cat ~/トップ

webapp-testing @castle-x

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend...

writing-plans @castle-x

Use when you have a spec or requirements for a multi-step task, before touching code

writing-skills @castle-x

Use when creating new skills, editing existing skills, or verifying skills work before deployment

xlsx @castle-x

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and...

database-analyzer @netresearch

Analyze and optimize database schemas, identify performance issues, and suggest improvements. Use when working with...

accessibility-audit @namesreallyblank

Automated accessibility testing via Playwright MCP and axe-core

agent-context-isolation @namesreallyblank

Agent Context Isolation

agent-orchestration @namesreallyblank

Agent Orchestration Rules

agentic-workflow @namesreallyblank

Agentic Workflow Pattern

agentica-claude-proxy @namesreallyblank

Guide for integrating Agentica SDK with Claude Code CLI proxy

agentica-infrastructure @namesreallyblank

Reference guide for Agentica multi-agent infrastructure APIs

agentica-prompts @namesreallyblank

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

agentica-sdk @namesreallyblank

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

agentica-server @namesreallyblank

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

agentica-spawn @namesreallyblank

Spawn Agentica multi-agent patterns

ast-grep-find @namesreallyblank

AST-based code search and refactoring via ast-grep MCP

async-repl-protocol @namesreallyblank

Async REPL Protocol

background-agent-pings @namesreallyblank

Background Agent Pings

braintrust-analyze @namesreallyblank

Analyze Claude Code sessions via Braintrust

braintrust-tracing @namesreallyblank

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

bye @namesreallyblank

Save session state (continue working or exit safely)

cli-reference @namesreallyblank

Claude Code CLI commands, flags, headless mode, and automation patterns

complete-skill @namesreallyblank

A complete skill for E2E testing

completion-check @namesreallyblank

Completion Check: Verify Infrastructure Is Wired