cat ~/トップ

swarm @Yeachan-Heo

N coordinated agents on shared task list with SQLite-based atomic claiming

tdd @Yeachan-Heo

Test-Driven Development enforcement skill - write tests first, always

ultrapilot @Yeachan-Heo

Parallel autopilot with file ownership partitioning

ultraqa @Yeachan-Heo

QA cycling workflow - test, verify, fix, repeat until goal met

ultrawork @Yeachan-Heo

Activate maximum performance mode with parallel agent orchestration for high-throughput task completion

writer-memory @Yeachan-Heo

Agentic memory system for writers - track characters, relationships, scenes, and themes

agent-context-isolation @parcadei

Agent Context Isolation

agent-orchestration @parcadei

Agent Orchestration Rules

agentic-workflow @parcadei

Agentic Workflow Pattern

agentica-claude-proxy @parcadei

Guide for integrating Agentica SDK with Claude Code CLI proxy

agentica-infrastructure @parcadei

Reference guide for Agentica multi-agent infrastructure APIs

agentica-prompts @parcadei

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

agentica-sdk @parcadei

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

agentica-server @parcadei

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

agentica-spawn @parcadei

Spawn Agentica multi-agent patterns

ast-grep-find @parcadei

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

async-repl-protocol @parcadei

Async REPL Protocol

background-agent-pings @parcadei

Background Agent Pings

braintrust-analyze @parcadei

Analyze Claude Code sessions via Braintrust

braintrust-tracing @parcadei

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

build @parcadei

Workflow orchestrator that chains existing skills for feature development

cli-reference @parcadei

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

commit @parcadei

Create git commits with user approval and no Claude attribution

complete-skill @parcadei

A complete skill for E2E testing