mcpbeat

Data Flow

athola/data-flow

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

792 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
324
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/athola/claude-night-market --skill data-flow

The instruction itself

9 sections, as written by the author

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?"

When NOT To Use

  • Static call structure (use cartograph:call-chain)
  • Process steps and state transitions (use cartograph:workflow-diagram)

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).

Exit Criteria

  • [ ] Mermaid sequenceDiagram syntax generated with participants

and at least one ->> call arrow

  • [ ] mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram

called with diagramType: "sequenceDiagram" and returns without

error (or retry attempted on first failure)

  • [ ] Participant count is at most 10; if more components exist,

they are aggregated and the aggregation noted

  • [ ] A 2-3 sentence description of the depicted flow is shown

alongside the rendered diagram

  • [ ] Return arrows (-->>) are present for any request that has

a corresponding response in the traced flow

How to use it

Copy the folder

Take athola/data-flow from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.