Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.

Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.

Run shell commands and analyze output with validated summaries. Use for build logs, test output, or any command with substantial output. Protects context by returning concise summaries with...

Spawns subagents with configurable tool access that return just the answers without flooding your context. Use for summarizing extensive git history, comparing across multiple repositories in...

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call...

Context and working knowledge for Calci’s prediction-market domain, which is powered by Kalshi. Use this skill whenever the user asks about Calci prediction markets, Kalshi markets, tickers, order...

North star guidance for the agent-resources project. Use this skill to understand project context, get inspiration for development decisions, and resolve uncertainty about feature priorities or...

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...

Generate and validate the ADR index for this repo (docs/adr/*.md -> docs/adr/index.json). Use when updating ADRs, checking ADR metadata format, or keeping agent context small; enforce...

Before product-market fit, your job is to learn as fast as possible. That means doing things that won't scale - manual onboarding, concierge service, recruiting users one by one. Paul Graham's...

What makes founders succeed? Paul Graham has observed thousands of founders and distilled patterns. Relentlessly resourceful. Fierce nerds. Earnest. These traits matter more than credentials or...

Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object',...

Acquisition is expensive. Retention is profitable. Customer success is the discipline of ensuring customers achieve their desired outcomes with your product - which leads to retention, expansion,...

Good taste is knowing what is good. Craft is making it real. Together they separate products people tolerate from products people love. Paul Graham's essays explore how taste develops and why it...

Parallelizes codebase exploration and research by launching multiple subagents simultaneously. Use when exploring codebases, researching questions, investigating bugs, gathering context from...

Investigate a topic with Grok 4.1 via OpenRouter and generate a Markdown report with a timeline, verifiable claims, and sources (web/X). Use it when the user says “investiga…”, “haz research…”,...

Most successful startups pivoted. Instagram was a check-in app. Slack was a game. YouTube was a dating site. The ability to recognize when to pivot and execute the pivot without losing momentum is...

Founders face unique challenges in how they work. Maker vs manager schedule conflicts. Default alive vs dead math. Time and money slowly leaking away. Effective founders develop systems for...