Development plugins

Autonomous GitHub Project board runner: super-board, super-build, super-qa, super-review, super-collect, visual, git-sync, ui-refine-loop, pr-security-review (security pass on every PR; onboard adds Cloudflare's on-demand security-audit). After install, run /super-board onboard to add the guard hooks, .claude/bin scripts and workflows a plugin cannot ship.

9 skills

Docker-authored knowledge skills for AI coding agents across Dockerfiles, Compose, Docker Agent, Docker Sandboxes, and safe Docker workflows.

13 skills

텍스트 설명 한 줄로 캐릭터 + 동작 애니메이션 + 8방향 스프라이트 세트를 생성하고 게임 엔진용 번들로 내보내는 스킬.

1 skill

Zero-config goal-to-tasks engine for Claude Code, plugin-native rebuild with CDD-verified execution

11 skills · 1 agent · 1 MCP server · hooks

Turn a gameplay video into a playable Three.js game with every asset generated on fal, checked side by side and playtested

1 skill

Requires Claude Code v2.1.143+ (older versions reject the strict plugin-manifest displayName field — run `npm install -g @anthropic-ai/claude-code@latest` to upgrade; see docs/06-guide/cc-compatibility.guide.md). Vibecoding Kit - PDCA + Sprint Management + CTO-Led Agent Teams + Living Context System + 43 PM frameworks. v2.1.14 5 differentiations (Memory Enforcer, Layer 6 Defense, Sequential Dispatch, Effort-aware, Heredoc-bypass) — a sixth, PostToolUse continueOnBlock, was withdrawn in v2.1.37 (ENH-432) after the field was measured to belong to prompt-type hook definitions, which bkit has none of. v2.1.15 pdca-status.json fix. v2.1.16 4 GitHub issues (Quality Gates UX). v2.1.17 5/12~5/20 contract red 8-day class close. v2.1.18 Issues #100/#101/#102 — Sprint Trust UX Fix. v2.1.19 Quality Maturation Sprint — 5 sub-sprint master plan (S1 Self-Dogfooding Enablement / S2 Convention Restoration / S3 Sprint Report Maturity / S4 External Dogfooder Lifecycle / S5 Sprint Maturity Index) + ENH-318 차별화 7/7 정식 편입 + Real User Hall of Fame 도입 + 첫 외부 dogfooder entry @pruge. v2.1.20 Marketplace Recovery — minimum CC v2.1.143 advisory (F1+F4) + plugin manifest 21-key whitelist CI gate (F5+F6, ENH-322) + claude plugin validate wire (F7, ADR 0006 § Empirical Validation Gate) + cc-regression R3-321 (F8, ENH-321) + SessionStart CC version detection (F10, ENH-323) + ADR 0011 Plugin Manifest Schema Compliance Policy + Hall of Fame @bj (#2 external dogfooder, Lifecycle 5-stage). v2.1.21 Issue Response — Session Title Isolation (#111: per-session sessions[sessionId] cache map + GC + legacy migration + stable session tag for parallel-window disambiguation) + Sprint Output Enforcement (#113: lib/sprint/executive-summary.js sprint-shape + scripts/sprint-skill-stop.js run-export Stop hook + SKILL_HANDLERS sprint registration + advancePhase phaseTransitionSummary + /sprint status·watch human-readable display) + ADR 0012 Sprint Stop Hook Output Enforcement. v2.1.24 Skill Namespace Hardening — Issu

44 skills · 2 commands · 34 agents · 2 MCP servers · hooks

Conventional Git automation, advanced repository management, and GitFlow workflow automation for feature, hotfix, and release branches with post-finish cleanup

8 skills

AI-first Git CLI automation — atomic AI commits, co-change relations, autonomous git health agent, pre-tool hook safety, and workspace initialization

4 skills · 1 agent · hooks

Retrieve code context for any repo, library, or natural-language query via DeepWiki, Context7, Exa, git clone, and web search+fetch

2 skills · 1 agent · 3 MCP servers

Fast code search for Android/Kotlin/Java, iOS/Swift/ObjC, Dart/Flutter, TypeScript/JavaScript, Rust, Ruby, C#, PHP, Python, Go, Perl, C++, Protocol Buffers, and WSDL/XSD projects

1 skill · 7 commands · hooks

Interviews you about what to build, then generates a self-contained blueprint another Claude Code instance can build from autonomously — acceptance criteria and a runnable verify command on every build step. Greenfield and brownfield.

1 skill · 6 commands · 3 agents

Elixir/Phoenix/LiveView development with specialist agents, Iron Laws, and Tidewave MCP integration

50 skills · 26 agents · hooks

Elixir Rewrite Architect — rewrite an app from any language or framework (Rails, Django, PHP, Node, Go, JVM, .NET, Rust, Python scripts, CLIs, workers) into Elixir the Elixir way. Analyzes features and why each mechanism exists, decides the compatibility bar, designs a Phoenix/Ecto/Oban/OTP architecture, then hands vertical slices to /phx:plan and verifies parity.

6 skills · 7 agents

Compatibility namespace for the Elixir/Phoenix plugin's /ecto:* commands

2 skills

Based on the proxy gateway service of dubbo-go, it solves the problem that the external protocol calls the internal Dubbo cluster. At present, it supports HTTP and gRPC[developing].

Spec-driven development with research, requirements, design, tasks, autonomous execution, and epic triage. Fresh context per task.

5 skills · 16 commands · 10 agents · hooks

Spec-driven development using GitHub spec-kit methodology. Constitution-first approach with specify, plan, tasks, and implement phases.

4 skills · 5 commands · 6 agents · hooks

Claude Code plugin for sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Provides slash commands and skills for recipe browsing, cluster management, and multi-node orchestration.

3 skills · 8 commands

Build Vue and Nuxt apps with the maz-ui ecosystem instead of re-implementing it: maz-ui skill, MCP server (docs, component APIs, icons, Tailwind theme tokens, code review) and a hook that reviews every edited file

1 skill · 1 MCP server · hooks

Build a SaaS app with coding agents on Next.js, Supabase, Clerk and Netlify: the path from idea to production, multi-tenant authorization, the production choices for Supabase and Clerk, environments and secrets, product design, transactional email, uptime monitoring, cookieless analytics, legal pages, remote MCP servers, ChatGPT plugins and embedded Claude agents.

14 skills

Ship AI-built apps: document the app, review it for correctness, security and performance, have a fresh reviewer clear every push that deploys and every release, round after round, prove it with a test harness that fakes the right side, and release through a gate with the owner's go. Where the free pm-ai-shipping plugin moved: turn that one off once this is installed.

11 skills

Make your own agent setup reliable: instruction files that are met at the moment they apply, rules held by hooks instead of prose, status that survives context compaction, the handover the next session starts from, a session's friction turned into a setup fix, and the Windows shell traps that break agents.

6 skills

Build, evaluate, and optionally evolve code and Jev decision pipelines.

1 skill

Project-scoped 1C rules installer for Claude Code, OpenCode and Kilo CLI. Calls install.ps1; does not dump on-demand rules into .claude/rules/.

2 skills · 2 commands · hooks

This plug-in contains agentic engineering skills for Qt software development, such as Qt C++/QML code review, QML coding, or Qt C++/QML code documentation skills, plus the hosted Qt Documentation MCP server for live Qt API lookups. The skills have been tested with frontier LLMs from the Claude, Gemini, and GPT LLM families. These agentic development skills use AI and can make mistakes. Always double-check the output carefully.

13 skills · 2 agents · 1 MCP server

Lets Claude see SwiftUI: renders #Preview blocks to PNG on any iPhone or iPad, light or dark, through the Prefire MCP server, without Xcode Previews.

1 skill · 1 MCP server

Run mobile changes on Revyl cloud devices and verify them with screenshots and semantic validation through the Revyl CLI.

17 skills · 1 agent · 1 MCP server · hooks

HTML and CSS language servers from VS Code

LSP

Ada/SPARK and GPR language server

LSP

Lean 4 language server with per-file Lake project-root detection (lake serve, or lean --server for standalone files), elan toolchain discovery, multi-project and worktree routing, and bounded memory (Lean workers are closed when idle or past a cap). Bundles the lean-goal CLI for proof goals, candidate tactics and Mathlib-wide lemma search.

1 skill · LSP