METHODOLOGY

A repeatable, verifiable pipeline, driven by a PRD

Every exhibit runs the same closed loop. Here's the shape of it, and the tooling that makes it repeatable.

01

Explore

Scan the repo, read context, frame the problem with the agent.

02

PRD

Write a PRD: scope, tasks, and acceptance criteria.

03

Implement

The agent writes code and tests against the PRD.

04

Verify

Lint, typecheck, Lighthouse, CI, then loop back.

iterate When verify fails, loop back to implement; Claude Design ⇄ UI runs on every visual change.

60–90s demo, coming soon

A short walkthrough of the loop in action: PRD → implement → verify → ship.

The kit

An open-source agentic-dev-kit: Claude Code skills, a custom MCP server, and PRD templates, dropped into each repo. The portfolio is built by dogfooding it end to end.

The PRD loop

Every feature starts as a behavioral PRD: scope, tasks, and acceptance criteria. The agent implements against it, and a failing check loops straight back to implement.

Claude Design → UI

Visual work flows from a Claude Design handoff (tokens + components) into the live UI. A design-sync skill keeps the shadcn token contract and the implementation aligned on every visual change.

MCP + skills

A project MCP server exposes schema introspection, exhibit scaffolding, and deploy status. Skills (prd / implement / verify / design-sync) drive the repeatable steps.

Closed-loop verify

Lint, typecheck, tests, Lighthouse, and CI form the gate. Nothing ships until the loop closes green, and the proof is the public GitHub history.