carterdea
64 verified skills64 total stars
agent-browser
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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
tools1
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
development1
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
development1
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
development1
domain-model
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
testing1
grill-me
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".
testing1
prove-it-bug-fix
Reproduce bugs with a failing test before fixing
testing1
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
development1
shopify-theme-pull
Pull merchant-edited content from a live Shopify theme
content-media1
qa
Verify completed work in the browser using QA notes from a plan file
testing1
pair-programming
Senior engineer pairing mode with assumption surfacing, pushback, scope discipline, and simplicity enforcement
testing1
handoff
Generate a continuation prompt so the next session can pick up where this one left off
data-ai1
gh-review-pr
Review a GitHub PR focusing on correctness, tests, and risk
testing1
claude-review
Get a second opinion on code changes from Claude Code CLI. Use before PRs or when you want an independent review from a different AI model. Trigger when the user asks for a code review, second opinion, or says "claude review".
tools1
execute-plan
Work through a plan file task-by-task, checking off items as they complete
testing1
gh-commit
Create small, logical commits with conventional commit messages
tools1
gh-ship
Commit, push, and create PR in one step
tools1
merge-conflicts
Rebase current branch onto main/master, resolve merge conflicts, and force-push
data-ai1
react-doctor
Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
development1
shopify-dev-theme
Create an unpublished Shopify theme named after the current git branch
development1
smart-brevity
Rewrite text using Smart Brevity principles — shorter, sharper, audience-first communication. Use this skill whenever the user wants to: rewrite or edit text to be more concise, apply Smart Brevity formatting, improve emails/newsletters/presentations/speeches/social posts/meeting agendas, audit a codebase or website for copy improvements, make writing punchier or clearer, reduce word count while preserving meaning, or mentions "Smart Brevity" in any context. Also trigger when the user pastes a block of text and asks to "tighten," "shorten," "clean up," "make it punchy," "cut the fluff," or similar brevity-related requests. Even if the user doesn't say "Smart Brevity" explicitly, use this skill for any request to improve the clarity, brevity, or impact of written communication.
development1
work-forever
Run in highly autonomous mode for long-running tasks with minimal questions
tools1
qa-gstack-only
Report-only QA testing -- finds bugs but NEVER fixes them. Runs browser-based QA testing, documents issues with screenshot evidence, produces health scores and structured reports. Use when asked to "just find bugs", "QA report", "audit this site", or when you want a QA assessment without code changes. For the full test-fix-verify loop, use /qa-gstack.
development1
subagent-orchestrator
Orchestrate sub-agents to accomplish complex long-horizon tasks without losing coherency. Use when the user asks to "use subagents", "orchestrate", "delegate to agents", or requests a complex multi-step task that benefits from sub-agent coordination.
data-ai1
baseline
Install a quality baseline on a repo — linter, formatter, dead-code scanner, lefthook hooks, named local URLs (portless), and a context-efficient backpressure wrapper.
development1
skill-creator
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.
testing1
clean-coder
Invoke this skill when the user swears or becomes upset
development1
audit-ai-code
Audit AI-generated or AI-shaped backend/general code diffs for duplicate helpers, over-defensive control flow, broad exception wrappers, speculative scaffolding, comment/docstring boilerplate, local style drift, hallucinated APIs/dependencies, fixture-shaped test hacks, and obvious safety/performance gaps. Use when reviewing or safely cleaning up Python, TypeScript, or other implementation code after a feature, bugfix, or prototype pass.
tools1
de-slop
Remove AI artifacts and cleanup noise before a PR
data-ai1
audit-ai-frontend
Audit AI-generated or AI-looking frontend implementations, UI screenshots, and design diffs for generic AI aesthetics, card/gradient/font tells, weak UX copy, accessibility gaps, brittle responsive behavior, and one-off design-system drift. Use when reviewing or restyling React, Tailwind, shadcn/ui, HTML/CSS, landing pages, dashboards, or app screens to make the UI feel more intentional without a full redesign unless explicitly requested.
development1
audit-ai-writing
Reference-only checklist for AI-writing artifacts, citation failures, and cleanup rewrites in Markdown, MDX, wiki text, or pasted chatbot output. Use when you need objective residue checks, false-positive-safe prose triage, and practical fixes without relying on detector scores.
testing1
clean-gone
Cleans up all git branches marked as [gone] (branches that have been deleted on the remote but still exist locally), including removing associated worktrees.
development1
clean-worktrees
Audit and clean agent-created Git worktrees (Codex, Claude Code, OpenCode, Pi, or plain `git worktree add`) and leftover worktree directories safely. Use when disk usage appears inflated by `~/.codex/worktrees`, per-repo `.claude/worktrees`, `.worktrees`, other agent worktree roots, Git worktree metadata, detached worktrees, stale branch worktrees, or when the user asks to map worktrees to pull requests before deletion.
development1
code-review-prompt
Generate a comprehensive code review prompt for the current branch that can be copied into another Claude session
development1
codex-review
Get a second opinion on code changes from OpenAI Codex CLI. Use before PRs or when you want an independent review from a different AI model.
tools1
design-doc
Format implementation plans as structured design documents for technical review. Use when planning multi-step features, refactors, migrations, or architectural changes before coding. Produces a design doc with problem context, proposed solution, file map with verified line references, alternatives considered, and phased implementation tasks. Trigger on "plan this out", "write a design doc", "help me plan the approach", "think through the tradeoffs", or any request to reason about how to build something before building it.
development1
garry-tan-code-review
Interactive code review with opinionated recommendations and explicit sign-off before changes. Based on Garry Tan's review prompt.
development1
pre-pr
Run complete validation before creating a PR - security, tests, breaking changes, and generate PR description
testing1
rams
Run accessibility and visual design review against WCAG guidelines
documentation1
gh-fix-ci
Find the first failing CI check, fix it, and re-run verification
testing1
humanize-ai-text
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero, Turnitin, and Originality.ai. Based on Wikipedia's comprehensive "Signs of AI Writing" guide. Makes robotic AI writing undetectable and human-like.
documentation1
iterate-forever
Visual-reference-to-app implementation loop for building or restyling a web app screen to match a provided reference image. Use when Codex is asked to take a screenshot/reference/mockup/image and build an app or route that looks like it, especially when the task requires hosting the app, capturing Playwright screenshots, comparing against the reference, and repeatedly editing until the result is close.
development1
make-tests
Add tests for the change you're working on
testing1
new-skill
Create a new skill from conversation history or user description
tools1
office-hours
YC-style office hours with two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Produces a design doc, not code. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building".
development1
qa-gstack
Systematically QA test a web application and fix bugs found. Runs browser-based QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-gstack-only. Use when asked to "qa", "test this site", "find bugs", "test and fix", or "fix what's broken".
development1
self-improve
Codex-specific, session-driven self-improvement for Codex behavior and project instructions. Use when the user asks to inspect past Codex sessions, run a "dream" pass over prior interactions, mine repeated user corrections/preferences, improve or draft skills, update repo/project `AGENTS.md` guidance, or propose durable edits to global `~/.codex/AGENTS.md`.
development1
shopify-liquid-patterns
Common Liquid code patterns for Shopify theme development. Use when writing Liquid templates, handling translations, product displays, or theme customizations.
development1
web-animation-design
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance/exit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal/dropdown/tooltip/popover/drawer animations, gesture animations, drag interactions, button press feel, "feels janky", "make it smooth".
tools1
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
development1
gh-address-pr-comments
Resolve actionable review comments for a PR one-by-one
documentation1
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
testing1
emil-design-engineering
Design engineering principles and patterns for building polished, accessible web interfaces. Use this skill when building UI components, reviewing frontend code, implementing forms, handling touch interactions, optimizing performance, or creating marketing pages. Triggers on: design engineering, UI polish, input fields, form validation, button states, touch devices, mobile UX, accessibility, a11y, keyboard navigation, aria labels, font rendering, typography, layout shift, z-index, animations, transitions, easing, hover effects, tap targets, iOS Safari, prefers-reduced-motion, marketing pages, landing pages, dark mode, theme switching, scrollbars, gradients, shadows, virtualization, preloading.
development1
trello-cli
Operate Trello through the local CLI tool. Use this skill whenever the user asks to create, update, move, archive, search, or inspect Trello boards, lists, cards, comments, checklists, attachments, labels, members, or custom fields — or when they mention the Trello CLI, `trello` command, or want to manage Trello from the terminal. Also use this when working in the Trello_CLI repository and needing to exercise the binary.
tools1
shopify-app-store-review
Run a pre-submission compliance check against your Shopify app's codebase. Reviews App Store requirements and surfaces likely issues before you submit for official review.
development1
shopify-use-shopify-cli
Choose when the user needs **Shopify CLI** to run or fix something now: validate app or extension config on disk (`shopify.app.toml`, `shopify.app.NAME.toml`, `shopify.extension.toml`); run or troubleshoot store workflows (`shopify store auth`, `shopify store execute`); inventory or product changes by handle, SKU, or location name; or CLI setup, auth, upgrade issues. Emphasize **commands and operational steps**, not only authoring GraphQL. Skip for API-only understanding or codegen with no CLI execution. Examples: validate configuration before deploy; run an existing query via CLI; list products; missing `shopify store execute`.
tools1
code-simplifier
Review recently changed files for reuse, clarity, and efficiency issues, then apply behavior-preserving simplifications. Uses parallel subagents when the harness supports them; otherwise reviews in-process.
development1
shopify-polaris-admin-extensions
Add custom actions and blocks from your app at contextually relevant spots throughout the Shopify Admin. Admin UI Extensions also supports scaffolding new adminextensions using Shopify CLI commands.
tools1
shopify-polaris-app-home
Build your app's primary user interface embedded in the Shopify admin. If the prompt just mentions `Polaris` and you can't tell based off of the context what API they meant, assume they meant this API.
development1
shopify-storefront-graphql
Use for custom storefronts requiring direct GraphQL queries/mutations for data fetching and cart operations. Choose this when you need full control over data fetching and rendering your own UI. NOT for Web Components - if the prompt mentions HTML tags like shopify-store, shopify-cart, use storefront-web-components instead.
development1
shopify-payments-apps
The Payments Apps API enables payment providers to integrate their payment solutions with Shopify's checkout.
development1
shopify-trello-delivery
Ship Shopify theme work from a Trello ticket end to end: inspect the card including Figma links, implement the theme change, deploy or update the correct preview/dev theme, browser-QA desktop and mobile against Figma when available, create or update the GitHub PR, attach screenshots, comment on Trello, and move the card forward. Use this whenever the user mentions a Shopify theme task with a Trello card, Figma design/artboard, preview theme, Customizer, dev theme, PR handoff, Ready for Review/Testing, or asks to update an existing Shopify PR from a ticket.
development1
trello-delivery
Ship a Trello ticket end to end on any web app (Vercel, Fly.io, or other host — no Shopify): pull the latest main, read the card including Figma links, implement the change in a worktree, run the project's own tests/lint/typecheck, run de-slop and code-simplifier and fold the worthwhile cleanups in, QA desktop and mobile on a local Portless preview URL, capture screenshots, open or update the GitHub PR, link the PR and Trello to each other, attach screenshots to both, comment on the card, and move it to review. Use this whenever the user points you at a Trello card or ticket for a code task and wants it delivered as a reviewable PR — phrases like 'do this Trello ticket', 'ship this card', 'pick up this ticket and open a PR', 'update the PR for this card', or names a card/list/board with a feature or bug to implement. This is the default Trello-to-PR workflow for non-Shopify projects; for Shopify theme work use shopify-trello-delivery instead.
development1
shopify-baseline
Install or upgrade a quality baseline for Shopify theme repos. Use this whenever the user asks to add Shopify theme linting, Biome, Theme Check, Playwright accessibility checks, Vitest, Vite build tooling, lefthook hooks, GitHub Actions CI, Shopify Lighthouse CI, Claude Code PR review workflows, or a context-efficient run_silent.sh setup across Shopify sites.
tools1