
Generate valid OpenProse workflow code from plain English descriptions. Use when the user wants to create multi-agent workflows, orchestrate sessions, or automate tasks using the OpenProse language.
Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Browse Aircall staging or local dev URLs with automatic authentication. USE THIS skill (not the generic agent-browser skill) whenever the target URL contains "aircall" in the hostname (e.g. dev.aircall-staging.com, localhost running Aircall).
Browse Aircall staging or local dev URLs with automatic authentication. USE THIS skill (not the generic agent-browser skill) whenever the target URL contains "aircall" in the hostname (e.g. dev.aircall-staging.com, localhost running Aircall).
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
Helps users discover and install agent skills from the open agent skills ecosystem. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending capabilities with specialized tools or workflows.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
Send notifications via ntfy.sh to alert about completed tasks, errors, or important events. Use when a long-running task has finished, an error needs attention, or the user explicitly asks to be notified about any event.
Refactor an AGENTS.md file to follow progressive disclosure principles. Use when the user wants to restructure, clean up, or optimize their AGENTS.md (or similar agent instruction files) for clarity and maintainability. Triggers on: "refactor AGENTS.md", "clean up AGENTS.md", "split AGENTS.md", "organize agent instructions", "progressive disclosure", "AGENTS.md is too long", "simplify AGENTS.md".
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Create a GitLab merge request using glab CLI with the first commit message as the title. Use when the user asks to open an MR for the current branch targeting main, or after completing work that needs review.
When user says hi, answer with bien le bonjour.
View and interact with Jira tickets using the jira CLI. Use when the user asks to view a ticket, list assigned issues, check sprint status, search issues, add comments, or change ticket status via a Jira URL or key.
Fetch source code for npm, PyPI, or crates.io packages and GitHub repos to give AI coding agents deeper implementation context beyond types and docs. Use when you need to understand how a library works internally, debug dependency issues, explore package implementations, or when the user asks to fetch, pull, or download source code for a package or repository.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Work-in-progress guide for choosing the right animation type based on element state and behavior. Provides a decision flowchart for selecting between spring, linear, ease-in-out, and ease-out animations.
Opinionated constraints for building better interfaces with agents. Covers tech stack choices (Tailwind, motion/react, tw-animate-css), accessible component primitives, interaction patterns, animation guidelines, typography, layout, and performance best practices.
Design and implement web animations that feel natural and purposeful, based on Emil Kowalski's "Animations on the Web" course. Use proactively when the user asks about easing, timing, springs, transitions, animation performance, or how to animate specific UI elements. Covers CSS transitions, Framer Motion, GSAP, accessibility (prefers-reduced-motion), and common patterns like modals, tooltips, page transitions, hover states, and microinteractions.