shipwright

Lightweight SDLC for ongoing changes in completed Shipwright projects. TRIGGER when: user asks to add a feature, fix a bug, change behavior, refactor, update, modify, or improve code in a project that has shipwright_run_config.json with status complete. Also when user describes a bug report, enhancement request, or any code-level change to a finished project. DO NOT TRIGGER when: user asks about project setup (/shipwright-project), planning (/shipwright-plan), initial build (/shipwright-build), deployment (/shipwright-deploy), running tests (/shipwright-test), or non-code tasks like documentation questions. Also DO NOT TRIGGER when the pipeline is still in_progress — those changes belong to the current pipeline phase.

Parses Conventional Commits from git history, generates Keep-a-Changelog entries, creates version tags, and opens PRs. TRIGGER when: user wants to create a changelog, generate release notes, tag a version, create a release, bump version number, create a PR for release, or review unreleased changes. DO NOT TRIGGER when: user asks to write code (/shipwright-build), run tests (/shipwright-test), fix a bug (/shipwright-iterate), deploy (/shipwright-deploy), create requirements (/shipwright-project), plan implementation (/shipwright-plan), or design UI (/shipwright-design).

On-demand detective audit for cross-artifact consistency plus auto-background compliance documentation. Scans specs, plans, configs, event log, ADRs, and compliance reports for drift that the preventive Canon gate and reactive Phase-Quality Stop hook don't catch. Still produces the traceability matrix, test evidence, change history, SBOM, and dashboard when auto-background updates fire between phases. TRIGGER when: user wants a cross-artifact consistency audit, drift check, FR coherence verify, ADR integrity check, compliance report, audit documentation, traceability matrix, test evidence report, SBOM, or change history. Also when user asks about regulatory compliance, audit readiness, or documentation for auditors. DO NOT TRIGGER when: user asks to write code (/shipwright-build), run tests (/shipwright-test), fix a bug (/shipwright-iterate), deploy (/shipwright-deploy), create requirements (/shipwright-project), plan implementation (/shipwright-plan), or design UI (/shipwright-design). If the user just wants

Implements code from /shipwright-plan sections using TDD, code review, Conventional Commits, and feature branch workflow. TRIGGER when: user wants to implement a planned section, build code from a plan, implement a feature from a section file, start coding a planned component, continue building the next section, write test cases for a section, implement tests, or create unit tests from a plan. DO NOT TRIGGER when: user asks to fix a bug or make a quick change to existing code (/shipwright-iterate), run existing tests (/shipwright-test), deploy (/shipwright-deploy), create requirements (/shipwright-project), plan implementation (/shipwright-plan), or design UI (/shipwright-design). Also DO NOT TRIGGER for ad-hoc code changes that don't reference a section file — use /shipwright-iterate instead.

Security scanning with automated remediation. Supports two backends — OSS (Semgrep + Trivy + Gitleaks, local) or Aikido (cloud SaaS). Findings flow back to the coding agent for fixes. Use after /shipwright-build or standalone. Trigger: 'security scan', 'aikido', 'semgrep', 'vulnerabilities'.

Generate UI mockups from IREB specs as standalone HTML. Screens + user flows, iteratable via chat. TRIGGER when: user wants to create UI mockups, design screens, generate HTML wireframes, create visual designs, design a user interface, preview a layout, create user flow diagrams, iterate on a screen design, or process design feedback. DO NOT TRIGGER when: user asks to implement code (/shipwright-build), run tests (/shipwright-test), fix a bug or change code (/shipwright-iterate), deploy (/shipwright-deploy), create requirements (/shipwright-project), or plan implementation details (/shipwright-plan).

"Profile-aware test runner. Runs unit tests, smoke tests, Playwright E2E, and optional security scans.\nTRIGGER when: user wants to run tests, execute test suite, check if tests pass, run unit tests, run E2E tests, run integration tests, verify test results, check design fidelity, visual comparison, compare UI with mockup, verify against design, run visual tests, or fix failing tests.\nDO NOT TRIGGER when: user asks to write new code or implement a section (/shipwright-build), fix a bug by changing code (/shipwright-iterate), deploy (/shipwright-deploy), create requirements (/shipwright-project), plan implementation (/shipwright-plan), or design UI (/shipwright-design)."

Onboards an EXISTING repository (brownfield) into the Shipwright SDLC. Analyzes the codebase (stack, routes, conventions, git history), generates CLAUDE.md + .shipwright/agent_docs + planning specs + compliance artifacts + all six shipwright_*_config.json, and writes a baseline E2E suite from a Playwright crawl when possible. After completion, /shipwright-iterate takes over for all future changes. The phase-router UserPromptSubmit hook is plugin-owned (registered in shipwright-iterate's own hooks.json); no project-level install is performed. TRIGGER when: user wants to onboard a brownfield repo, add Shipwright to an existing project, run /shipwright-adopt, import a legacy codebase, or bootstrap Shipwright on code that already exists. DO NOT TRIGGER when: shipwright_run_config.json already exists (use /shipwright-iterate), the user is starting a fresh greenfield project (use /shipwright-project), or the task is a normal SDLC operation (build/test/deploy/changelog/compliance).

"Creates detailed implementation plans from spec files via research, interview, external LLM review, and TDD approach. Generates section-based plans for /shipwright-build.\nTRIGGER when: user wants to plan implementation, create an implementation plan, break down a spec into sections, plan how to build something, create a technical design, generate build sections, or plan test strategy for a spec.\nDO NOT TRIGGER when: user asks to implement or write code (/shipwright-build), run tests (/shipwright-test), fix a bug or make a small change (/shipwright-iterate), deploy (/shipwright-deploy), define requirements (/shipwright-project), or design UI mockups (/shipwright-design)."

Deploy to Jelastic (Infomaniak) with smoke test verification, rollback support, and Supabase migrations. TRIGGER when: user wants to deploy, push to production, deploy to dev, deploy to staging, publish the application, rollback a deployment, or check deployment status. DO NOT TRIGGER when: user asks to write code (/shipwright-build), run tests (/shipwright-test), fix a bug (/shipwright-iterate), create a changelog (/shipwright-changelog), create requirements (/shipwright-project), plan implementation (/shipwright-plan), or design UI (/shipwright-design).

Decomposes project requirements into well-scoped planning units for /shipwright-plan. Generates CLAUDE.md and .shipwright/agent_docs for the target project. TRIGGER when: user wants to start a new project, define requirements, create a project spec, decompose a project into components, scaffold a new application, set up project structure, analyze requirements, or extend an existing project with new features that need full planning. DO NOT TRIGGER when: user asks to implement code (/shipwright-build), run tests (/shipwright-test), fix a bug or make a small change (/shipwright-iterate), deploy (/shipwright-deploy), generate a changelog (/shipwright-changelog), plan implementation details for an existing spec (/shipwright-plan), or design UI mockups (/shipwright-design).

"Pipeline Initializer & Phase Coordinator for the Shipwright SDLC pipeline. Writes the run spec, then DRIVES every phase from this one conversation via a phase-runner subagent.\nTRIGGER when: user wants to run the full pipeline, start the complete SDLC process, build an entire application from scratch, or resume an interrupted pipeline. Also when user says 'shipwright run' or 'start the pipeline'.\nDO NOT TRIGGER when: user asks for a specific phase only (project, design, plan, build, test, deploy, changelog, compliance), or asks to fix/change/add something to an existing project (/shipwright-iterate). If the user wants only ONE phase, trigger that specific skill instead."

Grade any git repository against the Control Grade rubric (A–F), read-only and deterministic. Projects a cold repo's git history + tests + configs into the same GradeInputs the compliance dashboard uses and reuses the shared scoring engine unchanged. Underivable dimensions render honest n/a and become the "what adopting Shipwright would light up" story. TRIGGER when: the user wants to grade a repository, score a repo's control posture, run /shipwright-grade, get a Control Grade for a local path, or evaluate how traceable/tested/controlled a codebase is. DO NOT TRIGGER for: writing code (/shipwright-build), fixing a bug (/shipwright-iterate), a full compliance audit of THIS project (/shipwright-compliance), or deployment (/shipwright-deploy).

Start local dev server and show browser preview URL. Available after first build split. TRIGGER when: user wants to see the app, preview changes, check the UI, open the browser, show me the app, start the dev server, or view the running application. DO NOT TRIGGER when: user asks to write code, run tests, deploy, or any other SDLC phase.