brainstorm-to-brief
claudeWide-to-narrow design workflow: exploration to polished design brief
50 skills · 4 commands · 9 agents
The multi-seat development pattern: a long-lived reviewer seat that owns every fresh review and re-check in a repository and posts one parseable verdict per head. Lead and setup seats follow.
Plugin shipyard from marketplace dotclaude in fairchild/dotclaude. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
leadThe lead seat — one long-lived session that owns a repository's queue, writes the briefs, dispatches implementers into their own worktrees, reads verdicts, and merges. Run as /shipyard:lead to take the seat.
reviewerThe reviewer seat — one long-lived session that owns every fresh review and re-check in one repository, probes the claims it is given, and posts one parseable verdict per head. Run as /shipyard:reviewer to take the seat.
setupFit the seats to one repository — detect its gate, tests, checks and venue, write .claude/shipyard.md, and leave the seats better configured than their defaults. Run as /shipyard:setup once per repository, or again when the repository's tooling changes.
"${CLAUDE_PLUGIN_ROOT}/scripts/seat-resume.sh" pre-compact
"${CLAUDE_PLUGIN_ROOT}/scripts/seat-resume.sh" start
Wide-to-narrow design workflow: exploration to polished design brief
50 skills · 4 commands · 9 agents
Claude Code configuration management for global and project settings
50 skills · 4 commands · 9 agents
Generate images via OpenAI, Google Imagen 4, Nano Banana Pro, fal.ai Flux
50 skills · 4 commands · 9 agents
Semantic versioned releases with AI changelogs, worktree-aware
50 skills · 4 commands · 9 agents
Guide for creating effective Claude Code skills with validation
50 skills · 4 commands · 9 agents
Lets the main thread compact at a moment it chooses, with instructions for the summary and its reasoning kept; runs /compact from a timer after its turn, then submits a prompt so the next turn starts on its own.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.