Productivity plugins

Verify task completion before finishing work. Catches incomplete work, bugs, and quality issues.

1 command · 1 agent

Hooks that forward subagent, MCP and session activity to the Agent Office server, plus the /agent-office:office command.

1 command · hooks

秘書から始める仮想組織スキル。3ステップで即運用開始、部署は必要に応じて自然に増える。

1 skill

8-step research methodology with independent Agent verification for systematic analysis, fact extraction, and verifiable conclusions

1 skill

Three reflexive levers that cut agent token cost — less code (YAGNI/stdlib-first), less prose, denser agent-to-agent handoffs (ESON/compact-JSON) — plus on-demand satellites (review, eco, gain, compress) and a hive of read-only subagents. Auto-intensity lite/full/ultra; safety-critical paths stay exact.

14 skills · 3 agents · hooks

Connect Claude to your Well financial data over a hosted OAuth MCP, with skills for building a compte de résultat / balance sheet, reconciling transactions, and querying the financial graph correctly.

9 skills · 1 MCP server · hooks

While Claude works, the chat shows one tall pixel-art card instead of every step.

2 commands

Sets the reasoning effort for every prompt automatically and shows a prompt-cache countdown with one-click Compact.

1 command

Adopt and audit production-proven implementation patterns.

2 skills

Connect Claude Code to Stash — stream activity to history, inject agent memory, collaborate in workspaces.

hooks

Persistent reviewed research and engineering runtime

3 skills · 1 MCP server

超圧縮コミュニケーションモード。日本語に最適化された原始人スキル。

7 skills · 6 commands · 3 agents · hooks

Analyzes and improves prompts using 31 frameworks. Intent-based selection routes to the right framework — from ultra-minimal (APE) to agentic (ReAct).

1 skill

Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.

17 skills · hooks

Compile markdown knowledge files or codebases into a topic-based wiki. Implements Karpathy's LLM Knowledge Base pattern.

1 skill · 12 commands · hooks

พอดี — พูดไทยสั้นๆ ลด output token 60-75% โดยไม่เสีย technical accuracy

2 skills · hooks

旅行数据源调研与响应式行程页面生成插件

5 skills · 4 MCP servers

Puts Onyx first for context retrieval in every Claude Code session

1 skill · 1 MCP server · hooks

BankMCP™ for Claude Code: /bank:setup walks you through installing it locally, /bank:deploy through hosting it; plus a skill with account mapping, categorisation rules and a monthly review format.

3 skills · 1 MCP server

9 skills covering ComfyUI custom node development with the V3 and V1 APIs

9 skills

Local image, video, music-video and Film Crew generation, voice and music, upscaling, LoRA training, Hugging Face model onboarding, agent swarms, local knowledge, code intelligence and supervised outreach, driven from Claude Code through the guaardvark MCP server.

15 skills · 1 MCP server

Safely upgrade DeepSeek Harness plugins with breaking change guides, migration recipes, and real-world examples from community practice

12 skills

Complete research methods for in-depth analysis, long-form reports and revisions.

1 skill · 1 MCP server · hooks

Makes the agent answer in ASD-STE100 Simplified Technical English.

Search jobs, tailor resumes, draft cover letters, and track applications via Workopia.

1 MCP server

Website QA tool built for coding agents (Claude Code, Cursor). 300+ rules across SEO, performance, security, accessibility & agent experience: audit from the CLI, fix findings in code, publish reports, and connect over MCP.

2 skills · 1 MCP server

5 lifecycle hooks (Stop quality gate, SessionStart context injection, PreToolUse security guards, PostToolUse continuous QA, UserPromptSubmit thinking nudge) + 11 context modes + 3 skills. Battle-tested across 3,000+ sessions.

3 skills · 1 command · hooks

Compose skill for AI coding agents: seven skills for Jetpack Compose and Compose Multiplatform (MVI, Koin, Navigation 3, Ktor, Room)

7 skills

Portable OrchestKit workflows for Codex: brainstorm, explore, implement, assess, verify, review pull requests, and render inline diagrams with glyph.

7 skills · hooks

Deploy, operate, and diagnose a self-hosted Portal relay, on any Linux host or through Oracle Cloud, Hetzner Cloud, AWS, and Cloudflare DNS.

7 skills