Web & Frontend

tentacle-pro Bundle

Posts content to WeChat Official Account draft box via official API. Supports HTML/Markdown input, cover image upload, inline image upload, and draft saving. Use when user asks to publish article draft to WeChat.

tentacle-pro Bundle

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md转html", "微信外链转底部引用", or needs styled HTML output from markdown.

tentacle-pro Bundle

Enterprise markdown-to-html renderer via API service. Sends markdown to api.tentacle.pro and writes returned html locally.

sudo-pradip Skill

Use when the user says "hey-god-build-a-new-world" (or the old chant "hey-god-help-to-build-new-world") or is starting a new project, service, or major component from (near-)empty — project setup, architecture design, greenfield builds.

syncfusion Bundle

Provides comprehensive guidance for implementing the Syncfusion JavaScript PDF library (@syncfusion/ej2-pdf) to create and manipulate PDF documents programmatically across TypeScript, JavaScript, Angular, React, Vue, and ASP.NET platforms. Use this when working with PDF creation, form filling, annotations, document merging/splitting, text or image extraction, or digital signatures.

taewanu Bundle

Turn a tangled technical thing (a gnarly bug and the decision it forces, a non-obvious system behavior, an architectural "why") into ONE self-contained, conclusion-first HTML page that explains it, can be handed off, and copies itself back out as Markdown. Use when the user wants something *explained and handed off*: "이거 왜 이런지 설명자료로 만들어줘", "남들도 이해하게 정리해줘", "이슈 설명 페이지", "결정 배경 정리", "explain this so the team gets it", "write up why this happens", "make a shareable explainer", "document this decision/tradeoff". Sibling of `visual-code-lecture` / `visual-code-review`, which annotate *real code*; reach for THIS when the subject is a situation, a decision, or a phenomenon. Not `visual-ui-compare` (pick by eye), not `/code-review` (audit).

taewanu Bundle

Render a diff, PR, or slice of code as a single self-contained HTML page: the real diff with inline margin annotations, a flow diagram, key snippets, risks, open questions. Click-to-copy notes round-trip decisions to chat. Two modes: **review** (a change/diff/PR) and **explain** (existing code or a subsystem). Use whenever the user wants a change or codebase made legible visually ("이 diff 설명해줘", "PR 리뷰 보기 좋게 만들어줘", "이 코드 흐름 그림으로", "아키텍처 html로 설명", "walk me through this PR", "explain this diff/PR as html", "visualize this change", "help me understand this module") or is about to dump a long diff as plain markdown. NOT a graded correctness audit: that's `/code-review`; this can lay those findings over the diff.

taewanu Bundle

Generate a single self-contained HTML page for making a visual decision by eye, open it in the browser, and let the user pick: a grid of variants side-by-side (color, size, spacing, shadow, radius, border, badge or card styles), or a live preview with sliders when the choice is motion or a continuous range (animation, easing, duration, transitions). Use whenever the user wants to compare or tune a visual choice ("비교해서 보여줘", "어떤 게 나아?", "A/B 보고 싶어", "html로 만들어 봐", "직접 보고 결정할게", "easing 비교", "이 애니메이션 느낌 좀 보자", "transition 속도 조절", "compare visually", "show me side by side", "which one looks better?", "tune this animation", "slider for this") or any time you're about to use AskUserQuestion with 2+ options for a visual property.

taewanu Bundle

Walk through code one line at a time as a guided, hand-drawn lecture: one self-contained HTML page you SCROLL, code pinned left and notes scrolling right, one note and its line(s) lit at a time, like a 족집게 강의. Use whenever the user wants code *taught* sequentially rather than scanned ("코드 한 줄씩 설명해줘", "족집게 강의처럼", "이 함수 따라가면서 설명", "이 로직 흐름 짚어줘", "라인별로 설명", "walk me through this line by line", "teach me this code", "explain this step by step", "guided tour of this function/file", "narrate this logic"). Sibling of `visual-code-review`, the static all-annotations-at-once page; reach for THIS when the goal is a paced, one-thing-at-a-time walkthrough. NOT a correctness audit (`/code-review`).

tanstack Bundle

Ship TanStack Charts with meaningful accessibility, deterministic SSR and hydration, correct adapter lifecycle, renderer and export choices, exact package subpaths, and explicit React Native validation.

tanstack Bundle

Migrate Observable Plot, Recharts, Chart.js, ECharts, direct D3, or another renderer to TanStack Charts by translating semantic ownership and proving visual, interaction, accessibility, export, bundle, and performance parity.

thorwhalen Skill

Analyze a captured UX evidence bundle (screenshots + DOM + a11y tree) for usability and accessibility issues.

thorwhalen Skill

Use this skill whenever the user wants to add, modify, or audit the chat UI / streaming / wire-protocol layer of an embedded AI assistant. Triggers include "build a chat UI", "add streaming responses", "render tool calls in the chat", "add thread CRUD", "show markdown in the assistant", "branch conversations", "make the AI response copyable", "switch from polling to streaming", "embed Claude into my React app", "set up assistant-ui", "use Vercel AI SDK in my app", "expose chat over SSE from FastAPI", or any task on the frontend chat layer of a React + Vite + shadcn application. Read this skill BEFORE writing any new chat component, runtime hook, or SSE endpoint.

tjboudreaux Skill

Anchor every engineering decision in user value, measurable outcomes, accessibility, and cross-platform experience coherence.

toolbox-playground Bundle

Productivity and document creation skill. Use when the user wants to create documents, presentations, spreadsheets, dashboards, or needs help with planning and organization tools. Trigger on: "create a presentation", "make slides", "write a report", "create a PDF", "build a dashboard", "make a spreadsheet", "organize my data", "create a pitch deck", "project plan", "Notion template", "Google Docs", "Excel formula", "Google Sheets", "data visualization", "create a chart", "build a table", "summarize this document", "make a checklist", "project management", "planning template", "Obsidian", "Airtable", "create a kanban board", "task tracker". Also trigger when the user wants to turn a presentation, PDF, or slide deck into a standalone HTML webpage: "create a webpage from this PDF", "convert my presentation to a webpage", "build an HTML page from my slides", "turn this slide deck into a page", "transformar PDF em página web", "criar página HTML a partir dos slides", "transformar apresentação em página web", or wh

toolbox-playground Bundle

Transforms DevOps Mentoria PPTX slides into Carreira Tech "Do Zero ao Primeiro Emprego" beginner-friendly slides, preserving original images at correct aspect ratios and adapting all content for an absolute beginner audience using the TBXTech visual identity. Trigger on: "transformar slides da mentoria para carreira tech", "adaptar aula devops para iniciante", "criar slides do curso carreira tech", "converter pptx mentoria para iniciante", "retraduza o ppt", "adaptar aula para público iniciante", "criar nova aula carreira tech", "transform mentoria slides", "adapt devops slides for beginners", "criar slides TBXTech", "nova aula do curso carreira tech". Also trigger when: user shares a PPTX from the DevOps Mentoria and asks to adapt it for the Carreira Tech course, or asks to create a new lesson in the TBXTech beginner pattern. Do NOT trigger for: creating HTML pages from slides (use productivity), generic presentation creation (use productivity), video or image generation.

toolbox-playground Bundle

Creates a spoken video script (roteiro) plus a local HTML slide presentation for a self-recorded talking-head video — the creator records themselves; AI prepares the material. Researches REAL data and verified sources on the internet for the topic. Trigger on: "cria um roteiro sobre", "roteiro para vídeo sobre", "roteiro e apresentação", "roteiro e slides", "me ajuda a preparar um vídeo sobre", "apresentação para meu vídeo", "slides para o vídeo de", "vou gravar um vídeo sobre", "preparar conteúdo sobre", "create a video script about", "script and slides for my video", "help me prepare a video about". Also trigger when: the user gives a content topic/theme (career tips, free courses, certifications, tech questions like "vale a pena X em 2026?") and wants material to record a video about it. Do NOT trigger for: fully AI-generated videos with narration and rendering (use media-content-creation), webpages from existing slide decks (use productivity), blog posts without a video (use writing).

netdata Skill

Run, write, and maintain ai-viewer tests across Go backend and React frontend. Use when adding or changing tests, debugging CI failures, managing fixtures, or running benchmarks.

netdata Skill

Apply React/TypeScript/Vite patterns used in ai-viewer's frontend. Use when editing frontend/ — pages, components, API client, SSE handling, D3 visualizations.

ohyeh Skill

Turn a fuzzy subject — a problem description, an incident, a decision, a long-form idea — into a polished deliverable in the user's chosen format (md, html page, Artifact, image, or plain prose). Runs the writing production line (mine → structure → tighten) with stop-slop discipline, then hands rendering to using-design-skills. Invoke when the user wants something EXPLAINED WELL as a document/page, not when they just want code changed.

ohyeh Bundle

Which design skill, in what order. Invoke BEFORE any visual output: web page, landing page, dashboard, product UI, mobile screen, HTML report, diagram, chart, plan page, artifact, motion, redesign, 「做個頁面」, 「畫圖」, 「報告做成網頁」, plus module or API interface design. Picks one direction authority and an executor per stage, closes with an evidence check. Even a 1% chance means invoke it.

ommakes Bundle

Component selection rubrics organized by job-to-be-done. Use after vois-patterns determines structure, before vois-tokens applies tokens. Optionally records each choice via the vois_record_component_choice MCP tool if one is available. Use when deciding between similar components — Dialog vs Drawer, Toast vs Banner, Select vs Combobox, etc.

openapi Skill

Openapi utility services - real-time currency exchange rates, HTML-to-PDF conversion (renders JavaScript), .it domain registration/management, and managed RAG (retrieval-augmented generation over your documents). Use for these one-off utility tasks.

pentesterflow Bundle

Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked service_role) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging "certificate"/verification/entitlement rows the app trusts). Use when the target's frontend talks to *.supabase.co, ships an anon JWT, or you see /rest/v1/, /auth/v1/, /storage/v1/ requests.

peterfox Bundle

Generate visually stunning, colorful, procedural 3D backgrounds for Remotion videos using react-three-fiber and GLSL shaders. Use this skill whenever a user asks for: animated backgrounds, 3D backgrounds, shader backgrounds, liquid gradients, plasma effects, aurora effects, galaxy/nebula backgrounds, noise-based patterns, or any kind of procedurally generated visual backdrop for Remotion. Also trigger when the user wants to make a Remotion video "look more interesting", "add a background", or "make it pop visually". All backgrounds are deterministic — driven by useCurrentFrame() — so they render frame-perfectly in Remotion.

pkc278 Bundle

Use this skill ONLY when the user EXPLICITLY requests filing an upstream issue for MoviePilot core, frontend, or an installed plugin, for example "反馈 issue", "提 issue", "报 bug", "给 MP 提 issue", "让上游修一下", "提交错误报告", "提需求", "功能请求", or English "file an issue / report a bug / open an upstream issue / feature request". A bare problem report is not enough: diagnose locally first. This skill uses its own scripts under `scripts/`; it does not add or call dedicated Agent tools for collect / prepare / submit.

gualask Bundle

Recover the goal behind a reported symptom, or the shape of a change nobody has decided yet. Use when the user reports a symptom, an experience, or a doubt without naming what should change, or asks what a change would consist of while its shape is still open — even when the target is already named. Do not use once the request names both its target and the change to make to it, even when voiced as a doubt: a named component with its technical alternatives, a proposal whose worth or impact is the question, a bounded edit, a defect whose fix is one localized edit, or code review.

hanzili Skill

Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser automation MCP server and Chrome extension.

home-assistant Skill

Home Assistant frontend Lit conventions. Use when working with reactive properties, internal state, DOM queries, lifecycle methods, or render-derived state.

home-assistant Skill

Home Assistant standalone demo structure, configurations, URL navigation, mocked APIs, shared demo stubs used by gallery, and verification. Use when changing files under demo/, changing gallery consumers of demo/src/stubs/, or running and validating the demo.

home-assistant Skill

Home Assistant frontend TypeScript conventions. Use when defining or reviewing backend data contracts, optional schemas, shared types, assertions, or Lit lifecycle types.

home-assistant Skill

Home Assistant frontend event patterns. Use when typing event handlers, using HASSDomEvent types, dispatching with fireEvent, or declaring HASSDomEvents and event maps.

home-assistant Skill

Home Assistant frontend PR and review guidance, including implementation quality, existing review feedback, established design patterns, and the authority of UI/UX evidence. Use when reviewing frontend changes, preparing a PR, checking recurring review issues, or applying the PR template.

home-assistant Skill

Home Assistant frontend gallery structure, pages, demos, content, and verification. Use when changing files under gallery/, including gallery markdown, TypeScript demos, sidebar entries, mock data, page generation, or gallery builds.

home-assistant Skill

Home Assistant frontend styling, theming, spacing, responsive layout, RTL, and View Transitions guidance. Use when editing CSS, layout, motion, or visual component structure.

home-assistant Skill

Home Assistant frontend testing and validation workflow. Use when adding or updating tests, running lint, TypeScript checks, Vitest, Playwright e2e suites, dev servers, or chart-data benchmarks.