
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments.
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy to create intentional compositions.
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback.
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
Plan commits for all dirty git changes in the current repository. Use when I say `commit-plan`, `commit plan`, `plan to commit all dirty`, `group my dirty changes into commits`, or ask for a safe commit plan without actually committing. Do not use when I explicitly want you to commit or push immediately, rewrite history, or work outside git.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.
Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.
Add strategic color to features that are too monochromatic or lack visual interest. Makes interfaces more engaging and expressive.
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight.
Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.
Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.
Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful.
Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library.
Persist durable user corrections and preferences across sessions through a repo-tracked plain-text `feedback.log`. Use when starting a session that should honor prior reusable feedback, or when the user gives durable guidance about workflow, formatting, style, tooling, review expectations, or communication that should apply again later.
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly.
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. Generates creative, polished code that avoids generic AI aesthetics.
Normalize design to match your design system and ensure consistency
Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.
Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Use when handling commit or push requests, refreshing the root README, or changing repo behavior that can make the root README stale, especially when the README needs to sell the repo clearly to recruiters before setup details take over
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Use when work in this repo introduces a concrete manual verification step, changes the expected outcome of an existing manual check, or exposes an obvious gap in the shared smoke-test checklist.
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.
Use when I explicitly want the current intended dirty git worktree committed and pushed now, including requests like `commit dirty`, `commit all dirty`, `commit and push this`, or `ship these changes`, after verifying scope and running the minimum relevant checks. Do not use for commit planning only, history rewrites, force-pushes, or ambiguous mixed diffs.
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
Use this skill when the user wants logo design, brand identity, visual direction, color palette selection, typography pairing, SVG logo concepts, favicon creation, Open Graph assets, or a lightweight brand guide for a product, app, website, startup, or repo. Do not use this skill for general UI implementation unless the task is specifically about brand identity or visual language.
Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.
Commit and push only the git changes dirtied during the current Codex session, while leaving pre-existing dirty work from other sessions uncommitted. Use when I say `commit-session`, `commit session`, `ship this session`, `commit only this Codex session`, or explicitly ask to avoid committing pre-existing or other-session dirty changes. Do not use for commit planning only, all-dirty shipping, history rewrites, or cases where session scope cannot be proven from Codex logs.
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
Push interfaces past conventional limits with technically ambitious implementations. Whether that's a shader, a 60fps virtual table, spring physics on a dialog, or scroll-driven reveals — make users ask "how did they do that?"
Improve typography by fixing font choices, hierarchy, sizing, weight consistency, and readability. Makes text feel intentional and polished.
Use when initializing a LeetCode Python problem from a same-name `.txt` prompt dump and `.py` stub, especially when the goal is to scaffold a local runner and unittest coverage without generating the solution itself.
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.