productivity▌

Search and deploy pre-configured services from Railway's template marketplace. \n \n Supports 20+ templates across databases (PostgreSQL, Redis, MySQL, MongoDB), CMS platforms (Ghost, Strapi), storage (Minio), automation (n8n), and monitoring (Uptime Kuma) \n Query templates by category or verification status; fetch template details including serialized configuration needed for deployment \n Deploy templates to a project and environment in two steps: fetch template metadata, then execute deploym

Structured framework for evaluating startup pivots using insights from product leaders. \n \n Applies the Four Ps framework (Problem, Persona, Product, Positioning) to diagnose what needs to change, rather than pivoting blindly \n Emphasizes rational distance from emotional attachment: assess whether you've truly exhausted possibilities or just lost momentum \n Challenges founders to consider magnitude: most pivots are too small (10%) when breakthrough often requires fundamental rethinking (200%

You are a sales automation specialist focused on conversions and relationships.

Static security analysis for GitHub Actions workflows invoking AI coding agents. \n \n Detects nine attack vectors where attacker-controlled input reaches AI agents in CI/CD pipelines, including env var intermediaries, direct expression injection, CLI data fetches, dangerous sandbox configs, and wildcard user allowlists \n Scans .github/workflows/ for Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference steps; resolves one level of composite actions and reusable workflows \n Cap

Translate user needs into development-ready stories with Mike Cohn format and Gherkin acceptance criteria. \n \n Combines \"As a / I want / so that\" user story structure with \"Given / When / Then\" acceptance criteria for testable, outcome-focused work \n Includes quality checks and anti-patterns to avoid generic personas, vague outcomes, and scope creep \n Designed for backlog grooming, sprint planning, and shared understanding between product, engineering, and QA \n Emphasizes stories as con

Search and stream TV shows, anime, and variety content across multiple sources with optional casting to Xiaomi or Android TVs. \n \n Searches multiple source sites for shows, anime, short dramas, and variety programs with pagination support \n Supports casting to Xiaomi TVs and Android TVs (via TvBox) when configured with device IP environment variables \n Some sources return webpage URLs instead of direct playable links; use curl to extract actual .m3u8 or .mp4 addresses \n Search operations ma

Framework for registering LLM tools with custom UI rendering in assistant-ui. \n \n Supports both backend tools (via AI SDK) and frontend-only tools, each with optional custom UI rendering through makeAssistantToolUI \n Includes human-in-the-loop patterns with requires-action status for confirmation workflows and interactive tool responses \n Tool UI receives execution status, arguments, results, and a submitResult callback for interactive tools \n Common setup patterns provided for weather APIs

End-to-end type-safe APIs for TypeScript with zero code generation. \n \n Shares TypeScript types between client and server automatically—no codegen required, with full type inference across queries, mutations, and subscriptions \n Integrates seamlessly with React Query for caching, optimistic updates, and infinite queries; supports Next.js App Router, Server Components, and WebSocket subscriptions \n Validates all inputs with Zod schemas; includes middleware for authentication, logging, and rat

Structured frameworks for evaluating competing options and making clearer trade-off decisions. \n \n Applies mental models from 40 product leaders covering decision context, constraint identification, cost quantification, and framework selection \n Core principles include optimizing for order-of-magnitude over precision, applying the \"would I start this today?\" test to avoid sunk cost fallacy, and using weighted criteria matrices for multi-factor decisions \n Helps surface hidden costs like ma

Lightweight web search and content extraction via Brave Search API, no browser required. \n \n Two core commands: search.js for querying the web with configurable result counts, and content.js for extracting readable markdown from specific URLs \n Search results include title, link, and snippet by default; add --content flag to include full page content as markdown \n Ideal for documentation lookup, fact-checking, and fetching web content without the overhead of browser automation \n Requires BR