you're documenting:

| Type | Use When | Mermaid Block |
|------|----------|---------------|
| **sequence** | Agent-to-tool flows, multi-step workflows, API call chains | `sequenceDiagram` |
| **class** | Data models, object relationships, schema structure | `classDiagram` |
| **deployment** | On-device vs cloud allocation, infrastructure topology | `graph TB` with subgraphs |
| **component** | High-level system overview, major pieces and connections | `graph LR` |
| **state** | Workflow states, agent decision logic, valid transitions | `stateDiagram-v2` |

## Steps

### 1. Identify the Diagram Type

Read $ARGUMENTS. If no type is given, ask:
- Is this about the *flow* of an interaction? → sequence
- Is this about *data shape* or relationships? → class
- Is this about *where things run*? → deployment
- Is this about *what the major pieces are*? → component
- Is this about *states and transitions*? → state

### 2. Gather Context

- Glob relevant source files, skill definitions, or agent configs
- Read existing `.orchestra/uml/` diagrams to avoid duplication and match style
- Read the active milestone PRD for scope

### 3. Generate the Diagram

Use the appropriate Mermaid syntax:

**Sequence:**
```mermaid
sequenceDiagram
    participant A as Agent
    participant T as Tool / MCP Server
    participant API as External API
    A->>T: tool call with params
    T->>API: downstream request
    API-->>T: response
    T-->>A: structured result
```

**Class:**
```mermaid
classDiagram
    class Artifact {
        +String ticket
        +String status
        +Date created_on
    }
    class PRD {
        +String objective
        +List criteria
    }
    Artifact <|-- PRD
```

**Deployment:**
```mermaid
graph TB
    subgraph Device["On-Device"]
        App["App"]
        Model["Local Model"]
    end
    subgraph Cloud["Cloud"]
        Worker["Cloudflare Worker"]
        DB["D1 Database"]
    end
    App -->|inference| Model
    App -->|API call| Worker
    Worker -->|query| DB
```

**Component:**
```mermaid
graph LR
    A["Component A"]
    B["Component B"]
    C["Component C"]
    A -->|action| B
    B -->|result| C
```

**State:**
```mermaid
stateDiagram-v2
    [*] --> Draft
    Draft --> Approved
    Approved --> InProgress
    InProgress --> Complete
    Complete --> [*]
```

### 4. Write the File

Save to `.orchestra/uml/{project}-{type}-{purpose}.md`

Naming convention: `[project]-[diagram-type]-[purpose].md`
- `chiropractic-sequence-soap-pipeline.md`
- `orchestra-component-plugin-structure.md`
- `kairos-state-daily-rhythm.md`

Include frontmatter per ADR-001 (UML carries `created_on` only — no status, no ticket):

```yaml
---
created_on: {YYYY-MM-DD}
---
```

Full file structure:
```markdown
---
created_on: YYYY-MM-DD
---

# {Diagram Title}

> {One sentence: what this diagram shows and why it exists}

```mermaid
{diagram code}
```

## Notes

{Optional: call out non-obvious decisions, constraints, or what to look at first}

## References

- {Spec, ADR, or external doc this diagram relates to}
```

### 5. Cross-Reference

If this diagram was prompted by a spec or ADR, add a reference line to that document pointing back to the diagram. The relationship is:
- **Specs** document *what* — reference the UML for *how*
- **ADRs** document *why* — reference the UML for the topology that resulted from the decision

## Examples

See `examples/` for reference diagrams:

| File | Type | What It Shows |
|------|------|---------------|
| `examples/sequence.md` | sequence | Multi-phase agent workflow with parallel tool calls and retry logic |

## Quality Checks

- [ ] Diagram type matches what's being shown (don't use sequence for topology)
- [ ] Participants and nodes have human-readable labels, not code identifiers
- [ ] Mermaid syntax is valid — no unclosed blocks, correct arrow types
- [ ] Filename follows `[project]-[type]-[purpose].md` convention
- [ ] `created_on` frontmatter is present
- [ ] One sentence description is present below the title

Files: 4

Size: 10.8 KB

Complexity: 22/100

Category: Design

Source: https://github.com/mpazaryna/agentic-factory/tree/main/skills/orchestra-uml

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts