Claude Code プラグイン
公開されている Claude Code marketplace からの 5,968 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
公開されている Claude Code marketplace からの 5,968 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
.claude-plugin/marketplace.json を含むリポジトリを提出すると、すべての plugin を掲載します。
marketplace を提出するOneScience / OneSkills skills for AI-native scientific research workflows, coding, runtime submission, debugging, and environment setup.
Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code, check whether the work is actually finished, brainstorm wide with a different model per cognitive frame, or just ask all of them something.
productivityGABBE core: 44 agent skills for the everyday engineering loop — spec, plan, TDD, review, research, security, memory and audit, with Brain and Loki mode. Add the gabbe-* topic plugins from the same marketplace for the rest of the 214.
GABBE ai skills (11): AI and agent engineering: multi-agent systems, agent UIs and protocols, context engineering, RAG evaluation, LLM-as-judge and reasoning patterns.
GABBE architecture skills (29): software architecture: patterns, C4 and diagrams, domain models, event-driven and microservice design, governance, migration and scalability.
GABBE brain skills (13): Brain Mode internals: cognitive architectures, active inference, global workspace, working and episodic memory, self-improvement.
GABBE coding skills (28): coding: language performance, testing strategies (browser TDD, property-based, metamorphic, chaos), evals, UI generation and diagram canvases.
GABBE ops skills (30): operations: deployment, environments, observability, incidents, performance, cost and release management.
GABBE product skills (21): product: requirements review, user research, story maps, business case, estimation, accessibility, sustainability and change management.
GABBE security skills (21): security, privacy and AI safety: access control, secrets, cryptography, prompt-injection defence, red teaming, compliance and legal review.
All structured thinking skills in one install: root-cause analysis, trade-offs, pre-mortems, prioritization, estimation, creative and critical thinking, plus a selector that picks the right method.
A markdown brain that gives your AI coding tools judgment and rigor. Skills: init, build, debug, performance, qa, interview, learn, signature, persona, route, lint, clarify, deepen, double-check, deprecate, roadmap, assess, constitution, living-docs, specify, blueprint, breakdown, checklist, analyze, converge, prototype, explain, prompt, quarantine, report, handoff, levelup, help + agents: architect, code-reviewer, refactorer, tech-scout. Experimental (v0.33.2).
Attribution, lift test readouts and media budget planning from your WorkMagic data
38 native skills for engineering, operations, and cross-cutting development practices — see README for the full list.
Lauren Tan's pstack & Poteto Mode engineering workflow for Claude Code: evidence-first, minimal blast radius, TDD, and rigorous verification. Full v0.15.0+ upstream sync.
developer-toolsPoteto Mode workflow for Claude Code: disciplined engineering, systematic decomposition, and rigorous verification.
developer-toolsDrop-in replacement and superset for pstack-claude with complete upstream v0.15.0+ parity, SessionStart hooks, and multi-agent support.
developer-toolsDevelopment experts for 10 programming languages (Python, TypeScript, JavaScript, Go, Rust, C++, Kotlin, PHP, Lua and Perl), plus FastAPI and Node.js specialists and a refactoring agent.
Socratic onboarding, 4-stage reflexive coding, methodology hooks, specialized agents and the Lotus Wisdom MCP for the sandwich methodology.
Evaluate prompts and skills through parallel execution comparison in git worktrees