OpenParable
Skip to content
← Back to skills

Data Flow

Documents
data-flow

Data Flow is an Agent Skill for documents published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generates a Mermaid sequence diagram showing how data moves between components. Use when tracing request flows or documenting data transformation pipelines.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/analysis/data-flow-athola-claude-night-market/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/data-flow, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Data Flow Diagram

Generate a Mermaid sequence diagram showing how data moves between components in a codebase.

When To Use

  • Tracing how a request flows through the system
  • Understanding data transformation pipelines
  • Documenting API call chains
  • Answering "what happens when X is called?"

Workflow

Step 1: Explore the Codebase

Dispatch the codebase explorer agent:

Agent(cartograph:codebase-explorer)
Prompt: Explore [scope] and return a structural model.
Focus on function calls, data transformations, and
inter-module communication for a data flow diagram.

Step 2: Generate Mermaid Syntax

Transform the structural model into a Mermaid sequence diagram.

Rules for data flow diagrams:

  • Use sequenceDiagram for request/response flows
  • Participants are modules or components (not functions)
  • Arrows show data direction: ->> for calls, -->> for returns
  • Use activate/deactivate for long-running operations
  • Add Note over for data transformations
  • Limit to 8-10 participants maximum
  • Use alt/else for conditional flows
  • Handle circular calls by showing them once with a note

Example output:

sequenceDiagram
    participant User
    participant Command as /commit
    participant Sanctum as sanctum.commit
    participant Leyline as leyline.git_platform
    participant Git

    User->>Command: /commit
    Command->>Sanctum: generate_message()
    Sanctum->>Leyline: get_staged_changes()
    Leyline->>Git: git diff --cached
    Git-->>Leyline: diff output
    Leyline-->>Sanctum: structured changes
    Note over Sanctum: Classify change type
    Sanctum-->>Command: commit message
    Command->>Git: git commit -m "..."

Step 3: Render via MCP

Call the Mermaid Chart MCP to render:

mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram
  prompt: "Data flow diagram of [scope/feature]"
  mermaidCode: [generated syntax]
  diagramType: "sequenceDiagram"
  clientName: "claude-code"

If rendering fails, fix syntax and retry (max 2 retries).

Step 4: Present Results

Show the rendered diagram with a brief description of the flow depicted (2-3 sentences).