GODMODE

Machine learning model training with HuggingFace. Fine-tuning LLMs, dataset creation, GPU selection, training monitoring. Use for training custom models. Don't use for using pre-trained models via API.

Estimates project cost at market rates. Scans codebase, counts APIs, integrations, and complexity. Shows what the project would cost without AI. Use for pitches and ROI demonstrations.

Marketing and conversion optimization. Landing page CRO, copywriting, positioning, GTM strategy, A/B testing. Don't use for product development or technical decisions.

Product management frameworks. PRD writing, user stories, OKRs, roadmap, TAM/SAM/SOM analysis, competitive research. Don't use for technical implementation.

Scraping specific platforms with ready connectors. Google Maps businesses, Twitter trends, YouTube subtitles, Instagram/TikTok content. Use for platform-specific data collection.

Data analysis from external services. Connects to Google Sheets, Notion, HubSpot via Composio. Builds charts, runs queries, generates insights. Don't use for database queries.

Temporal knowledge graph for long-term memory. Facts have timestamps and expiry. Tracks how decisions evolve over time across projects. Use for Stage 3 deep memory. Don't use for simple key-value storage.

Structured data extraction from multiple websites into normalized tables. Returns JSON with consistent schema across sources. Use when you need STRUCTURED data, not raw content.

Web scraping with Firecrawl and Bright Data. JavaScript rendering, anti-bot bypass, structured data extraction. Use for market research, competitor analysis, documentation. Don't use for authenticated/private content.

UI component vocabulary for precise communication. Correct naming of navigation, inputs, feedback, layout patterns. Use to translate user descriptions into exact component names.

Mobile app design patterns for iOS and Android. Native navigation, touch targets, platform conventions, safe areas. Don't use for web-only interfaces.

110+ free animated React components for text, backgrounds, UI. Includes Background Studio, Shape Magic, Texture Lab. Use when building visually engaging interfaces. Don't use for non-React projects.

Converts UI screenshots and design mockups into production-ready HTML/CSS code. Multi-agent architecture analyzes layout, plans structure, generates clean code. Use when you have a design image and need code. Don't use for code-to-code tasks.

UI/UX design system generator with CSV database. 67 styles, 96 palettes, 57 fonts, 25 charts, 13 stacks. Use for UI design, landing pages, dashboards, components, style selection. Generates complete design systems via --design-system.

NestJS and Node.js backend development. REST APIs, middleware, guards, DTOs, database integration. Don't use for Python backends or frontend code.

Semantic code search via MCP. Indexes entire codebase, finds relevant code by natural language query. 40% token savings. Use for large codebases (10K+ lines). Don't use for small projects.

PostgreSQL and MongoDB database design. Schema design, migrations, indexing, query optimization, RLS security policies. Don't use for application logic or API development.

React and Next.js frontend development. Components, hooks, state management, routing, Tailwind CSS styling. Don't use for React Native mobile or backend API development.

React Native and Expo mobile development. Navigation, native modules, platform-specific code, app store preparation. Don't use for web React or backend development.

Python development with FastAPI, data processing, audio analysis with librosa. Type hints, async patterns, Pydantic models. Don't use for JavaScript/TypeScript code.

Scans React code for anti-patterns. Finds unnecessary useEffect, prop drilling, accessibility issues. Run repeatedly until all issues pass. Don't use for non-React code.

CI/CD pipeline with GitHub Actions. Automated testing, building, deployment. PR checks, auto-merge, release workflow. Don't use for Jenkins or GitLab CI.

Application deployment strategies. Zero-downtime deploy, rollback procedures, database migrations during deploy. Don't use for initial server setup.

DNS configuration and SSL certificates. Domain setup, Cloudflare CDN, Let's Encrypt, HTTPS enforcement. Don't use for application-level security.

Docker and docker-compose configuration. Multi-stage builds, container orchestration, volume management, networking. Don't use for Kubernetes or cloud-native deployments.

Generates step-by-step instructions for manual tasks that cannot be automated. Server panel configuration, DNS changes, app store submissions. Use when agent cannot perform the action directly.

Application and server monitoring. Error tracking, log aggregation, alerting, uptime monitoring. Use for production setup. Don't use for development debugging.

Linux server configuration. Firewall, SSH hardening, user management, system updates. Use for initial VPS setup or server hardening. Don't use for application deployment.

Cross-model code review. Sends code to a DIFFERENT model (GPT/Gemini) for independent review. Reviewer must be on a different model than the code author. Use for critical PRs and security-sensitive code.

Multiple AI models critique a spec/PRD until consensus. GPT, Gemini, Grok each find different weaknesses. Iterates until all models agree the spec is solid. Use for critical project specifications.

Gemini as design advisor and visual analyst. Sends UI screenshots, designs, or visual content to Gemini for expert review. Strong in UI/UX critique, visual analysis, document understanding. Don't use for backend code or security.

Delegates text tasks to Google Gemini through MCP (gemini/gemini-reply). Use for architecture disputes, design critique, second opinions. Don't use for media — use gemini-media for images/video.

GPT as security advisor and architectural critic. Sends code or decisions to GPT for independent second opinion. Strong in security audits, code review, and finding logical flaws. Don't use for routine coding or simple tasks.

Multi-model planning committee. Up to 4 models create plans independently, then an anonymous judge selects the best or combines the best parts. Use for major architectural decisions.

Running AI models locally with Ollama and llama.cpp. Free inference, privacy, custom model deployment. Use for cost-free routine tasks or private data processing. Don't use when quality of Opus is needed.

Orchestrates large-scale code changes in parallel. Decomposes work into 5-30 independent units, each agent in isolated git worktree with tests and PR. Use for migrations, refactoring across many files. Don't use for single-file changes.

Deep code review like a senior engineer. Checks SOLID violations, security vulnerabilities (XSS, injections, race conditions), performance issues (N+1, missing cache), error handling and edge cases. Don't use for formatting or style-only reviews.

Verifies that separate code parts work together. Checks imports, API contracts, shared types, data flow between components. Use after multiple agents completed parallel tasks.

Reviews recently changed code for reuse, quality, and efficiency. Spawns 3 parallel review agents, aggregates findings, applies fixes. Official Anthropic skill. Use after completing any coding task.

Scans external skills and plugins for prompt injection, command injection, and malicious patterns before installation. Use before installing ANY external skill or plugin. Don't skip this check.