Code2Flow

Analyze codebase structures and source files to generate clear, accurate Mermaid.js diagrams that visualize system architecture and workflows.

Security Scan

The skill is an instruction-only Mermaid diagram generator that asks the agent to analyze user-provided code and produce Mermaid.js diagrams; its requirements and instructions are consistent with that purpose and it does not request extra permissions or installs.

Purpose & Capability

Name/description (Code2Flow / generate Mermaid diagrams from code) match the SKILL.md: it instructs the agent to analyze provided code/dirs and output diagrams. The skill requires no binaries, env vars, or external installs, which is proportionate for an instruction-only diagramming helper.

Instruction Scope

Runtime instructions are narrowly scoped to analyzing directory structures and code snippets supplied by the user and producing Mermaid diagrams with a structured markdown response. The SKILL.md does not instruct reading system files, environment variables, or sending data to third-party endpoints.

Install Mechanism

There is no install spec and no code files to write or execute. As an instruction-only skill this has a minimal on-disk footprint and low installation risk.

Credentials

The skill declares no required environment variables, credentials, or config paths. No unrelated secrets or credentials are requested, which is appropriate for its function.

Persistence & Privilege

always:false (default) and no persistent installs or configuration changes are requested. The skill does not request to modify other skills or global agent settings.

Assessment

This skill appears coherent and low-risk as written, but keep these practical precautions: (1) Do not paste private secrets, credentials, or proprietary data into prompts you want to remain confidential — the skill's purpose is to analyze any code you provide. (2) The skill source and homepage are unknown; prefer skills with a public repo or maintainer identity if you need auditability. (3) Validate generated Mermaid output before publishing, and be cautious if you enable any agent/network access that could transmit pasted code externally. (4) If you require stricter guarantees, run the skill only in an environment with no outbound network access and avoid sending sensitive code to the agent.

You are the Auto Architect, an advanced AI Software Architect specializing in code analysis and visual documentation. Your primary directive is to analyze directory structures and source code files provided by the user, and explain the system's architecture by generating highly accurate Mermaid.js diagrams.

Core Execution Rules:

1. Deep Analysis: Thoroughly analyze the data flow, dependencies, and logical architecture between provided files.
2. Mandatory Visualization: You MUST include at least one valid mermaid code block in your response. Choose the most appropriate diagram type:
   • graph TD / flowchart for user journeys and logical flows.
   • sequenceDiagram for API interactions or inter-component communication.
   • classDiagram or erDiagram for database schemas and data models.
3. Structured Output: Always present your findings using clear markdown formatting, utilizing headings, bullet points, and brief architectural summaries BEFORE presenting the Mermaid diagram.
4. Syntax Validity: Ensure your Mermaid syntax is 100% valid. Escape special characters inside node text and avoid syntax that breaks standard Mermaid renderers.