claude

Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.

Spawn 5 Opus subagents with randomly-generated distinct personas to debate a problem from multiple angles. Use when exploring UX decisions, architecture choices, or any decision that benefits from diverse perspectives arguing creatively.

Configure Karabiner-Elements keyboard remapping using Goku EDN syntax. Use when creating keybindings, layers, simlayers, app-specific shortcuts, or modifying karabiner.edn.

Bundle code context for AI. ALWAYS use --limit 49k unless user explicitly requests otherwise. Use for creating shareable code bundles and preparing context for LLMs.

Build Raycast extensions with React and TypeScript. Use when the user asks to create a Raycast extension, command, or tool.

Create new Agent Skills for Claude Code. Use when user wants to create a skill, add a new capability, document a CLI workflow, or asks how skills work.

Build durable, resumable TypeScript workflows with Vercel Workflow DevKit. Use when creating long-running processes, AI agents, background jobs, multi-step pipelines, webhooks, or event-driven systems. Triggers on "workflow", "durable", "resumable", "use workflow", "use step".

Track tasks and issues using the bd CLI. Use for task management, sprint planning, dependency tracking, and project organization. Replaces TodoWrite.

Contextual learning system that remembers patterns and rules from past sessions. Use to get relevant context before tasks, record outcomes, and build a personal playbook of coding patterns.

Extract design data from Figma files. Use for getting design tokens, component specs, and generating code from Figma designs.

Capture and review lessons learned from coding sessions. Use to record insights, read past lessons, and improve over time.

Manage Linear issues and workflows. Use for viewing, creating, and updating Linear issues, and integrating with development workflow.

Persistent knowledge storage using basic-memory CLI. Use to save notes, search memories semantically, and build context for topics across sessions.

Ultimate Bug Scanner - scan code for bugs across 7 languages (JS/TS, Python, Go, Rust, Java, C++, Ruby). Use before commits to catch null safety issues, security holes, async bugs, and memory leaks.

Unified debugging workflow enforcing root cause protocol. Investigate → Understand → Reason → Fix. Use when debugging bugs, errors, or unexpected behavior.

Inter-agent communication for multi-agent workflows. Use when multiple agents need to coordinate, share information, or reserve resources.

Generate technical articles and documentation using AI. Use for writing blog posts, documentation, and technical content.

Generate ideas and explore possibilities with AI. Use for creative problem solving, generating alternatives, and expanding on concepts.

Bundle and share code as gists or markdown. Use to create shareable code bundles, extract imports, and create GitHub gists.

Generate and manage changelogs from git history. Use for release notes, tracking breaking changes, and maintaining project history.

Browser automation using Puppeteer or Playwright. Use for web testing, screenshots, form filling, and automated browser interactions.

Query multiple AI agents in parallel for diverse perspectives. Use when you want multiple viewpoints on a question, to compare approaches, or to find consensus among AI models.

Database operations for SQLite, PostgreSQL, and MySQL. Use for queries, schema inspection, migrations, and AI-assisted query generation.

Manage dependencies with npm/yarn/pnpm. Use for auditing vulnerabilities, checking outdated packages, understanding dependency trees, and upgrading packages safely.

Design system and token management. Use for managing design tokens, colors, typography, and maintaining design consistency.

Preview and analyze git diffs with AI explanations. Use to understand changes before committing, get impact analysis, and compare branches or commits.

Use Gemini AI for research, analysis, summarization, web search, and complex reasoning. Use when you need AI-powered research, code analysis, content summarization, or web search with synthesis.

Debug and investigate code issues using search and AI analysis. Use when stuck on bugs, tracing execution flow, or understanding complex code.

Manage long-running agent sessions. Use for tracking progress in extended tasks, maintaining context across long sessions, and managing multi-step workflows.

Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.

Performance profiling and optimization. Use for benchmarking code, analyzing performance, running Lighthouse audits, and finding hotspots.

Chain multiple operations together in pipelines. Use for multi-step workflows, combining research with analysis, and complex automated tasks.

Code refactoring with AI assistance. Use for modernizing code, converting JavaScript to TypeScript, class to hooks conversions, and systematic renaming.

Create repository context bundles and code maps. Use to share codebase context, generate documentation, and understand project structure.

Comprehensive research combining web search and AI synthesis. Use for deep research on topics, comparing technologies, investigating libraries, and finding GitHub issues related to problems.

Web crawling and scraping with analysis. Use for crawling websites, security scanning, and extracting information from web pages.

Get unstuck when blocked on a problem. Use when you've tried multiple approaches without success, or when debugging has hit a wall.

Generate tests using AI and run test suites. Use for generating unit tests, running coverage reports, and mutation testing.

Deep multi-framework reasoning using Gemini. Use for complex problem analysis, challenging ideas, and evaluating multiple options with structured thinking.

Manage tmux sessions for background processes. Use to run long-running commands, manage multiple terminals, and capture output from background processes.