ship-flow

Ask which skill or flow fits your situation. A router over the skills this plugin ships.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Maintenance check for installed Claude Code extensions (marketplace plugins, skills.sh skills, gstack, and repo-embedded skills). Produces one report answering whether upstream is still maintained, whether the local install is current, and what's unused. Use when the user asks to audit or clean up skills/plugins, find unused skills, check whether things are up to date, check for divergence, or when a weekly heartbeat nudges.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or says "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Grill the user relentlessly about a plan, decision, or idea until you reach shared understanding. Use when the user wants to stress-test their thinking, uses any "grill" trigger phrase, or when another skill needs the interview loop.

Compact the current conversation into a handoff document for another agent to pick up.

Audits the maturity of a repo's self-improvement loop harness (verifier=ceiling, Inner/Outer/Meta loops, vector-backed loop memory, skill/tool usage) via six parallel forensic investigation lanes, producing an L0-L5 scorecard and a prioritized improvement list saved as a report. Use when the user asks for a "harness maturity audit", a "loop engineering checkup", a self-improvement loop audit, or wants a periodic checkup after a milestone/epic completes.

Land an already-implemented, already-verified small fix through this repo's real gates (worktree isolation → verify → PR→integration → PR→release → deploy), stopping for human confirmation at the merge and deploy checkpoints. Use when the user wants to ship/merge/release a change that's already coded and verified (not a new feature to build — that's ship-feature), or asks to land/deploy a fix that just needs to reach production safely.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a terminal app or shareable HTML demo for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Use when you need to resolve an in-progress git merge/rebase conflict.

Turn loop outcomes into a verified-lessons memory — record what fixed a failure, recall it next time, and promote recurring lessons into skills/guidelines. Use when the user wants the loop to learn from past runs, capture a fix as a reusable lesson, see why runs keep failing, or decide what to codify into a skill or CLAUDE.md.

One-time interactive setup for this plugin in a consuming repo — interviews the user, writes `.claude/ship-flow.config.json`, and installs (or offers to install) a CLAUDE.md constitution, a CI workflow, and branch protection from this plugin's templates/. Use once per repo, when a repo first adopts ship-flow, or when re-running to fill in config that was skipped the first time.

End-to-end feature delivery when the user asks to take a feature, bug or tracked issue from plan to an open PR, or to ship/deliver/land a feature. Isolate, plan, build, verify, review and open the PR; stop for human merge. Research, local edits and routine Git synchronization use their own bounded procedure. Post-merge improvements require authorized scope.

Test-driven development with a bounded red-green loop and review-stage refactoring. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Teach the user a new skill or concept, within this workspace.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a reviewable PRD; publish to the specified tracker destination only when requested. Use when user wants to create a PRD from the current context.

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Compare this repo's vendored skills against upstream and report drift; apply bounded backports only when authorized. Use when checking for upstream drift, when a vendor-sync heartbeat nudges, or when the user asks whether vendored skills are current.

Stop. That last message did not land: re-pitch it.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.