Map rendered/pasted HTML class names back to source code (CSS Modules, Fluent UI, Griffel). USE WHEN: inspecting Playwright DOM output, debugging styles in the browser, or reverse-engineering pasted HTML.
27524d agoReviewMountCreate a free account to mount
Type-check and lint the CoreAI app. USE WHEN: the user asks to "lint", "fix lint", "run the linters", "check types", or after making code changes that need verification.
Create a new design variant or alternative for a page using the built-in feature/variant system. USE WHEN: a designer wants to try a different layout, create an "option B" or "version 2", compare designs side by side, add an A/B alternative, or explore an alternate version. Do NOT build a custom toggle solution.
27524d agoReviewMountCreate a free account to mount
CoreAI Sandbox component usage: import boundaries, published CoreAI documentation, and local adapter inspection. USE WHEN: editing any `*.tsx` file, picking a component, or writing component imports.
27524d agoReviewMountCreate a free account to mount
Start the CoreAI Sandbox dev server and open it using available browser tools. USE WHEN: the user asks you to "start the app", "run the dev server", "open the app", or "launch CoreAI Sandbox".
27524d agoReviewMountCreate a free account to mount
CoreAI Sandbox's TanStack Query + mock-JSON data layer. USE WHEN: editing data-fetching hooks (`app/hooks/use*.ts`), adding mock data in `app/data/`, or wiring a component to query state.
27524d agoReviewMountCreate a free account to mount
Read the shared Replica instructions before prototype work. They own task scope, component preflight, canvas setup, publishing and browser validation. This file owns Minimal's app conventions. Minimal uses React, TypeScript, Vite and TanStack Router with hash-based routes. It has no component library. Keep routing and scaffolding local to this app. Use an installed Node.js version matching engines.node in package.json: Run npm run check:starter for formatting, type checking, app tests, production-prototyping helper tests and the build. Use the individual commands while…
27524d agoReviewMountCreate a free account to mount
Use when asked to copy, clone, replicate or recreate a live production website or web app as a Replica prototype from its URL, such as "create a prototype from https://example.com" or "replicate this site for a demo". Do not use for building a new design from a brief, or for changing an existing prototype.
27524d agoReviewMountCreate a free account to mount
Shared context template library for setup-skills. Read when discovering context documents or their ownership. This library supplies research inputs, not active product context or a separate authoring workflow.
27524d agoReviewMountCreate a free account to mount
Audits actual components and routes against applicable WCAG 2.2 A/AA criteria using consumer-owned design-system evidence and repository tools. Use when asked for an accessibility audit, a11y check, keyboard or focus review, contrast check, or screen-reader verification.
27524d agoReviewMountCreate a free account to mount
Creates or updates believable deterministic raw fixture scenarios without breaking an existing prototype. Use when asked to add or change fixtures, seed data, sample data, scenarios, or cross-record relationships. Not for UI redesign, live-data infrastructure, or unrelated commands.
27524d agoReviewMountCreate a free account to mount
Use for explicit agent-browser CLI checks or a named browser capability neither the Copilot canvas nor configured Playwright MCP can supply. Ordinary rendered checks and browser selection belong to browser-canvas-validation.
Use the Copilot browser canvas first for rendered route checks, interaction tests, screenshots and visual, responsive or accessibility evidence. Use configured isolated Playwright MCP only when the canvas is unavailable for a required check.
27524d agoReviewMountCreate a free account to mount
Reviews existing UI components for design-system consistency, states, responsiveness and accessibility using consumer-owned context. Use when asked to review component quality, check design-system adherence or audit component consistency.
27524d agoReviewMountCreate a free account to mount
Builds new UI prototypes and makes targeted changes to existing prototypes using consumer-owned context. Use when asked to build a prototype, mock up a UI, or add, change, refine or recreate part of an existing prototype. Do not use for unrelated tasks, routine commands, Git lifecycle actions, acknowledgements or infrastructure work.
27524d agoReviewMountCreate a free account to mount
Writes a lightweight Markdown concept handoff from existing decisions and evidence. Use when explicitly asked for a developer handoff, to transfer a prototype or concept to another team, or to prepare a brief for implementation. Not for ordinary prototype completion, building, reviewing or publishing.
27524d agoReviewMountCreate a free account to mount
Prepare reusable repository-guidance improvements from selected Hub feedback findings when the user requests proposals or solutions after a review. Present each solution before edits; apply only explicitly approved proposals. Environment changes and prototype fixes are out of scope.
27524d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
GitHubSkill