cat ~/热门

parallel-agents @namesreallyblank

Parallel Agent Orchestration

performance-audit @namesreallyblank

Web performance testing via Playwright MCP - Core Web Vitals, Lighthouse

perplexity-search @namesreallyblank

AI-powered web search, research, and reasoning via Perplexity

pint-compute @namesreallyblank

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

playwright-automation @namesreallyblank

Browser automation via Playwright MCP - screenshots, interactions, DOM inspection

premortem @namesreallyblank

Identify failure modes before they occur using structured risk analysis

project-hooks @namesreallyblank

Create and manage project-specific Claude Code hooks

prove @namesreallyblank

Formal theorem proving with research, testing, and verification phases

qlty-check @namesreallyblank

Code quality checks, formatting, and metrics via qlty CLI

qlty-during-development @namesreallyblank

QLTY During Development

ralph @namesreallyblank

Setup Ralph autonomous coding loop (external fresh-context pattern)

recall-reasoning @namesreallyblank

Search past reasoning for relevant decisions and approaches

refactor @namesreallyblank

Code refactoring workflow - analyze → plan → implement → review → validate

reference-sdk @namesreallyblank

Check reference SDK implementations using btca ask

release @namesreallyblank

Release preparation workflow - security audit → E2E tests → review → changelog → docs

repoprompt @namesreallyblank

Use RepoPrompt CLI for token-efficient codebase exploration

research-agent @namesreallyblank

Research agent for external documentation, best practices, and library APIs via MCP tools

research-external @namesreallyblank

External research workflow for docs, web, APIs - NOT codebase exploration

research @namesreallyblank

Document codebase as-is with thoughts directory for historical context

review @namesreallyblank

Comprehensive code review workflow - parallel specialized reviews → synthesis

rlm-process @namesreallyblank

Process large contexts using RLM (Recursive Language Model) patterns - chunking, filtering, recursive sub-calls

router-first-architecture @namesreallyblank

Router-First Architecture

search-hierarchy @namesreallyblank

Search Tool Hierarchy

search-router @namesreallyblank

Choose the right search tool for each query type