Imagegen Frontend Mobile
Leon LinGenerates mobile app screen concepts and flows as images, for iOS, Android and cross-platform products.
By agent · Codex
Skills in the open SKILL.md format that Codex reads. Each one has a plain-language summary and the command to install it.
$ npx skills add <author>/<skill> --agent codexReplace the placeholder with the author and skill name from the skill's page. Start a new Codex session afterwards so the skill is picked up.
Generates mobile app screen concepts and flows as images, for iOS, Android and cross-platform products.
Generates website design references as images, one per section of the page.
Produces clean editorial interfaces with a warm monochrome palette, typographic contrast and flat bento grids.
Stops the model from truncating output: enforces complete code, bans placeholders and splits cleanly at token limits.
Audits an existing website or app for generic AI design patterns and upgrades it without breaking functionality.
Defines the fonts, spacing, shadows, card structures and animations of agency-grade design, and blocks common AI defaults.
Generates DESIGN.md files for Google Stitch with strict typography, calibrated colour and asymmetric layouts.
The original v1 of the taste skill, kept for projects that depend on its exact behaviour.
Uses the ctx7 CLI to fetch library documentation, manage AI coding skills and configure Context7 MCP.
Fetches current library and framework documentation and code examples through the Context7 MCP server.
Retrieves up-to-date documentation, API references and code examples for any library, framework or SDK.
Adds captions or subtitles to an existing talking-head video without editing the footage, from plain verbatim to cinematic styles.
Turns an article, notes or a topic into a faceless explainer video with typography, diagrams and data visuals invented for each scene.
Authors or edits a custom HyperFrames composition for longer and multi-scene pieces, such as brand reels, montages and title cards.
Covers the HyperFrames CLI loop: init, capture, lint, check, preview, render and publish.
Entry point for making, editing or rendering a video or motion graphic with HyperFrames; it selects and installs the right workflow.
Creates short motion graphics where motion carries the message: kinetic typography, stat count-ups, chart hits and logo stings.
Turns a music track into a beat-synced video such as a lyric video, slideshow or kinetic promo.
Turns a GitHub pull request into a video that explains the code change, built from the diff, commits and files.
Turns a product URL, script or brief into a product launch or promo video.
Ports the source of an existing Remotion composition to HyperFrames HTML.
Authors a HyperFrames slideshow or pitch deck with fragment reveals, branching, hotspot navigation and a presenter mode.
Adds timed graphic overlays to a talking-head, interview or podcast video: titles, lower-thirds, callouts and quotes synced to the transcript.
Plans, designs and implements A/B tests, from a single experiment to a full growth experimentation programme.
Questions
Often. A skill is a folder of instructions and scripts in the open SKILL.md format, which Codex reads. A skill that depends on tools only one agent provides will not carry over, so read the skill's source before you rely on it.
Each skill page has an install command. Run it in a terminal, then start a new Codex session so the skill is picked up.
An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.