AI Agent Skills

Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents generic AI aesth…

Use this skill whenever the user asks to test, validate, UAT, regression-check, or investigate the behaviour of a browser-based application — including Copilot Studio ag…

Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting. Use when you'd otherwise guess.

Customize Univer color themes, branded palettes, dark mode, and theme-aware plugin styles across Sheets, Docs, Slides, Bases, Boards, and PDFs. Use when setting an initi…

Use when completing frontend or UI work that needs visual verification, before claiming the UI is correct

Reproduce web UI bugs and verify browser workflows with Playwright MCP or the project's existing browser tests.

Implement an already-selected visual direction from a mockup, screenshot, or reference site in an existing project, using project-owned code and equivalent-state browser…

Plan, conduct, and analyze UX research using proven methodologies. Use when planning user research, writing interview scripts, creating test plans, recruiting participan…

Generates deep links to the Arize UI for projects, traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Discovers organization and pro…

Generate unit and UI tests for specified code with edge cases and mocks. Triggers: "generate tests", "write tests", "add tests", "test coverage".

Generate isolated UI components with all 8 states and variants — button systems, forms, cards, modals, nav. Design System-aware when a token set is confirmed. Load skill…

Guides the agent through connecting an MCP client to the hosted, unofficial Capacitor MCP server by Capawesome, which serves the official Capacitor documentation for v8,…

Run the machine-verifiable gate (typecheck, test, lint, plus a screenshot for UI) so a diff is review-ready. Triggers "proof of work", "is this review-ready", "prove it…

Interrogate a UX idea, requirement, flow, feature, or design direction before execution. Use when a designer asks to be challenged, wants assumptions exposed, wants a re…

Create a high-quality pull request description for UX-related implementation that explains why the change exists, what behavior changed, design-system usage, states, acc…

Automates macOS Messages (iMessage/SMS) via JXA with reliable service→buddy resolution. Use when asked to "automate iMessage", "send Messages via script", "JXA Messages…