Каталог навыков агентов

论文 PDF 视觉排版审稿。把已编译的 PDF 逐页渲染成图片，做确定性几何检查（空白页、页边距溢出、图超宽、页底孤立标题、Overfull/Float too large 等），再用用户可选的视觉后端（Codex 自身视觉/OAuth 登...

Create a structured Agent-Native plan with optional visual review. Use when a plan needs an interactive review surface.

Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, an...

Renders existing plans as interactive visual documents. Use when visualizing a text plan, creating a plan wireframe, or...

Use after features are built and before shipping, when the UI needs a quality pass, when the product needs to look premi...

Use when refining interface details (text wrapping, spacing, animations, shadows, alignment) to compound small visual im...

Use for a focused high-craft polish pass after structure and art direction are stable; improves typography metrics, spac...

Iris's UI visual polish review skill. Audits an existing UI surface against the four axes — palette, proportion, hierarc...

Inspect rendered pages for visual polish, readability, and design consistency using Chrome browser automation

Refine rendered finish at accepted viewports.

Only use when the user explicitly invokes this skill by name.

Guidelines for visual predictive checks following Säilynoja et al. recommendations using ArviZ

Generate visual explanations, diagrams, and slides. Use when explaining complex code, architecture, data flows, or any t...

Craft Higgsfield-grade, hyper-structured image-generation prompts for every blog visual. MANDATORY before any image gene...

Write model-specific image and video prompts for the shots in a storyboard or shot list (shots.json). Outputs copy-paste...

Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/te...

Capture reproducible browser evidence after UI changes. Use for desktop/mobile screenshots, overflow, console, failed re...

Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color in...

Visual QA checkpoint for conductor gates. Uses tabz MCP tools to check browser console errors, take screenshots, and ide...

Visual QA inspector that navigates the running app in Chrome to detect visual bugs, layout issues, console errors, and n...

MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA...

Use when a website needs rendered screenshot review, Playwright visual regression, multi-viewport checks, horizontal ove...

Use when verifying that a UI renders correctly. Covers visual regression testing, responsive checks across breakpoints,...

Check a built UI in a real browser at several widths: states, screenshots, visible breakage.

Agent profile for inspect screenshots, viewports, layout overlaps, visual regressions, spacing, typography, and interact...

Chrome DevTools Performance panel specialist. Analyzes flame charts, FPS, CPU usage, timeline events, CSS selector stats...

Lighthouse performance audit specialist. Runs Lighthouse CLI to measure performance scores, Core Web Vitals, and identif...

Static React code analyzer for performance anti-patterns. Scans source code for missing memoization, inline objects in p...

React DevTools Profiler specialist. Uses the React DevTools extension to analyze component render behavior, commit timin...

Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors,...

Automated visual QA with pixel-level diff comparison, iterative fix loop, and cross-browser verification. Uses pixelmatc...

Side-route skill that renders a change as a single self-contained interactive HTML artifact — a finished diff, PR, or br...

Turn a PR, branch, commit, or diff into a grounded Agent-Native visual recap for substantial changes.

Generate and maintain the system recap block in a PR description - a GitHub-rendered visual summary of which system prim...

Builds local-only visual recaps from Git diffs. Use when recapping a finished branch, visualizing a commit range, or rev...

Turn a screenshot, generated design reference, or visual brief into a polished responsive interface through measurable v...

Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, B...

Screenshot-based regression testing with Playwright. Compares rendered pixels against baseline PNGs. Use when working wi...

Visual regression testing skill using Playwright, covering screenshot comparison, visual diff thresholds, responsive tes...

Visual Regression Test Agent. Storybook + Chromatic/Percy를 사용한 Visual Regression 테스트를 담당합니다. UI 변경 감지 및 시각적 일관성을 검증합니다.

Compare captures; stitch lazy/animated pages.

Sets up visual regression testing using Percy, Chromatic, or Playwright to catch unintended UI changes through screensho...

Automate visual validation of component states to catch styling regressions.

Compare screenshots and pixel diffs.

This skill enables Claude to execute visual regression tests using tools like Percy, Chromatic, and BackstopJS. It captu...

Implements visual regression testing with screenshot comparison, diff detection, and CI integration using Playwright or...

Use when implementing UI components, design systems, or responsive layouts - verifies visual correctness through screens...

Use this skill when users mention "visual regression", "detect UI changes", "screenshot comparison", "visual testing", "...

Comprehensive visual regression testing using Playwright and jest-image-snapshot. Implements screenshot comparison, base...

AI-powered visual regression testing skill for e-commerce websites. Designs screenshot comparison workflows, mobile/desk...

Pixel-diff two environments (prod vs UAT, or local legacy vs upgrade) with Playwright screenshots and an HTML report. Us...

Validates visual consistency across UI changes using screenshot comparison. Uses MCP browser tools for automated screens...

identify screenshot with web evidence. Primary owner: visual identification and live verification. Do not use for: code...

Audits the visual presentation and responsive behavior of web interfaces for accessibility barriers. Use when a user ask...

Review visual work against approved art direction, hierarchy, composition, readability, consistency, production constrai...

Automated visual design review — screenshot V0 demo URLs or local HTML, analyze rendered output, and validate against br...

Start the website dev server and screenshot pages in both light and dark mode, at desktop and mobile widths, to catch vi...

Automated visual review pipeline — Playwright screenshots, self-analysis, fix loop, escalation. Used by Aphrodite for UI...

Audit and specify images and visual assets for meaning, accessibility, discoverability, context, performance, licensing...

Adds visual capabilities to the agent using Playwright MCP with Script Execution support.

You are a masterful Visual Storyteller, a hybrid designer and illustrator who can translate complex ideas and narratives...

Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand s...

Visual storytelling skill chain for DSH; use for narrative motion, scroll-driven UX, and stack-aware implementation rail...

Transforms data into compelling visual narratives by applying narrative structure, annotation techniques, scrollytelling...

Use when creating or modifying UI components, styling, themes, or layouts in peek-stash-browser. Follow these visual con...

Color scheme and icons for consistent Autopilot output. Reference when formatting agent output and status messages.

Create, extract, and apply portable visual design systems via visual-style.md files. Use when: (1) Creating a visual-sty...

Build a persistent visual brand identity for image generation. Defines how the brand looks visually — aesthetic, lightin...

This skill should be used when the user asks about "colors", "hex codes", "path colors", "tile background", "rendering o...

Run a visual design experiment (EXP): several isolated candidates against one frozen visual contract, judged blind again...

Visual iteration workflow for Script Kit GPUI. Use when making UI changes that need visual verification — focus indicato...

Compare implementation screenshot with Figma design for visual testing

Validate UI work by driving the browser — what to click, what to check, screenshot evidence, and strict resource discipl...

Use for visual UI verification with Playwright MCP. Test user flows, verify UI states, and catch visual regressions.

Run the app locally and take screenshots using Puppeteer to verify UI changes; use when validating demo pages, checking...

Implement visual regression testing with Playwright screenshots, Chromatic, Percy, and Argos CI. Covers baseline managem...

Design and implement visual regression testing for UI changes. Definesscreenshot coverage, rendering stabilization, base...

32 curated visual theme packs plus a deep knowledge base on color science, typography, motion, global design culture, an...

Master guide for multimodal vision UI auditing (Gemini 4 Argon/Pro Vision, Claude Sonnet 5.5 Vision, GPT-5.6 Sol Vision,...

Visual UI testing expert using Playwright MCP for browser automation. Use when testing responsive layouts, verifying UI...

Audit web and app interfaces using visual evidence. Use when Codex is asked to critique UI/UX, polish a design, inspect...

Use when: Assessing visual polish, validating game appearance, or claiming visual work is complete

Structured visual QA verdict for screenshot-to-reference comparisons

Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across mu...

Visually verify implemented features work correctly before marking complete. Use when testing UI changes, verifying web...

Verify UI-facing changes by running a screenshot-analyze-verify loop across configured viewports, with a browser-tool pr...

This skill should be used when the user asks to 'verify visual output', 'check how it looks', 'render and review', 'visu...

Visuelle Verifikation via Puppeteer. Erzwingt echte Sichtprüfung statt theoretischer Code-Analyse. Nimmt Screenshots, an...

Visualises any content as a rendered visual output — never plain text. Use this skill whenever the user says 'visualise...

Renderiza redes de personagens e locais com filtros temporais e agrupamento semantico para evitar saturacao visual no na...

Herramienta de visualización de datos estadísticos que proporciona una interfaz de alto nivel para dibujar gráficos esta...

Transforma contenido de texto complejo en diagramas de Mermaid profesionales. Proporciona prevención de errores de sinta...

Design and produce data visualizations, Base chart views, financial K-line charts, network graphs, AntV infographics, an...

Rules for charts and visualization. Use when the user asks for charts, graphs, plots, or visual representations (line, b...

Data visualization with OpenAlgo - candlestick charts, options payoff diagrams, P&L dashboards, and real-time Streamlit...

Generate shareable visual outputs for sports analytics: calibration curves, equity curves, radar charts, matchup cards,...

Choose between RViz2, Foxglove, Lichtblick, and Rerun to inspect robot behavior.

Publication-quality statistical visualization with mandatory best practices. Use when creating plots, charts, figures, o...

Knowledge about pyecharts chart creation, HTML report generation, and visualization best practices

Evaluate and implement visualization algorithms for ocean/foam rendering. Use when discussing rendering techniques, cont...