shipwright

Use when reviewing AI-generated code, apps, workflows, skills, PRDs, GitHub repos, or automation outputs before accepting or publishing them. Trigger this whenever the user asks whether an agent's work is actually usable, complete, safe, non-hallucinated, or ready to merge.

Use when checking whether a web app, localhost build, demo URL, landing page, AI-generated frontend, or GitHub project actually works in the browser before shipping. Trigger this whenever the user asks to test, verify, inspect, QA, launch, debug UI, check console errors, check mobile responsiveness, or validate a project in a real browser.

Use when scanning GitHub Trending, GitHub Explore, or hot repositories to identify useful tools, product opportunities, skill/workflow ideas, and hype traps for builders.

Use when preparing a GitHub repository, skill pack, template, CLI, MCP server, or open source developer tool for public release. Trigger this whenever the user asks to publish, launch, tag a release, improve GitHub presentation, choose topics, write release notes, or make a repo more discoverable.

Use when converting a rough product, workflow, agent, skill, or developer tool idea into a lean PRD with scope, user stories, acceptance criteria, and launch plan.

Use when auditing a GitHub repository, open source project, skill pack, template, CLI, MCP server, or developer tool before publishing or promoting it.

Use when converting a PRD, product brief, or feature spec into GitHub-ready issues with labels, acceptance criteria, dependencies, and verification steps.

Use when testing whether a GitHub README, open source project, skill pack, CLI, template, MCP server, or developer tool can be installed and used by a first-time user. Trigger this whenever the user asks to check setup docs, installation instructions, onboarding, quickstart, examples, or whether a repo is easy to adopt.

Use when turning a hot repository, GitHub trend, market signal, or competitor into a differentiated product idea, MVP scope, and positioning plan.

Use when turning a repeated agent workflow, prompt sequence, operating procedure, or domain process into a concise Codex or Claude skill.