Plugins

Tools for auditing and maintaining The Workshop's skills, presets, and distribution boundaries

7 Claude Skills for running workshops that produce decisions: intention framing, agenda design, pre-work emails, facilitator run sheet, live capture of post-it walls, 48-hour synthesis, and the facilitation retro.

Skills for scaffolding a Python/FastMCP repo (uv + just + ruff + ty), building Prefab/MCP App UIs, and generative UI.

Workspace management framework: structured markdown workspace for specs, context, memories, and issues with wikilinks, frontmatter relationships, and agent-executable issue decomposition.

Voice-friendly workspace discovery and task routing for compatible web and content projects.

Automatic daily work-sync log — PostToolUse hook captures gh pr/issue create/merge/close, and a companion skill lets Claude log research/ops/checkpoint events into a dated markdown note (feeds standups via Obsidian/Logseq/plain markdown)

Route engineering work (/go), capture and consume handoff briefs, and drain the work queue unattended

Git worktree management using crewchief CLI

Manage git worktrees using git gtr (create, copy files, navigate)

from builtby-win/skills

from franchiseai/claude-code-plugins

from iknite/claude-code-marketplace

Block risky Git commands and notify on configurable native-edit auto-grants.

worktree-integrator の初期セットアップ（設定ファイル・dev サーバー定義・MCP 登録・検証）を案内するスキルと、環境不調を一次調査する読み取り専用の診断エージェント

A git worktree workflow for running multiple Claude Code sessions in parallel — no restarts, no manual checkouts. Built on native worktrees, it covers the full lifecycle from spinning up an isolated worktree to finishing it through a guarded, never-squashed PR merge, with a live dashboard of in-flight work and deterministic guards against squash merges and committing unresolved conflicts.

Replaces Claude Code's built-in worktree — aligns with native git worktree where CC diverges (HEAD base, origin/* auto-tracking) and adds layers native lacks: .worktreeinclude/.worktreelink for gitignored files with a /worktree-setup skill that scans and builds them, upstream-aware removal guard, idempotent re-entry.

Set up parallel Git worktree-based development environments with shared config files via symlinks.

Git worktree-based parallel development environment setup (Japanese version).

Git worktree 기반 태스크 격리 개발 — worktree 생성/제거, main 보호, 미커밋 방지

from brendanwhit/superintendent

from K-shir0/claude-code

Law-governed git worktree protocol for agents: standardized lifecycle (create/announce/isolate/sync/deliver/cleanup), non-negotiable laws (one worktree = one branch = one task, announce before create, no cross-worktree writes), a per-project registry, and /wt-* commands.

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) and automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions).

Git worktree management guidance and activity-tracking hooks for parallel AI agent workflows.

Route Claude Code's auto-created git worktrees through worktrunk so background and --worktree sessions inherit project hooks (env symlinks, installs, port allocation).

Work in a Worldbuilding project: a fiction encyclopedia of characters, settings, factions, and lore.

Wormhole cross-chain messaging and token transfers — NTT (Native Token Transfers) framework, VAA (Verified Action Approvals), guardian network, automatic and manual relayers, Wormhole Queries for cross-chain reads, and Standard Relayer integration. Covers Wormhole SDK, contract interfaces, and deployment across Ethereum, Solana, Arbitrum, Base, and Optimism.

Wormhole cross-chain messaging and token transfers — NTT (Native Token Transfers) framework, VAA (Verified Action Approvals), guardian network, automatic and manual relayers, Wormhole Queries for cross-chain reads, and Standard Relayer integration. Covers Wormhole SDK, contract interfaces, and deployment across Ethereum, Solana, Arbitrum, Base, and Optimism.

Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?", "how should I approach X?", "quick script vs. robust system", "how much architecture?", "how much do I build here?". Fires even without "poc" or "right-size" — any time effort and complexity of what to build are being weighed.

Personal ops lab. Logged-in-browser-first triage (Gmail / Teams / Slack / school + work portals), mnemos memory system, delivery skills (commit-curator, pr-handoff, flow-conductor), 10-hook safety net (PII / secret scanner, send confirm, late-night guard, profile mismatch detector, audit logger).