agentleFS
fnayoufnayou/dotfiles/.claude/skills/create-architecture/SKILL.md

create-architecture

Skill2 starsChanged 5 months agoMITView on GitHub

Produces a numbered architecture document under docs/architecture/. Locate and read the relevant PRD under docs/prd/. Do not proceed without it. For each significant design choice, state the tradeoff: List explicit architecture decisions made. These become the basis for ADRs in docs/decisions/. List what could go wrong: Briefly note how the architecture supports future growth without requiring a redesign. Write the architecture document to a numbered file: Use the next available number in the sequence. Reference the related PRD by number.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use asset-spec, create-control-manifest and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • MRCalderon3DSkill

    art-bible

    Define a visual direction that artists, UI, technical art, and marketing can execute consistently.

    Also in 10 projects that use this

  • +9 more from lilangMax

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 2

    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:

    Write the architecture document to a numbered file:

    line 68
  2. Distinctive:

    Use the next available number in the sequence.

    line 75

“Common” is measured: kept by at least 6 in 10 of the 12 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

Skill: create-architecture

Produces a numbered architecture document under docs/architecture/.

When to use

  • A PRD has been approved and needs to be translated into a structural design.
  • The user requests an architecture proposal for a new package category or layout change.
  • An existing architecture decision needs revisiting.

Process

Step 1 — Read the PRD

Locate and read the relevant PRD under docs/prd/. Do not proceed without it.

Confirm:

  • What is the goal?
  • What is in scope and out of scope?
  • What platform(s) are targeted?
  • What safety requirements must the architecture respect?

Step 2 — Propose structure

Define:

  • Directory layout (use ASCII tree when helpful).
  • Package organization (common / macOS / Arch).
  • File naming conventions.
  • Stow package strategy when relevant.

Step 3 — Identify tradeoffs

For each significant design choice, state the tradeoff:

Option A: [description]
  Pro: [benefit]
  Con: [cost or risk]

Option B: [description]
  Pro: [benefit]
  Con: [cost or risk]

Decision: [chosen option and reason]

Step 4 — Define decisions

List explicit architecture decisions made. These become the basis for ADRs in docs/decisions/.

Step 5 — Define risks

List what could go wrong:

  • Platform-specific risks (behavior differs on macOS vs. Arch).
  • Stow conflict risks.
  • Privacy risks.
  • Reversibility risks.

Step 6 — Define future extensibility

Briefly note how the architecture supports future growth without requiring a redesign.

Step 7 — Produce the document

Write the architecture document to a numbered file:

docs/architecture/0001-stow-layout.md
docs/architecture/0002-macos-arch-separation.md

Use the next available number in the sequence. Reference the related PRD by number.

Architecture document template

# Architecture: [Title]

**Number:** 0001
**Status:** Draft | Approved | Superseded
**Date:** YYYY-MM-DD
**PRD:** [link or number]

## Context

[What was requested and what state the repository is in]

## Proposed Structure

[Directory tree or layout description]

## Design Decisions

### Decision 1: [title]
[Tradeoff analysis and chosen option with reason]

### Decision 2: [title]
[Tradeoff analysis and chosen option with reason]

## Risks

- [risk]

## Extensibility

[How this design supports future growth]

## Open Questions

- [unresolved item]

## Recommended Next Step

[What the Planner should do with this]

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.