
Use when you have a written implementation plan to execute in a separate session with review checkpoints. Triggers are "execute plan", "let's implement the plan", "implement plan".
Update local AGENTS.md with strategic knowledge discovered during this session. Use when user says "learn", "save knowledge", "update AGENTS.md", "capture learnings", or at end of significant work sessions. Also used by commit skill for pre-commit knowledge capture.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
REPL-Driven Development Workflow in Clojure
Commit current changes
Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.
Deploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).
Creates an LLM-friendly project summary
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
Guidelines for creating API routes in Expo Router with EAS Hosting
Build and distribute Expo development clients locally or via TestFlight
Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling
Guidelines for upgrading Expo SDK versions and fixing dependency issues
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create structured implementation plan in docs/plans/
Run a second-opinion code review using the Codex CLI (`codex exec review`) in the background and surface the findings when it finishes. Use when the user says "review with codex", "second-opinion review", "what does codex think", or wants an outside model to look at local changes (uncommitted, current branch vs main, or a named commit). Also used as the review checkpoint inside the `executing-plans` skill.
You MUST use this before any creative work that is large in scope - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use this before small or medium creative coding work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design, then writes a lightweight implementation plan compatible with executing-plans.
Use when writing prose humans will read - documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.
Review local code changes — uncommitted work, the current branch vs main, or a specific commit — for code quality, minimal implementation, basic security, and feature completeness. Use this skill whenever the user asks to review code, review changes, review a branch, review a commit, audit a diff, sanity-check what's about to be committed, or asks "is this ready to ship?" — even when they don't say the word "review" explicitly. This is a fast local review run inside the project, not the cloud-based /ultrareview. The output is a severity-grouped findings report with file:line citations.
Use when you have a spec or requirements for a multi-step task, before touching code. Triggers are "let's create a plan".