
Data Flow
- 77 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
Data Flow is an agent skill that explores your codebase and generates a Mermaid sequence diagram documenting how data moves between components.
About
Data Flow is an agent skill that produces Mermaid sequence diagrams describing how data and control move between components in your codebase. It is aimed at solo and indie builders who need clear request-path documentation for APIs, CLIs, or agent stacks without spending hours in a diagramming tool. Invoke it when you are tracing an end-to-end request, documenting a transformation pipeline, or mapping an API call chain for teammates or future you. The workflow dispatches a codebase explorer to build a structural model focused on calls and transformations, then converts that model into sequenceDiagram syntax with opinionated limits (participants as modules, conditional branches, transformation notes). The result is paste-ready documentation you can drop into READMEs, ADRs, or onboarding notes—especially valuable when agents have generated code you do not yet fully mental-model.
- Two-step workflow: codebase explorer agent first, then Mermaid sequenceDiagram generation
- Sequence-diagram rules: 8–10 participants max, activate/deactivate, alt/else, Notes for transformations
- Models request/response with ->> and -->> at module/component level (not per-function noise)
- Handles circular calls once with a note instead of cluttering the diagram
- Answers “what happens when X is called?” from traced function calls and inter-module communication
Data Flow by the numbers
- 77 all-time installs (skills.sh)
- Ranked #705 of 1,879 Documentation skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill data-flowAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 77 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Generate a Mermaid sequence diagram that shows how requests and data move between modules so you can explain or debug flows without drawing diagrams by hand.
Who is it for?
Best when you're documenting API or CLI request paths, agent tool chains, or ETL-style pipelines before handoff or refactor.
Skip if: Skip if you only need a static C4 or deployment topology with no request-level tracing, or repos where an explorer agent cannot read the relevant scope.
When should I use this skill?
Tracing how a request flows through the system, understanding data transformation pipelines, documenting API call chains, or answering what happens when X is called.
What you get
You get a bounded, readable Mermaid sequence diagram you can commit to docs or share with reviewers after the explorer pass and diagram rules are applied.
- Mermaid sequenceDiagram block showing module-level request/response flow
- Structural notes for transformations and conditional branches
By the numbers
- Limits diagrams to 8–10 participants maximum
- Uses a two-step workflow: explore codebase then generate Mermaid
Files
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
sequenceDiagramfor request/response flows - Participants are modules or components (not functions)
- Arrows show data direction:
->>for calls,
-->> for returns
- Use
activate/deactivatefor long-running operations - Add
Note overfor data transformations - Limit to 8-10 participants maximum
- Use
alt/elsefor 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
sequenceDiagramsyntax 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
Related skills
How it compares
Use instead of ad-hoc chat explanations of call stacks when you want a repeatable sequence-diagram artifact tied to explored code structure.
FAQ
Who is data-flow for?
Developers using Claude Code, Cursor, or similar agents who need sequence-level documentation of how requests traverse their system.
When should I use data-flow?
During Build when tracing a user request through services, documenting a data transformation pipeline, or mapping an API call chain before you ship or onboard someone new.
Is data-flow safe to install?
Review the Security Audits panel on this Prism page and your repo policy before running any agent that explores the filesystem; the skill itself outputs diagram text rather than executing your app.