Web & Frontend

mcj-coder Skill

Use this skill whenever deploying or auditing environments to ensure each environment can be mapped to explicit component versions and tags, preserving immutable provenance.

mcj-coder Bundle

Use when repository includes .NET Aspire usage, distributed application setup, or cross-component behavior validation. Produces BDD-style integration tests with health checks and observability verification.

mcj-coder Bundle

Use when user decides repository organization, where functionality should live, or reviews component boundaries. Determines cross-component ownership and placement (macro), delegates intra-component file layout to scoped-colocation (micro).

barkleesanders Bundle

Build, structure, and ship web apps/sites with the Hono framework — the the user default for new sites and for converting React SPAs to SSR. Use when the user wants to create a Hono app, convert/remake a site in Hono, add SSR + islands on Cloudflare Workers, set up Hono routing/middleware/JSX, choose between hono/jsx (server) and hono/jsx/dom (client), wire the Vite build, or asks "is this Hono", "make it Hono", "Hono SSR", "Hono on Workers", "@hono/jsx", "islands", "hono framework". Loads current, verified Hono API patterns so you leverage the framework fully instead of guessing from memory.

barkleesanders Bundle

Design and build frontend interfaces with high design quality. Picks a bold aesthetic direction, then hands the brief to the Hallmark anti-AI-slop engine (default) to design/build/audit/redesign — or generates screens via Google Stitch MCP when the user explicitly asks for Stitch. Use for UI design, screen mockups, design systems, building components / pages / apps, or any "design" / "build a [component/page/UI]" request.

jankneumann Bundle

Render the architecture graph as a single self-contained interactive HTML page — foldable structure tree, animated dependency graph, and cross-connection tracing

barkleesanders Bundle

Reverse-engineer ANY binary, bundle, distributable, OR the private API of a website you're logged into. Binaries — compiled native (.exe/.dll/.so/.dylib/Mach-O), JVM (.jar/.apk/.dex), .NET (.dll/.exe IL), iOS (.ipa), browser extensions (.crx/.xpi), WebAssembly (.wasm), Python bytecode (.pyc), React Native Hermes (.hbc), JS bundles, firmware blobs, installers (.deb/.rpm/.dmg/.msi). Websites — record a real logged-in session to HAR (incl. the log-out/log-in auth handshake), distill it, and generate a typed TypeScript client + MCP server. Routes to the correct tool per artifact class — Ghidra is just one tool in the kit. Use when the user says decompile, disassemble, reverse-engineer, RE, "look inside this binary/app/extension/firmware", "make an API/MCP server for this website", "capture the network calls this site makes", HAR, triage malware, audit a binary for vulns, diff functions across versions, or port a closed-source thing to a CLI. Does NOT debug or pentest live websites — for debugging route to /debug

hairyf Bundle

Wagmi — React/Vue/Solid hooks and Core for Ethereum; config, connectors, read/write contracts, TanStack Query.

barkleesanders Bundle

Deep multi-source research on a topic across a 10-provider search stack via the `websearch` CLI with automatic quota failover — self-hosted SearXNG and Marginalia (both keyless/unmetered), Linkup, Parallel, You.com, Tavily, Brave, Jina, Exa, TinyFish — plus the Exa MCP for filtered/semantic search and full-page crawling. Fans out queries, reads sources, adversarially verifies every load-bearing claim, and synthesizes a cited HTML report. Use when the user says 'deep research', 'research <topic>', 'dig into <topic>', 'deepsearch', '/deepsearch', or wants a thorough, fact-checked, multi-source brief — NOT a single quick lookup (use the plain WebSearch tool for that).

barkleesanders Skill

Drive the macOS GUI (click / type / scroll / drag / screenshot any native app) from Claude or any CLI via the open-source `cua` command — real hardware CGEvents (cliclick) + screenshots (screencapture) + Accessibility element finding (osascript). No Codex, no cloud vision, no reverse-engineering. Ships a Cobra CLI AND an MCP server (`cua_*` tools). Use when the user wants to operate a native Mac app, automate a desktop task, take over a GUI, click a control that ignores synthetic clicks (file pickers, Chrome/Polymer toggles, "Load unpacked"), or asks about "computer use", "control my Mac", "drive an app", "click/type in <app>", "cua". Replaces the old /computer-use-bridge skill.

barkleesanders Skill

Default output format for reports, summaries, analyses, dashboards, audits, comparisons, digests, briefings, and any deliverable with structured/spatial information. Generates a single self-contained HTML file (no external dependencies) the user can open in a browser, share, print to PDF, or paste into Notion. Lightweight cousin of /design and /magazine — no AI generation server, no editorial chrome, just clean Tailwind-via-CDN HTML that beats Markdown on scannability, comparison, and feel. Use whenever the user asks for a report, summary, breakdown, analysis, audit, dashboard, comparison, or any deliverable that previously would have been a .md file. Triggers: 'report', 'summary', 'audit', 'analysis', 'dashboard', 'compare', 'breakdown', 'rundown', 'brief', 'digest', 'overview', 'recap', 'write up', 'document', 'deliverable'. Reference: https://thariqs.github.io/html-effectiveness/

jankneumann Bundle

Drive a deployed frontend via Playwright using OpenSpec WHEN/THEN scenarios; emit behavioral_failure findings.

aradotso Skill

Build and customize a web-based digital banking dashboard with HTML, CSS, and JavaScript for financial tracking and analytics

jankneumann Skill

Guides stable API and interface design for REST endpoints, GraphQL schemas, module boundaries, and component contracts. Use when designing new APIs, defining type contracts between modules, establishing boundaries between frontend and backend, or modifying existing public interfaces. Covers Hyrum's Law, contract-first design, the One-Version Rule, REST resource patterns, pagination, PATCH semantics, and idiomatic type-system patterns in both TypeScript (discriminated unions, branded types) and Python (Pydantic discriminated unions, NewType branded types, FastAPI route shapes, frozen dataclasses).

jankneumann Skill

Optimizes application performance with the MEASURE → IDENTIFY → FIX → VERIFY → GUARD workflow. Covers frontend Core Web Vitals (LCP ≤ 2.5s, INP ≤ 200ms, CLS ≤ 0.1), bundle budgets, and React re-render hygiene, PLUS backend latency budgets, Postgres/MySQL EXPLAIN ANALYZE workflows, N+1 query detection, connection-pool sizing, and async profiling with py-spy / cProfile. Use when performance requirements exist, when Core Web Vitals or p95 latency miss thresholds, or when profiling reveals bottlenecks that need fixing.

frumu-ai Skill

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

fakhriaditiarahman Skill

Specialist in Modern Web Development using Next.js 14+ with App Router. Expert in React Server Components (RSC), Server Actions, Streaming, and Vercel-native optimization.

fakhriaditiarahman Skill

Expert in the Laravel ecosystem (v11+), specializing in full-stack development using TALL (Tailwind, Alpine, Laravel, Livewire) or VILT (Vue, Inertia, Laravel, Tailwind) stacks. Deep mastery of Database optimization (MySQL, PostgreSQL), Clean Code, and Scalable Architecture.

fakhriaditiarahman Skill

Expert in crafting, optimizing, and evaluating effective prompts for Large Language Models. Specializes in advanced prompting techniques (CoT, ReAct, Few-Shot) to maximize model performance and reliability.

frumu-ai Skill

Build an interactive HTML dashboard with charts, filters, and tables

frumu-ai Bundle

Suite of tools for creating elaborate, multi-component HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

frumu-ai Skill

Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".

outlinedriven-odin-gemini-cli-extension Bundle

One-shot bootstrap of strict-mode tooling per ecosystem plus per-task GOALS.md scaffolding so an agentic loop can self-verify. Writes typechecker / linter / schema-validator config for TS (strict + noUncheckedIndexedAccess + exactOptionalPropertyTypes), Python (Pyright strict, Ruff strict), Rust (Clippy deny-correctness), Go (golangci-lint with staticcheck), OCaml (dune --release) at project edges; establishes a `.agent-tasks/<id>/GOALS.md` per-task convention distinct from project-stable AGENTS.md. C++/Java/Kotlin and framework specifics (Spring Boot, Nest, React-strict) are out of scope in this commit — surface as a follow-up when invoked on those ecosystems. Trigger on new project bootstrap, agentic-task setup, "make this self-verifying", "set the loop's goal", "scaffold goals for this issue". Pairs with `llm-self-loop` runtime — bootstrap once, run many.

notque Bundle

Design workflows — UX copy, design systems, design critique, accessibility review, design handoff, user research synthesis. Use when writing UI copy, reviewing designs, building component systems, checking accessibility, or preparing developer handoffs.

sandbaseai-sandbase-skills Bundle

Extract full transcripts and captions from YouTube videos for content analysis, summarization, note-taking, and repurposing. Supports multiple languages and auto-generated captions. Ideal for research, content creation, and accessibility workflows.

camoneart Skill

Perform comprehensive web page quality audits using Chrome DevTools MCP including responsive layout verification, interactive element testing, console/network error detection, and accessibility checks. Use when user mentions "quality check", "UI check", "page audit", "responsive check", "deploy check", or asks to verify a web page before deployment. Also triggers on Japanese terms like "品質チェック", "UIチェック", "表示確認", "デプロイ前確認", "レスポンシブ確認", "アクセシビリティ確認".

camoneart Bundle

Create distinctive, production-grade frontend interfaces with high design quality that avoid generic AI aesthetics. Adapt to ANY aesthetic direction the user provides. Use when building web components, pages, or applications (websites, landing pages, dashboards, components, HTML/CSS layouts, or when styling/beautifying any web UI). Use when the user mentions UI/UX design, beautiful UI, frontend design, component creation, cool UI, impressive design, or Japanese equivalents like UI/UXデザイン/美しいUI/フロントエンドデザイン/ コンポーネント作成/かっこいいUI/印象的なデザイン.

grtninja Bundle

Enforce explicit desktop startup acceptance across local app repos. Use when normalizing Windows app launchers, stale-window cleanup, frontend/backend coupling, state restore, shortcut ownership, or machine-specific app rosters.

oaustegard Bundle

Removes LLM prose tics from drafts — staged reveals, "it's not X, it's Y", significance tags, abstraction agency, coy headers, fragment cadence, the flatter slop patterns (copula avoidance, participle tails, forced triads, chatbot residue), the flat-certainty patterns the pass itself produces (bare adverbs, juridical vocabulary, verification compounds, privative coinages), and the confiding-essayist patterns (announced honesty, stranded auxiliaries, retroactive significance, totalizing claims, obituary headlines) — and returns plain human technical prose. Use when text needs editing for register, when someone says "de-claude", "de-slop", "humanize this", "this reads like AI", "make this sound human", "remove the tics/claudisms", or asks for a voice/register pass on a post, README, report, PR description or essay. Also use before publishing any draft Claude wrote. Verifies the rewrite kept every claim. Produces either clean prose or an annotated HTML diff showing every edit with its original and reason.

notque Bundle

Verify cross-component wiring and data flow.

notque Bundle

Standalone WebGL fragment shaders for card visual effects: holographic foil, shimmer, rarity glow.

notque Skill

Convert PDF, Office, HTML, data, media, ZIP to Markdown.

notque Bundle

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports. Generic: works for any service or stack.

grtninja Bundle

Enforce AvatarCore workstation desktop-launch acceptance when frontend/backend launcher ownership, stale-window cleanup, and health proof must be explicit. Use when backend-only startup is being mistaken for app readiness or when a combined launcher is being introduced or repaired.

grtninja Bundle

Validate and repair VRM Sandbox startup acceptance with shim-first local model authority, frontend/backend bring-up, and avatar-runtime launch proof. Use when launch behavior, chat handoff, voice fallback, or runtime bridge acceptance must be verified end to end.

notque Bundle

Context-driven aesthetic exploration with anti-cliche validation.