Web & Frontend

neuralblitz Skill

AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer

neuralblitz Bundle

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".

arcanedge-ai Skill

Use before finalizing a meaningful code change. Reviews the final diff for correctness, scope control, maintainability, validation gaps, safety risk, performance risk, accessibility risk, and subagent claims that still need verification.

gustavosilveira23 Bundle

Expert motion design and creative coding for the web -- the layer beyond static UI: scroll-driven animation, WebGL/canvas, generative and interactive effects, and the craft of movement itself. Activates when building, evolving, reviewing, or planning any motion or interactive-graphics work -- animated heroes, scroll storytelling, parallax, particle fields, shader/distortion effects, 3D scenes, custom cursors, smooth scroll. Triggers on: motion design, animation, scroll animation, ScrollTrigger, GSAP, Lenis, smooth scroll, parallax, WebGL, Three.js, react-three-fiber, R3F, canvas, shader, GLSL, particles, generative, Perlin/simplex noise, distortion, liquid hover, image hover effect, custom cursor, magnetic button, split text, 'make it feel alive', 'creative coding', 'interactive site', 'immersive', 'like Awwwards / bruno-simon / noomo'. Also activates on: 'animate the entrance', 'scroll effect', 'floating 3D object', 'reacts to the mouse', 'premium scroll feel', 'particle background'. Applies whenever movemen

vorlaxen-labs Skill

Frontend decision boundaries. Constrain decisions, not implementations. Use for web UI components, pages, forms, client-side state, and frontend code.

wowcube Skill

Stage 3 component of the WowCube pipeline, invoked by cube_orchestrator — not a standalone user entry point. Use only when the orchestrator routes to asset generation because the manifest exists but packed assets and _ids.h do not. Generates AI sprite PNGs (from each sprite's gen_prompt) and synthesised WAV sounds (encoded to beta mp3), pauses for user review, then packs them into the beta container: `app_<game>/index.bin`, `art/packed/*.raw` + `*.pal`, `sound/assets/*.mp3`, and `src/app_<game>_ids.h`.

wowcube Skill

Stage 2 component of the WowCube pipeline, invoked by cube_orchestrator — not a standalone user entry point. Use only when the orchestrator routes to prompt generation because a GDD exists but the prompts file and asset manifest do not. Decomposes a GDD into implementation prompts plus the asset manifest, where every sprite carries a ready-to-run AI generation prompt (gen_prompt).

wowcube Skill

Infrastructure-and-packaging component of the WowCube pipeline, invoked by cube_orchestrator — not a standalone user entry point. The orchestrator routes here at two points: the infra gate before Stage 4 (scaffold app_<game> from the template, pack art, and smoke-build + launch the simulator) and Stage 5 after implementation (build the ARM device target and verify the cube-loadable .oct embeds the code). Use only when the orchestrator routes here.

yxy050208 Skill

基于已注册实验的真实产物撰写中英实验报告；use when producing a lab report, design record, reproducibility package, or formal HTML/PDF output

lucasaero-pr Skill

Acts as a Senior QA Engineer & Testing Architect (10+ years) specializing in Node.js/Next.js test automation. Delivers Jest/Supertest (95%+ coverage), Cypress/Playwright E2E, RTL, NestJS/Next.js testing patterns, Testcontainers, BDD/Pact, k6/Artillery, OWASP ZAP, CI quality gates. Use when the user asks for test strategy, test suites, coverage, E2E, integration tests, performance/security testing, or quality engineering for NestJS/Next.js.

lucasaero-pr Bundle

Define and implement a complete test strategy for Node.js/Next.js/NestJS projects. Use when the user asks for a test pyramid, complete test suites (unit, integration, E2E), coverage thresholds/CI gates, performance testing (k6/Artillery), security (OWASP ZAP), accessibility (axe-core), or mentions tools like Jest, Supertest, Cypress, Playwright, or Pact.

lceric Bundle

Build, refactor, and troubleshoot sem.ai-style Next.js console/admin features in an existing repo. Use this skill whenever the user asks for console/dashboard/admin pages, login-gated app flow, NewAPI/OpenAI-compatible management API integration, Node-layer /api proxying, HTTP Only cookie/session auth, token/key management UI, avoiding Next redirects/caching on API routes, or splitting large frontend components into maintainable modules. This skill is especially relevant for Next App Router projects where AGENTS.md warns that framework APIs may differ from prior training data.

lceric Bundle

Generate images using gpt-image-2 API. Use this skill when the user asks to generate, create, or draw an image. Triggers on prompts like "generate an image of...", "create a picture showing...", "draw...", "设计一个...图片", "生成...图", or any request to produce visual content. Also use for generating reference sheets, concept art, UI mockups, character designs, and layered component breakdowns for animation (Spine2D, Live2D, etc.).

mathaix Skill

Choose and run the smallest safe OpenClaw Machines verification path for backend, frontend, Worker, host enrollment, Firecracker, rootfs, and self-hosted changes.

scottyroges Skill

Use when the user asks to be quizzed on — or to verify their understanding of — a PR, commit, branch, diff, spec, plan, or a generated visual-skills doc. Generates a comprehension-check HTML quiz grounded in the real source, and optionally grades free-text answers live in the terminal.

scottyroges Skill

Use when the user asks to turn a spec, plan, or design markdown into a self-contained, visually readable HTML document grounded in the real codebase — with diagrams, a file tree, annotated code, and open questions. The general-purpose illustrated-doc renderer (for an approval-focused design spec use visual-spec; for a code change use visual-recap).

scottyroges Skill

Use when the user asks to visualize, render, or "make readable" a design spec / design doc / RFC / proposal as a self-contained HTML page — to get a reader up to speed fast and let them approve it. Covers design docs, RFCs, and spec markdowns (e.g. anything under a docs/ specs folder) grounded in the real document.

scottyroges Skill

Use when the user asks to map, document, or make sense of a whole codebase as a standing self-contained HTML atlas. Produces orientation-first system and domain pages plus recursive conceptual topics for focused technical depth.

scottyroges Skill

Use when the user asks to visualize, render, recap, or "make readable" a pull request, commit, branch, or git diff as a self-contained HTML review document. Covers PR recaps, commit/branch reviews, and working-tree diffs grounded in the real repo.

pedronauck Skill

React component patterns — Tailwind styling, size, explicit props, useMemo, useEffect, hooks. Use when writing or reviewing React components, views, or hooks in the frontend. Don't use for non-React JS/TS (use javascript), folder placement (use folder-structure), or general size limits outside components (use code-standards).

profpowell Skill

Build content-focused websites with Astro. Use when creating .astro files, working with content collections, configuring islands architecture, or deploying to Cloudflare/DigitalOcean.

profpowell Skill

Modern CSS organization with native @import, @layer cascade control, CSS nesting, design tokens, and element-focused selectors. AUTO-INVOKED when editing .css files.

dokhacgiakhoa Skill

Tailwind CSS v4 principles and modern design tokens.

wubabalala Bundle

Playwright browser automation with two modes: (A) Record mode — automate web interactions (forms, clicks, screenshots/Canvas export) requiring JS rendering or login state. (B) Direct scripting — render Mermaid diagrams, charts, or HTML to PNG images without recording. Keywords: playwright, codegen, browser automation, web scraping, architecture diagram, render chart, Mermaid to PNG, screenshot export, canvas export. Do NOT trigger for: static page fetching (use WebFetch/curl), pure API calls, or DOM text extraction without interaction.

a-attia Bundle

Author or revise any project document whose primary audience is a HUMAN -- README.md, PLAN.md, per-paper survey notes (notes/survey_*.md), bibliography collection logs (references/_collection_log.md), reviewer-response drafts, per-section research notes (notes/section_*.md), per-component implementation plans (notes/impl_*.md). Apply the human/agent audience split (these docs are NOT downstream renderings of AGENTS.md), the two-tier readability structure (orient-quickly + look-up-later), proper sectioning + cross-references, narrative prose over telegraphic fragments, and tables/trees/code-blocks where they aid scanning. Use whenever the agent will produce text that a human collaborator (the user or a co-author or a reviewer) is expected to read for review or reference.

agentpit-io Skill

A 股、港股与美股的投研总调度技能，覆盖深度研究、快速扫描、投委会评审、游资/龙虎榜(LHB)分析、杀猪盘识别、估值测算、IC 投资备忘录，以及 Bloomberg 风格的 HTML 报告。

ashish7802 Skill

Enforces Svelte 5 runes ($state, $derived, $effect) and universal data loading standards.

ashish7802 Skill

Enforces type-safe route loaders, progressive enhancement actions, and optimistic mutations.

awesomemotive Bundle

Use when integrating, debugging, asking about, or auditing PushEngage push notifications in any mobile app (iOS, Android, Flutter, React Native). Detects the customer's platform and hands off to the matching platform spoke.

awesomemotive Bundle

Use ONLY when the active repo is a native iOS app (Podfile, Package.swift, or *.xcodeproj present at the project root) AND there is NO `pubspec.yaml` with a `flutter:` SDK block AND NO `package.json` with `react-native` or `expo` dependency. Handles full PushEngage integration end-to-end, plus debugging existing integrations. Do not use for Android, Flutter, or React Native apps even if PushEngage is mentioned.

awesomemotive Bundle

Use ONLY when the active repo is a native Android app (build.gradle or build.gradle.kts at root with AndroidManifest.xml under app/src/main) AND there is NO `pubspec.yaml` with a `flutter:` SDK block AND NO `package.json` with `react-native` or `expo` dependency. Handles full PushEngage integration end-to-end, plus debugging existing integrations. Do not use for iOS, Flutter, or React Native apps even if PushEngage is mentioned.

awesomemotive Bundle

Use ONLY when the active repo is a Flutter app (`pubspec.yaml` with a `flutter:` SDK block). Handles full PushEngage integration end-to-end (Dart init + Android native config + iOS native config + NSE) plus debugging existing integrations. Do not use for native iOS, native Android, or React Native apps even if PushEngage is mentioned.

awesomemotive Bundle

Use ONLY when the active repo is a React Native app (`package.json` with `react-native` dep, typically alongside `ios/` and `android/` folders, Turbo Modules / New Architecture). Handles full PushEngage integration end-to-end (JS init + Android native config + iOS native config + NSE) plus debugging existing integrations. Do not use for native iOS, native Android, or Flutter apps even if PushEngage is mentioned.

cham0287 Bundle

Review React and React Native code structure using contextual rules for ownership, data access, UI-to-code mapping, composition, naming, and accessibility. Use when a user asks to review, refactor, or design React code or a component-heavy diff. Inspect real call sites and repository conventions before reporting findings. Do not use for visual styling critique, broad application architecture, or performance review without structural evidence.

cham0287 Bundle

Create a concise, self-contained HTML artifact containing only the prompts the user directly entered in one Codex task. Use when the user asks to view, export, collect, review, or share their prompts from the current or a specified Codex task/session, especially requests for a prompt log, prompt history, or user-input-only artifact.

contentstack Skill

Use when changing Next.js App Router structure, next.config.mjs, images, PostCSS, or Tailwind in kickstart-next-ssr.