Collaborative solution brainstorming and technical decision-making. Activate when users want to explore ideas, evaluate approaches, discuss architecture, or make design decisions. Focus on dialogue and refinement - NO implementation until explicit user confirmation.
Activate for brand voice, visual identity, messaging frameworks, asset management, and brand consistency. Use when creating branded content, establishing tone of voice, managing marketing assets, validating brand compliance, or maintaining brand standards across marketing materials.
Activate for marketing campaign planning, execution, and optimization. Use when launching campaigns, coordinating multi-channel efforts, managing budgets, or tracking campaign performance.
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
Browser-based asset gallery for managing marketing assets. Visual grid with filter/search, brand context sidebar, and actions (preview, edit, generate). R2-ready manifest for future cloud sync. Use when browsing assets, managing content library, or generating new assets with brand context.
Activate for content strategy, editorial calendars, content pillar mapping, blog planning, and content audit. Use when planning content programs, creating editorial workflows, or building topic clusters.
Creative direction for digital marketing and advertising. Use when creating campaign concepts, visual directions, video scripts, ad copy, brand content, or selecting creative styles. Includes 55 creative style templates with copy-ready keywords, color palettes, music/voiceover guidance. Covers: minimalist, maximalist, nostalgic (80s/90s), cinematic, humor, UGC, luxury, futuristic, emotional storytelling, data-driven personalization. References include color psychology, voiceover styles (conversational, authoritative, inspirational, playful), audio/music trends, visual design trends 2025-2026.
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.
Entry point for design tasks. Routes to brand-guidelines (brand identity, voice, assets), design-system (tokens, component specs), or ui-styling (implementation). Use for design decisions, visual consistency, design system creation.
Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions, managing Docker containers and images, setting up CI/CD pipelines, optimizing cloud infrastructure costs, implementing global caching strategies, working with cloud databases, or building cloud-native applications.
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
Activate for email campaigns, newsletters, drip sequences, automation flows, and email copywriting. Use when creating email content, designing automation workflows, or optimizing email performance.
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications, OR when they provide screenshots/images/designs to replicate or draw inspiration from. For screenshot inputs, extracts design guidelines first using ai-multimodal analysis, then implements code following those guidelines. Generates creative, polished code that avoids generic AI aesthetics.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.