Debugging
Debugging utilities
using superpowers
GitHubUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
caveman
GitHubUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
scaffold exercises
GitHubCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
write a skill
GitHubCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
writing fragments
GitHubGrilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.
scaffold exercises
GitHubCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
caveman
GitHubUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
write a skill
GitHubCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
backend patterns
GitHubBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
content engine
GitHubCreate platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
deep research
GitHubMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
frontend patterns
GitHubFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
nextjs turbopack
GitHubNext.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
video editing
GitHubAI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
x api
GitHubX/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
nextjs turbopack
GitHubNext.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
backend patterns
GitHubBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
frontend patterns
GitHubFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
agent architecture audit
GitHubエージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。
agent harness construction
GitHubAI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。
agent introspection debugging
GitHubキャプチャ、診断、封じ込め回復、内省レポートを使用した AI エージェント障害のための構造化された自己デバッグワークフロー。
agent payment x402
GitHubタスクごとのバジェット、支出コントロール、ノンカストディアルウォレットを備えた x402 決済実行を AI エージェントに追加します。agentwallet-sdk を通じて Base をサポートし、OKX Payments / OKX エージェント決済プロトコルを通じて X Layer をサポートします。
agentic os
GitHubClaude Code 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。
api design
GitHubリソース命名、ステータス コード、ページネーション、フィルタリング、エラー応答、バージョン管理、およびレート制限を含む REST API デザイン パターン。