ツール

OpenAI's official Codex plugin for building frontend apps and generating visual assets, testing and debugging in a browser, plus best-practice skills for React, shadcn/ui, Stripe payments and Supabase databases. Codex only.

Figma's Codex plugin in OpenAI's official marketplace: implements UI from designs, generates Code Connect mappings, and creates or updates pages, component libraries, FigJam diagrams and slides in Figma. Needs a connected Figma account.

OpenAI's official Codex plugin that turns early product ideas, live pages or screenshots into interactive prototypes, proposing a few visual directions before building. Also reviews user flows, researches user pain points and checks accessibility issues.

Creates, edits and validates reproducible Python and SQL Jupyter notebooks: organizes cells as reports or tutorials, checks conclusions against actual output and reruns top to bottom before handoff. Maintained by OpenAI in the Data Analytics plugin of openai/plugins.

OpenAI's official Codex plugin that guides sequencing analysis from BCL/FASTQ: QC, RNA-seq differential expression, single-cell, variant calling and metagenomics, favoring nf-core and other public pipelines with reproducible run logs. Checks for local tools first. Research use only.

OpenAI's official set of 18 web data visualization skills: chart selection and critique, D3, Canvas, Three.js, maps, statistical uncertainty, live dashboards, Gantt charts, UML and scrollytelling. Ships with a Codex plugin; installed alone, the plugin-level references are missing.

OpenAI's official Codex plugin with 18 skills to choose, design, build, test and export web charts, maps, dashboards, Gantt charts and UML, using D3, Vega-Lite and Three.js with attention to accessibility and responsiveness. Codex only.

Manage Kubernetes clusters in natural language: translates intent into kubectl operations and runs them, and can serve as an MCP server for other agents. Uses Gemini by default (API key required) and also supports OpenAI and local models. Maintained by Google Cloud.

Open-source LLM evaluation platform: one opencompass command picks the model and datasets and runs the evaluation across hundreds of benchmarks. Works with local Hugging Face models and API models, with vLLM and LMDeploy for faster inference.

Tw93's lean pack of engineering-habit skills: /think to pressure-test plans, /hunt for root causes, /check to review diffs, /ui for frontend interfaces, /write to polish Chinese and English prose, and more (8 skills). Works with both Claude Code and Codex.

Converts raster images like JPG and PNG to SVG, handling color tracing, black-and-white line art and unevenly lit scans, for vectorizing logos, illustrations and old drawings. The CLI is a 1.0 preview installed with cargo (needs Rust); a desktop app is also available.

A more intuitive find-and-replace tool than sed: uses JavaScript/Python-style regex syntax, supports literal string mode and in-place file edits, which suits agents doing bulk text rewrites.

Hands your current browser session to the agent through a Chrome extension: read console logs and network requests, take screenshots, and run Lighthouse performance, accessibility and SEO audits without signing in again.

Converts and two-way syncs Jupyter notebooks with plain Python scripts or Markdown, so agents can edit research and teaching notebooks like ordinary text and diffs stay readable. Needs a local Python environment; install with pip.

Creates a layered progressive blur at the top or bottom edge of the viewport by stacking backdrop-filter layers with gradient masks, with ready-to-paste HTML and CSS and knobs for height, blur steps, direction and z-index.

Adds a lightweight interactive WebGL globe with the cobe library: canvas sizing for device pixel ratio, location markers, rotation in onRender, resize handling and teardown, for plain pages or React/Next.js hero sections.

Has the agent use Iconify Simple Icons brand marks instead of typed company names in logo rows, integration grids and partner lists, sized in a 64x64 box, monochrome by default, grid-aligned and labeled for accessibility when needed.

Adds thin vertical guide lines at the content container edges plus small corner squares for a measured, structured layout, with CSS tokens and pseudo-element code that keeps guides behind content and out of pointer events.

Builds cinematic, scroll-driven product storytelling with GSAP ScrollTrigger: pinned scenes, scrubbed timelines, progressive UI reveals and section handoffs, with cleanup in React, simpler choreography on small screens and readable copy and CTAs.

Adds scroll-reveal animations that fire when elements enter the viewport, using an IntersectionObserver snippet plus keyframes and a Tailwind arbitrary animation class; tune threshold, rootMargin, duration, delay and play-once behavior.

Builds seamless infinite marquees for logos, testimonials, screenshots or tags by duplicating the item sequence and translating the track from 0 to -50%, with stable widths, faded edges, optional hover pause and reduced-motion handling.

General guidance for building UI with Tailwind CSS: responsive and state variants, dark mode, sparing arbitrary values, components before @apply, and pitfalls such as dynamically built class names missing in production, with button and hero examples.

Reveals headings and short copy word by word through an overflow mask as they scroll into view, using GSAP ScrollTrigger and a split helper that avoids the paid SplitText plugin, with aria-label, reduced-motion support and React cleanup.

Helps the agent add or debug web animations with GSAP: tweens, timelines and position parameters, easing, stagger and ScrollTrigger pin and scrub, plus fixes for jank, cleanup with gsap.context() in React and refreshing after images load.