Verify Phase D doc updates are accurate. Binary pass/fail gate — checks stat accuracy, file path validity, code-doc sync, completeness. Runs after /update-docs.
Branch-aware audit orchestrator. On main — scans whole project, opens tracker issue. On feature branch — scopes to diff, auto-fixes, stages changes.
Create distinctive, production-grade frontend interfaces. Rejects generic AI aesthetics (purple gradients, Inter font, glassmorphism). Design direction first, then implementation.
Merge current PR after CI passes. Waits for all checks, squash merges, deletes branch, switches to main.
Build multiple files/pages in parallel using subagents. Handles task division, shared file coordination, and build verification. Conflict-free by design.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Production-grade Claude Code skills for shipping quality code.
/ship
├── Audit find issues, auto-fix Critical/Major
├── Review code + UX review, fix until gates pass
├── Docs sync documentation, verify accuracy
└── Ship push branch, open PR
↓
your CI/CD deploys after merge
One command. Four quality gates. No silent failures.
In any Claude Code session:
/plugin marketplace add cloverink/shipwright
/plugin install shipwright@shipwright
Then invoke any skill with /ship, /push, /review-full, etc.
Symlink (for development on this repo itself)
git clone https://github.com/cloverink/shipwright.git
cd shipwright
./scripts/link-skills.sh
Manual copy (into a single project)
# All skills
cp -r skills/* /path/to/your-project/.claude/skills/
# Or pick individual ones
cp -r skills/ship /path/to/your-project/.claude/skills/
# List every shipped skill (sanity check)
./scripts/list-skills.sh
All 12 skills live flat under skills/ for easy discovery. Sorted below by /ship pipeline order, then standalone utilities.
| Skill | Phase | Model | What it does |
|---|---|---|---|
/ship | — | Opus | Full A→R→D→S pipeline orchestrator with gate enforcement |
/audit-full | A | Sonnet | Branch-aware audit: whole-project on main, diff-scoped on feature |
/review-full | R | Sonnet | Auto-detect scope (FE/BE/both), dispatch to code + UX review |
/review-code-fix | R | Opus | Code review → fix loop (max 3 rounds, gate >9/10) |
/review-ux-fix | R | Opus | UX review → fix loop (max 3 rounds, gate 10/10) |
/update-docs | D | Sonnet | Sync documentation with code changes |
/review-docs | D | Opus | Verify doc updates are accurate (binary pass/fail gate) |
/push | S | Sonnet | Smart commit + push + auto-create PR (blocks push to main) |
/merge-pr | post-merge | Haiku | Wait for CI → squash merge → cleanup branch |
/parallel-builder | — | Sonnet | Build multiple files in parallel, conflict-free coordination |
/frontend-design | — | Opus | Distinctive UI design (rejects generic AI aesthetics) |
/skill-creator | — | Sonnet | Guide for creating effective Claude Code skills |
Short answer: if you don't know, use /review-full. It auto-detects scope and dispatches to the right workers.
flowchart TD
User([You]) -->|default| RF["/review-full<br/>dispatcher"]
User -.->|skip auto-detect| RC["/review-code-fix"]
User -.->|skip auto-detect| RU["/review-ux-fix"]
User -.->|skip auto-detect| RD["/review-docs"]
RF -->|any code in diff| RC
RF -->|frontend in diff| RU
RF -->|docs-only diff| RD
Ship["/ship Phase R"] --> RF
ShipD["/ship Phase D"] --> RD
classDef entry fill:#e0e7ff,stroke:#4f46e5,color:#1e1b4b
classDef worker fill:#fef3c7,stroke:#d97706,color:#451a03
classDef user fill:#d1fae5,stroke:#059669,color:#022c22
class RF entry
class RC,RU,RD worker
class User,Ship,ShipD user
Decision matrix:
| Situation | Use |
|---|---|
| 🟢 Default for any review | /review-full |
| Force code review only (skip UX even on FE diff) | /review-full --code-only |
| Force UX review only (skip code) | /review-full --ux-only |
| Backend-only PR, want to bypass scope detection | /review-code-fix directly |
| Pure CSS/spacing polish, no logic changes | /review-ux-fix directly |
| Verify docs only (after editing docs, or as audit) | /review-docs directly |
Rule of thumb: /review-full covers most cases. The direct workers (/review-code-fix, /review-ux-fix, /review-docs) are escape hatches for when you know exactly what you want.
flowchart TD
Start([/ship]) --> A
npx claudepluginhub cloverink/shipwright --plugin shipwrightUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).