Nm Cartograph Workflow Diagram

Generate workflow diagrams showing process steps, decision points, and state transitions

Security Scan

The skill's instructions, requirements, and behavior are coherent for a workflow-diagram generator, but it will read repository files and send generated diagrams to a renderer service — so be mindful of sensitive content leakage and the renderer's trustworthiness.

Purpose & Capability

Name and description (generate workflow diagrams) match the SKILL.md: it instructs exploring the codebase for process steps and producing Mermaid flowcharts, then rendering them. No unrelated binaries, credentials, or installs are requested.

Instruction Scope

Runtime instructions explicitly dispatch a 'codebase-explorer' agent to explore the requested scope (Makefiles, CI configs, lifecycle methods) and then call an MCP renderer with the generated mermaidCode. This is appropriate for diagram generation, but it means the skill will read repository files and transmit generated code/prompt to an external rendering service — which could expose sensitive content if the explored scope contains secrets or private data. The SKILL.md uses a placeholder [scope] so callers should limit scope carefully.

Install Mechanism

Instruction-only skill with no install spec and no code files. Nothing is written to disk by an install process in the skill bundle itself.

Credentials

The skill does not request environment variables, credentials, or config paths. The absence of required secrets aligns with the described functionality.

Persistence & Privilege

always is false and autonomy is allowed by default. Autonomous invocation plus the codebase-explorer and MCP calls increases blast radius (the agent can run this flow without human intervention). This is expected for an agent skill, but users should be aware that it can run and transmit diagram content autonomously if allowed.

Assessment

This skill appears to do what it says: explore code, generate Mermaid, and render via an MCP. Before installing or running it: (1) avoid using it on repos that contain secrets, API keys, or sensitive CI variables (the skill will read CI configs and other files); (2) confirm the Mermaid renderer (MCP) is a trusted internal service — rendering sends the generated diagram and prompt outside your repo; (3) when invoking, explicitly set a narrow 'scope' (specific folders/files) rather than allowing whole-repo exploration; (4) if you need higher assurance, prefer generating Mermaid locally (no external renderer) or inspect the downstream renderer's privacy/retention policy. Confidence is medium because the skill is instruction-only (no code to inspect) and the host/handling of MCP calls cannot be verified from the SKILL.md alone.

Night Market Skill — ported from claude-night-market/cartograph. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Workflow Diagram

Generate a Mermaid flowchart showing process workflows, pipelines, or state machines from code or documentation.

When To Use

• Visualizing CI/CD or deployment pipelines
• Documenting multi-step development workflows
• Mapping state machines or lifecycle processes
• Answering "what steps happen when X runs?"

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 process steps, conditional logic, state
transitions, and pipeline stages for a workflow diagram.
Look for: Makefiles, CI configs, hook chains, command
sequences, and lifecycle methods.

Step 2: Generate Mermaid Syntax

Transform the structural model into a Mermaid flowchart with decision nodes and process steps.

Rules for workflow diagrams:

• Use flowchart TD for sequential processes
• Use flowchart LR for pipelines with parallel tracks
• Use shapes to distinguish step types:
  • [Rectangle] for process steps
  • {Diamond} for decision points
  • ([Stadium]) for start/end states
  • [[Subroutine]] for sub-processes
  • ((Circle)) for join/sync points
• Use -->|label| for transition conditions
• Group parallel tracks into subgraphs
• Color-code by outcome:
  • Default for happy path
  • Dotted (-.->) for error/fallback paths
  • Thick (==>) for critical path
• Limit to 20 nodes maximum

Example output:

flowchart TD
    start([Start: PR Created])
    lint[Run Linters]
    test[Run Tests]
    review{Code Review}
    approve[Approved]
    changes[Request Changes]
    merge([Merge to Main])

    start --> lint --> test
    test --> review
    review -->|pass| approve --> merge
    review -->|fail| changes -.-> lint

Step 3: Render via MCP

Call the Mermaid Chart MCP to render:

mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram
  prompt: "Workflow diagram of [scope/process]"
  mermaidCode: [generated syntax]
  diagramType: "flowchart"
  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 workflow stages and decision points (2-3 sentences).