agentleFS
jgamaraalvjgamaraalv/delivery-loop/.claude/skills/architecture-blueprint-generator/SKILL.md

architecture-blueprint-generator

Skill0 starsChanged 5 months agoMITView on GitHub

Analyze a codebase and generate Project_Architecture_Blueprint.md — detected stacks and architecture patterns, diagrams, layers, cross-cutting concerns, extension guidance. Use to document, map, or blueprint a project's architecture or keep it consistent.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read a reference only when writing that part of the blueprint:

    line 45

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Architecture Blueprint Generator

Analyze the architectural patterns actually implemented in the codebase and write a comprehensive Project_Architecture_Blueprint.md that serves as the definitive reference for maintaining architectural consistency and guiding new development. Document what the code does, not theoretical patterns — every claim should trace to project structure, dependencies, or configuration.

Options

Defaults below; adjust any of them when the user specifies:

OptionDefaultAlternatives
Technology stackAuto-detect.NET, Java, React, Angular, Python, Node.js, Flutter, …
Architecture patternAuto-detectClean, Microservices, Layered, MVVM, MVC, Hexagonal, Event-Driven, Serverless, Monolithic, …
DiagramsC4UML, Flow, Component, none (textual description instead)
Detail levelDetailedHigh-level, Comprehensive, Implementation-Ready
Optional sectionsAll includedDrop implementation patterns, extensibility, code examples, or ADRs on request

Workflow

  1. Detect — identify the stack(s) and architectural pattern(s) from project/config files, dependencies, folder organization, and dependency flow (detection signals in references/blueprint-structure.md §1).
  2. Write the core sections — overview, visualization, components, layers, data architecture, cross-cutting concerns, service communication, testing, deployment, governance, and the blueprint-for-new-development guide, following references/blueprint-structure.md section by section.
  3. Add the per-stack section for each detected technology, using the checklists in references/technology-patterns.md.
  4. Add the optional sections that apply — implementation patterns, extension/evolution guidance, code examples, ADRs — per references/optional-sections.md.
  5. Close with the generation date and recommendations for keeping the blueprint updated as the architecture evolves.

References

Read a reference only when writing that part of the blueprint:

  • references/blueprint-structure.md — the 12 core sections in full: detection signals, per-section content checklists, the new-development guide · read in step 2.
  • references/technology-patterns.md — stack-specific pattern checklists (.NET, Java, React, Angular, Python + how to derive others) · read in step 3.
  • references/optional-sections.md — implementation patterns, extension/evolution patterns, code examples, ADRs · read in step 4.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.