code-simplification
Use after implementing features, before claiming a phase is complete, when reviewing AI-generated code, or when code feels overly complex. Also use when you…
Use when reviewing code under Codex — verifying spec compliance, conducting quality review after a build, or checking that an implementation matches its plan. Trigger when the user says "review this", "review the implementation", "does this match the plan", "check the code
$ npx -y skills add lgbarn/shipyard --skill shipyard-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/shipyard-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when reviewing code under Codex — verifying spec compliance, conducting quality review after a build, or checking that an implementation matches its plan. Trigger when the user says "review this", "review the implementation", "does this match the plan", "check the code
name: shipyard-review description: Use when reviewing code under Codex — verifying spec compliance, conducting quality review after a build, or checking that an implementation matches its plan. Trigger when the user says "review this", "review the implementation", "does this match the plan", "check the code quality", or after a Shipyard build completes. This is the Codex inline-sequential form of the reviewer agent.
This is the reviewer role from Shipyard's `/shipyard:build` flow, adapted for Codex. In Claude Code a fresh reviewer subagent runs after the build; here you adopt the reviewer role yourself in this context.
**Degradation note:** because the same context that built (or read) the code now reviews it, the review is less independent than a fresh-context subagent. Counter this: re-read the actual files and the plan from disk before judging — do not rely on your memory of what you intended.
You are a **review-only** role. You MUST NOT edit code, run builds, or change state. You produce findings only.
Compare the implementation against its `PLAN.md` (or the issue's acceptance criteria):
**If Stage 1 fails, stop and report. Do not proceed to Stage 2** — the deviations must be fixed first.
Only after Stage 1 passes. Assess correctness, security, error handling, and clarity.
Every finding is specific and actionable: `path:line`, what's wrong, why it matters, and the remediation. Vague feedback ("could be improved") is not allowed. Classify severity:
failing tests.
If the same issue recurs across the change, flag it once with "applies throughout" and escalate its severity. End with a one-line verdict: blocked / needs-work / ship-ready.
A Claude Code plugin for structured project execution. Plan work in phases, build with parallel agents and TDD, review with security audits and quality gates, and ship with confidence.
Repo: lgbarn/shipyard
Use after implementing features, before claiming a phase is complete, when reviewing AI-generated code, or when code feels overly complex. Also use when you…
Use when shipping features with public interfaces that lack docs, generating documentation, updating README files, writing API docs, creating architecture…
Use when starting feature work that needs a branch, creating worktrees for isolation, making atomic commits during development, or completing a development…
Import a handwritten spec document into Shipyard, replacing brainstorming. Use when a freeform spec, requirements, or design document exists.
Import a spec-kit feature spec into Shipyard, replacing brainstorming. Use when a spec-kit feature directory exists with spec.md.
Use when working with Terraform (.tf, .tfvars), Ansible (playbooks, roles, inventory), Docker (Dockerfile, docker-compose.yml), Kubernetes (manifests, Helm…