agentleFS
Sign inStart free
HarambeeAIHarambeeAI/bayes-ship/skills/ship-architect/SKILL.md

ship-architect

Skill1 starsChanged 7 months agoMITView on GitHub

Define system architecture from approved PRD and research. Produces architecture doc, data model, API contracts, ADRs. Requires user approval. Must run after ship-spec.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read PRD.md + RESEARCH.md + PROJECT.md.

    line 14
  2. Very specific:

    Create .claude/state/ROADMAP.md — phases ordered by dependency from the PRD.

    line 30
  3. Distinctive:

    After approval, present build mode selection:

    line 32
  4. Very specific:

    Update progress.json: set phases.architecture.status to "approved".

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Architecture — System design

Pre-condition

.claude/state/PRD.md must exist and be approved (check progress.json).

Process

  1. Read PRD.md + RESEARCH.md + PROJECT.md.
  2. Produce ARCHITECTURE.md with:
    • Tech stack with rationale for each choice
    • System architecture (component-level: frontend, backend, database, external services)
    • Data model (full schema definitions with types, relations, constraints)
    • API endpoints (method, path, request/response shape, auth requirements)
    • Infrastructure layout (hosting: Railway, Vercel, Supabase, etc.)
    • Architecture Decision Records for non-obvious choices:
      ADR-001: [Decision title]
  Context: [Why this decision was needed]
  Decision: [What was decided]
  Rationale: [Why this option over alternatives]
  Consequences: [What this means for implementation]
  3. Save to .claude/state/ARCHITECTURE.md and .claude/state/decisions.md.
  4. Create .claude/state/ROADMAP.md — phases ordered by dependency from the PRD.
  5. Present architecture to the user for approval (approve / adjust).

  6. After approval, present build mode selection:

    "How do you want to proceed with implementation? A. Guided mode (default) — I plan each phase and wait for your go. B. Autonomous mode — I build everything without stopping. /bayes-ship:ship-auto C. Semi-autonomous — I pause between phases for a checkpoint. /bayes-ship:ship-auto --checkpoints"

  7. Update progress.json: set phases.architecture.status to "approved".
  8. Output next step based on user's build mode choice.

Gate

User MUST explicitly approve architecture before any implementation.

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.

Check your setup, free