productivity▌

Secure browser automation for sensitive operations like login, payments, and form filling with isolated credential handling. \n \n Executes credential entry, payment processing, and personal data form filling in a dedicated subprocess isolated from the main agent context \n Supports structured sensitive data via JSON file with predefined schema for credentials, payment info, and personal details; custom fields allowed \n Integrates with agent-browser through session state handoff, enabling authe

I help you create professional diagrams using text-based diagram tools like Mermaid and PlantUML. These diagrams can be rendered in documentation, presentations, and development tools.

This skill implements the product positioning methodology from April Dunford's "Obviously Awesome." It provides a structured, repeatable process for defining how your product is the best in the world at delivering something a well-defined set of customers cares a lot about. Positioning is the foundational strategic exercise that determines how customers perceive your product, what they compare it to, and ultimately whether they buy it.

Spawn isolated agents for parallel task execution with runtime-native team selection and fresh context per wave. \n \n Auto-selects spawn backend based on runtime: Claude Native Teams in Claude sessions, Codex sub-agents in Codex sessions, or inline fallback if multi-agent unavailable \n Executes tasks in dependency-ordered waves, spawning only unblocked tasks in parallel while respecting file ownership conflicts via pre-spawn manifest validation \n Implements Ralph Wiggum pattern: fresh worker

Generate website images and edit them with Gemini 3 Native Image Generation. \n \n Supports hero banners, service cards, infographics with legible text (94% at 4K), and multi-turn editing across 10+ aspect ratios and resolutions up to 4K \n Two active models: Gemini 3 Pro Image Preview for 4K and complex compositions; Gemini 2.5 Flash Image for fast iteration \n Handles up to 14 reference images (max 5 human for consistency), style transfer, color changes, element addition/removal, and aspect ra

Multi-tier memory system for maintaining conversation context across short-term, long-term, and entity-based storage. \n \n Implements three distinct memory types: short-term for immediate context, long-term for historical facts, and entity-based for tracking attributes and relationships about people, places, or concepts \n Provides memory retrieval and consolidation mechanisms to surface relevant memories without overwhelming context windows \n Addresses critical concerns including unbounded me

bash-pro

Search and recommend Claude Code skills from trusted marketplaces based on user requirements. \n \n Searches across six curated sources in priority order: anthropics/skills, ComposioHQ/awesome-claude-skills, travisvn/awesome-claude-skills, skills.sh, ClawHub, and skillsmp.com \n Filters results by community verification (10+ stars), maintenance status (updated within 6 months), and security checks for suspicious code patterns \n Ranks recommendations using a weighted scoring system that prioriti

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

This skill enables batch conversion of documents between multiple formats using a unified pipeline. Convert hundreds of files at once with consistent settings, automatic format detection, and parallel processing for maximum efficiency.