Archify

What it does

Archify combines diagram instructions with schemas, a renderer and validation tooling. It selects among architecture, workflow, sequence, data flow, lifecycle, ERD, class, tree, timeline and waterfall representations. For a code-backed diagram, the source asks the author to inspect repository evidence so the visual does not invent relationships.

When to use it

• Explain an API request across several services.
• Map database entities and key relationships.
• Turn a process or architecture question into a shareable HTML artifact.

Step-by-step workflow

1. Choose the diagram type that matches the question.
2. Read the required schema and authoring references.
3. Gather evidence and write the candidate with accurate nodes, relationships and labels.
4. Use the documented finalize workflow and treat failed gates as failures.
5. Inspect readability when visual review is needed, then deliver the HTML and relevant validation evidence.

Example request

Use Archify to explain checkout requests in this repository as a sequence diagram. Inspect the actual request path, include error branches supported by the code and distinguish external services. Produce standalone HTML with validation results. Do not add services or retries that are absent from the evidence.

Worked example

A checkout sequence should show when inventory and payment are called, including the actual failure path. A plausible-looking arrow is not evidence. Trace the code first, then verify that labels remain readable and that the exported artifact opens correctly.

What you get

A standalone HTML diagram or explainer with validation receipts appropriate to the workflow.

How to evaluate the result

• Confirm the requested artifact or behavior is actually delivered, with evidence appropriate to this workflow.
• Repeat the example on your own inputs and check the stated limits; repository popularity is not an execution test.
• Verify important facts, permissions and failure paths before adopting the result.

What you need

The Archify package, Node runtime, the selected schema/reference files and access to source evidence; browser/export prerequisites depend on the chosen path.

Setup and activation

Follow the publisher README for your specific client and preserve the complete selected skill folder, including companion references and scripts. Claude Code, Codex and other hosts may use different plugin or Agent Skills installation paths. This guide does not establish that every host has the same tools. Security-scan the exact version before installation; this website installs or executes nothing.

Limits and considerations

Automated schema and browser checks do not prove the architecture is factually correct. The source excludes dashboards from this skill’s intended explainer scope. Rendering dependencies and update behavior need review before installation.

Related workflows

• Use a task-specific validation workflow to check the final result.
• Review companion scripts and references before adding this skill to an agent.

License and reuse

Apache-2.0 at repository level; inspect per-file terms and separately licensed assets before reuse.

Further reading

• Publisher setup and compatibility instructions
• Reviewed skill version (immutable commit)