Web & Frontend

carthworks Skill

Inject styled developer signatures, author branding, project metadata, ASCII art, easter eggs, security contact information, and interactive DevTools inspection helpers (window.<App>) into the browser console log. Use whenever the user asks to add developer details, author info, console logs, branding banners, or DevTools easter eggs to a web app or website (React, Next.js, Vite, Vue, HTML).

dstreefkerk Bundle

Produce threat-modelling deliverables and artefacts — threat model documents, risk registers, kickoff packs, security acceptance criteria, executive summaries, compliance evidence packages, and squad self-serve kickstarts. Use this skill whenever the user asks to *produce*, *draft*, *generate*, *write*, or *create* a threat-modelling artefact — phrases like "draft a threat model document", "generate a risk register", "produce security acceptance criteria", "build a kickoff pack", "create an executive summary of threat model findings", "give me a TM doc for [system]", "help my squad self-serve a threat model on our component". This skill auto-detects available rendering capabilities (docx, pdf, xlsx agent skills, or Python with pandoc/openpyxl) and produces the highest-fidelity output available, falling back to markdown and CSV which work everywhere. Does *not* trigger for analytical asks like "what is STRIDE" or "what threats apply to [system]" — those go to the `threat-modeling` skill.

levyflux Bundle

Design, implement, improve, or review production-quality user interfaces through a product-design, frontend-engineering, and visual-validation workflow. Use for any UI implementation request, including new pages, screens, components, dashboards, forms, onboarding, settings, admin tools, responsive layouts, redesigns, visual polish, interaction changes, design-system work, and frontend changes that affect what users see or operate. Apply across web and app frameworks. Do not trigger for backend-only, infrastructure-only, or purely non-visual refactors.

loktar00 Bundle

Prove a frontend performance change with paired, measured before/after numbers instead of projections. Builds both git refs, serves each production build locally, drives a real signed-in browser N times per condition, and computes a verdict that fails on regression. Use when a change claims a performance benefit, when establishing a baseline before optimisation work, when a work package's verification contract names a metric, or whenever someone says something "should be faster".

loktar00 Bundle

The evidence standard for any QA work — visual, functional, regression, performance, accessibility, or mobile. Establishes what counts as proof, how to capture a baseline BEFORE changing anything, how to pair before/after when state drifts, and how to write a verdict that does not overclaim. Use whenever verifying a change works, before claiming something is done or fixed, when writing a verification plan, or when a test passes but you have not seen the thing actually work.

smturtle2 Bundle

Capture an ongoing idea stream verbatim and maintain a current-state HTML brief. Use for silent scribing or thought dumping, rather than requests for discussion or advice.

smturtle2 Bundle

Generate a visual blueprint before building new frontend UI or substantially redesigning a screen. Exclude small copy or styling changes, narrow bug fixes, and work that should preserve the existing design.

comsky Bundle

Diagnose and fix CJK (Korean, Japanese, Chinese) text-wrapping issues in web UIs. Systematically traces mid-syllable breaks, orphaned glyphs, and awkward line splits through a layered fix strategy covering global CSS cascade, component-library overrides, headline balancing, and translation-level phrase binding. Produces an evidence-based diagnosis and verification report before any code change is applied.

cookaihq Bundle

Use when the user wants to upload one local file into their own AWS SigV4-compatible S3 bucket (AWS S3, Cloudflare R2, MinIO/custom) and receive a public or presigned URL. Do not use for hosted temporary URLs without a user bucket, HTML preview, remote/base64 input, or bucket administration.

cookaihq Bundle

Use when the user wants to put a local HTML page (or any local file) online for preview and get a shareable URL — phrases like "在线预览"、"传到预览服务器"、"生成预览链接"、"preview.html 打不开/想发出去看"、"把这个页面发上去看效果"、"上传到 FTP 看预览". The skill auto-detects the entry file's associated assets (images/CSS/JS referenced by relative paths) and uploads them together so the online page renders correctly. Do NOT use for production deploys, npm publish, git push, or uploading to non-preview destinations.

cookaihq Bundle

Use when the user wants to turn a LOCAL file (image/audio/video/document) into a public URL that an AI API can consume — phrases like "把这个文件传上去拿个链接"、"上传文件换个 URL"、"这个视频/音频/PDF 传成在线地址给模型用". Also re-hosts a remote URL into a foxapi 72h short link. Returns a public URL valid for 72 hours. Do NOT use for HTML page preview (that's preview-share), production deploys, npm publish, or git push.

cookaihq Bundle

Use when the user wants to turn a folder of images + copy into a styled showcase page that mimics a known app's UI — phrases like "把这个文件夹做成小红书预览"、"做成小红书个人主页"、"生成小红书风格展示页"、"把这些图做成 XX 风格的页面". v1 ships the xiaohongshu (小红书) personal-homepage template. Generates a self-contained output folder (index.html + assets/) that opens locally and can be uploaded by the preview-share skill. Do NOT use for real deploys, or for uploading/publishing (that's preview-share's job).

get-convex Skill

Scaffold a brand-new Convex app from a one-sentence idea and build it live — a running Next.js + shadcn app with `convex dev` + `next dev` and error watchers already armed, going from idea to running app in under a minute (locally).

get-convex Skill

LABS — the FULL Convex quickstart: scaffold a Next.js + shadcn app from one sentence with passkey sign-in and an in-app feedback panel pre-baked, build it live, then PUBLISH to a public convex.app URL (with the user's confirmation).

otonashiz Bundle

将 Flomo 导出的 HTML 笔记文件转换为 Markdown 格式。当用户说"转换 flomo"、"flomo 转 md"、"转换笔记"或使用 /flomo-convert 命令时触发。自动查找 HTML 文件，提取时间范围，生成格式化的 Markdown 输出。

charleseungmin Bundle

Develop and modify the Exofit React components library in a way that matches its current architecture, public API shape, WebView bridge patterns, and TypeScript/React coding conventions. Use when Codex is working in this repository on chart components, wrappers, webview pages, hooks, routes, exports, Plotly configuration, postMessage handling, or related refactors that must stay consistent with the existing project structure.

akillness Bundle

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Use when the user wants architecture improvement candidates surfaced before choosing one. Triggers on: improve the architecture, find deepening opportunities, where should we refactor.

involvex Bundle

Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.

involvex Bundle

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.

bootgs Bundle

Explains bootgs' Virtual Transport Layer contract (how doGet/doPost events must be shaped for the router to resolve a controller method) and how to build a client that calls a bootgs backend from a web app UI, an HtmlService sidebar/dialog via google.script.run, or a deployed web app URL. Use when building a frontend that talks to bootgs controllers, or when requests aren't reaching the expected route.

bootgs Bundle

Documents apps-script-utils, a standalone guard/utility library for Google Apps Script (isX/nonX/requireX convention, A1-notation and sheet helpers, string/number/array helpers, typed exceptions, HTML/JSON/path helpers). Use when writing Apps Script code that needs input guards, spreadsheet range parsing, or common data utilities. Independent of any framework — also used internally by bootgs, so the two pair naturally if the project already uses bootgs.

mmkkkkzz Bundle

業務改善・BPR・システム導入のAs-is / To-beを、資料・議事録・画像・箇条書きから構造化し、必要なヒアリングをまとめて行った上で、保守可能なJSONと自己完結型HTML図として生成・更新・レビューする。現行業務、将来業務、業務フロー、システム連携、手作業、RPA、課題、KPI、変更点を可視化したい依頼で使用する。一般的な単発フローチャートや、見た目だけの画像生成には使用しない。

pramoddutta Skill

Scans a Playwright spec or Page Object for brittle locators and rewrites them to resilient ones. Use when an SDET says "fix these locators", "my selectors are flaky", "replace XPath with getByRole", "make these locators resilient", or pastes code full of nth-child/CSS-class/text selectors. Produces a before/ after rewrite map plus patched code — the engineer verifies each swap.

pramoddutta Skill

Generates CI configuration (GitHub Actions) for a Playwright suite. Use when an SDET says "set up Playwright in CI", "add a GitHub Actions workflow", "shard my tests across jobs", "upload traces and the HTML report", or "run browsers in a matrix". Produces a workflow with install, sharding, blob/HTML reporting, and artifacts — a draft the engineer commits and runs on their pipeline.

pramoddutta Skill

Sets up Playwright visual/screenshot regression testing. Use when an SDET says "add visual regression", "snapshot this component", "set up toHaveScreenshot", "mask the dynamic parts of this page", or "manage baselines". Produces snapshot tests with masking, thresholds, and a baseline strategy — a draft the engineer runs to generate and review the first baselines.

pramoddutta Skill

Integrates automated accessibility checks into Playwright tests using axe-core. Use when an SDET says "add a11y checks", "run axe on this page", "audit accessibility", "check WCAG compliance", or "triage these accessibility violations". Produces @axe-core/playwright-based tests, severity triage, and WCAG mapping — a draft the engineer runs, knowing axe catches only ~30-40%.

modem-dev Skill

How to write JSDoc (/** */) and inline (//) comments in the Astro codebase, for contributors reading the source — not end users. Use whenever writing or editing comments in .ts/.js source, including comments added incidentally while fixing bugs or building features. Does not cover the @docs-generated config/error reference.

modem-dev Skill

Use when creating, modifying, debugging, or running Qwik Playwright e2e tests under e2e/, including router, adapters, docs, CLI, and React integration suites.

kreuzberg-dev Skill

Use tree-sitter-language-pack api reference documentation.

kreuzberg-dev Skill

Use tree-sitter-language-pack cli reference documentation.

kreuzberg-dev Skill

Use tree-sitter-language-pack mcp reference documentation.

kreuzberg-dev Skill

Use when parsing source, extracting code structure, or detecting a language through the tree-sitter-language-pack MCP server's tools, rather than shelling out to the ts-pack CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.

managedcode Bundle

Use Biome in .NET repositories that ship Node-based frontend assets and want a fast combined formatter-linter-import organizer for JavaScript, TypeScript, CSS, JSON, GraphQL, or HTML. USE FOR: biome.json or @biomejs/biome setup; fast frontend formatting and linting; replacing overlapping frontend style tools deliberately. DO NOT USE FOR: ESLint-only plugin coverage; runtime site audits such as headers, accessibility, or browser behavior. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

managedcode Bundle

Use ESLint in .NET repositories that ship JavaScript, TypeScript, React, or other Node-based frontend assets. USE FOR: the repo has package.json, eslint.config.*, .eslintrc*, tsconfig.json, or JS/TS/React frontend files; the user asks for JavaScript or TypeScript linting, React rule. DO NOT USE FOR: CSS ownership by itself; route that to stylelint; HTML-only checks on static output; route that to htmlhint. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

managedcode Bundle

Use SonarJS-derived rules in .NET repositories that ship JavaScript or TypeScript frontends and need deeper bug-risk, code-smell, or cognitive-complexity checks than a minimal ESLint baseline. USE FOR: SonarQube, SonarCloud, or eslint-plugin-sonarjs setups; frontend code smells; cognitive complexity and deeper bug-risk rules. DO NOT USE FOR: lightweight base lint setups with no extra smell or complexity rules; teams that reject Sonar tooling. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

managedcode Bundle

Use Metalint in .NET repositories that ship Node-based frontend assets and want one CLI entrypoint over several underlying linters. USE FOR: unified frontend lint commands; combined ESLint, Stylelint, HTMLHint, or similar checks; CI orchestration over multiple frontend linters. DO NOT USE FOR: simple repos where Biome already covers the required surface; teams that have not decided which underlying linters own each file type. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.