productivity▌

Generates dependency-aware implementation plans optimized for parallel multi-agent execution. \n \n Creates atomic, independently executable tasks with explicit dependency declarations to maximize parallelization across agents \n Requires codebase investigation, documentation retrieval for external libraries, and clarifying questions before planning to eliminate ambiguity \n Structures plans with task IDs, dependency arrays, descriptions, file locations, and validation criteria; includes visual

Automatically organize invoices and receipts into a tax-ready filing system with consistent naming and logical folder structure. \n \n Extracts key information from PDFs, images, and documents: vendor name, invoice number, date, amount, and description \n Renames files to a standardized format ( YYYY-MM-DD Vendor - Invoice - Description.ext ) for easy sorting and retrieval \n Organizes files by vendor, expense category, time period, or tax classification based on user preference \n Generates a C

Extract and analyze competitors' ads from ad libraries to identify successful messaging, creative patterns, and positioning strategies. \n \n Scrapes ads from Facebook Ad Library, LinkedIn, and other platforms, capturing screenshots and analyzing messaging themes, pain points, and value propositions \n Identifies patterns in successful ads by categorizing them by theme, audience, and format, then explains why certain approaches likely perform well \n Supports competitive set analysis across mult

Gemini 2.5 Computer Use browser automation with Playwright-based agent loops and safety confirmations. \n \n Implements a screenshot-to-action cycle: capture screen, send to Gemini, parse function calls, execute in Playwright, return results until task completion or turn limit \n Supports multiple browser options: bundled Chromium (default), Chrome/Edge channels via COMPUTER_USE_BROWSER_CHANNEL , or custom executables like Brave \n Includes safety confirmation workflow that prompts users before

Generate \"ideal promise vs cruel reality\" visual comparisons by analyzing image content across any domain. \n \n Automatically detects image domain (architecture, portrait, product, food, travel, gaming, fitness, home, tech) and current state (deteriorated, ideal, or normal) \n Outputs three modes: idealized rendering, realistic everyday appearance, or side-by-side comparison with automatic layout (left-right or top-bottom based on aspect ratio) \n Applies five universal contrast dimensions ac

$21

AI-powered market briefings with multi-region coverage, portfolio tracking, and automated delivery. \n \n Covers US, European, and Japanese markets with news from WSJ, Barron's, CNBC, Yahoo Finance, and Finnhub via RSS feeds and APIs \n Generates morning and evening briefings with Gemini-powered summaries in English or German, delivered via WhatsApp or displayed on demand \n Supports portfolio management (add/remove stocks, import CSV) with ticker-specific news and price alert configuration \n C

Remove AI code slop \n Check the diff against main, and remove all AI generated slop introduced in this branch. \n This includes: \n \n Extra comments that a human wouldn't add or is inconsistent with the rest of the file \n Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted / validated codepaths) \n Casts to any to get around type issues \n Any other style that is inconsistent with the file \n \n Report at the end with onl

Detailed, phased implementation plans with sprints and atomic tasks for bugs, features, or tasks. \n \n Structures plans into research, requirements clarification, sprint-based implementation, and risk assessment phases \n Breaks work into demoable, independently testable sprints with specific, committable atomic tasks including file paths and dependencies \n Asks targeted clarification questions upfront to resolve ambiguities around scope, constraints, priorities, and success criteria \n Identi

Automate Marshroom cart issue setup with branch creation, status tracking, and context injection. \n \n Reads the Marshroom state file, filters cart issues matching the current repository, and creates a feature or hotfix branch with standardized naming ( Feature/#N or HotFix/#N ) \n Mandatory state.json update: sets issue status to running via marsh start command or atomic jq write, with verification to ensure the update succeeds \n Injects issue body as context so the agent understands the full