Web & Frontend

adu2021 Skill

Reduce web agent context size by 51% while maintaining task performance using lightweight LLM retrieval to extract relevant accessibility tree lines. Task-guided filtering removes irrelevant elements, improving inference cost and security by neutralizing prompt injection attacks without sacrificing normal operation.

adu2021 Skill

Designs terminal-based AI coding agents through workload-specialized model routing, where distinct models handle planning, thinking, critique, and execution tasks. Implements extended ReAct loop with context compaction and approval gates for safe command execution.

adu2021 Skill

Create principle-guided reward models for web automation agents that evaluate reasoning process quality rather than just outcomes. Implement domain-specific principles (HTML understanding, interaction patterns, state tracking) to guide agent behavior in web navigation and task completion.

adu2021 Skill

Predict GUI state evolution by generating HTML code rather than pixel images. Combines visual fidelity of pixel-based approaches with structural precision of code-based methods through deterministic rendering. Enables agents to evaluate action consequences and select best decisions before execution.

adu2021 Skill

Build a single model handling multimodal understanding, generation, and editing tasks efficiently through token compression and intelligent component sharing. EMMA-4B surpasses larger models while reducing computational burden—ideal when you need unified performance across vision and language tasks.

nota-america 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]".

nota-america Bundle

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

undermybelt Bundle

Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation.

undermybelt Bundle

Browser automation CLI for AI agents. Use for opening pages, snapshots with @e refs, clicking, filling forms, testing web apps, screenshots, PDFs, extraction, console/errors, network logs, auth state, Electron app automation, Slack automation, exploratory QA, and repeatable browser workflows. Chinese triggers include 浏览器自动化, 打开网页, 点按钮, 填表单, 截图, 页面快照, accessibility tree, @e 引用, 测网页, QA, 冒烟测试, 浏览器回归, 抓页面文本, 提取页面数据, Electron 自动化, Slack 自动化.

undermybelt Bundle

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

undermybelt Bundle

Generate A-share individual stock fundamental and industrial-chain research reports from a stock code using the reviewed stock-analysis source tree. Use when the user explicitly asks for A-share stock code analysis, 个股分析, 股票基本面分析, 股票研究报告, A股研报, HTML stock report generation, or A股产业链卡脖子/龙头买入逻辑. Do not use for global non-mainland-A-share leader screens.

undermybelt Skill

AgentHansa changelog/source-of-truth 梳理 — 平台规则、新功能、游戏类型变化的自动发现与记录。SPA 应用的 changelog 不在静态 HTML 中，需通过 API 端点捕获变化。

undermybelt Bundle

Generate dark-themed standalone HTML architecture diagrams with inline SVG, based on the Cocoon-style architecture diagram pattern, but adapted for Hermes. Use when the user wants a clean architecture diagram delivered as a single .html file that opens in any browser.

undermybelt Bundle

Gap-driven arXiv research: identify gaps in project docs, search arXiv API for papers, extract key sections via ar5iv HTML fallback, write structured synthesis md, convert best paper to Python. Trigger when user asks to 'find papers', 'research papers for X', '补强文档', or '搜论文并转成py'.

undermybelt Skill

Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. Use when building any interactive UI component or form.

undermybelt Skill

Operate or review the AI Daily Frontier / github-trending-spider project: a Python + Vue app that aggregates GitHub Trending, Hacker News, TLDR AI, V2EX, Linux.do, OpenAI, Anthropic, and InfoQ AI sources into Chinese AI/frontier summaries, JSON snapshots, a FastAPI read API, optional scheduler, optional SMTP email, and a Vue frontend. Use when the user mentions github-trending-spider, AI Daily Frontier, 每日AI前沿, AI 资讯聚合, GitHub Trending 日报, AI 新闻爬虫, or multi-source AI news digest automation.

undermybelt Skill

Production-ready animation patterns for React / Next.js — button, modal, toast, stagger, page transitions, exit animations, scroll, and layout — built on motion-foundations tokens and springs.

undermybelt Bundle

个股深度分析的核心工作流。当用户要求"深度分析 / 全面分析 / 帮我看看 / 值不值得买 / DCF / 机构建模 / 首次覆盖 / 投委会备忘录"等涉及个股研究的请求时触发。覆盖 A 股、港股、美股，产出 22 维数据 + 52 位大佬量化评审 + 6 种机构级估值建模 (DCF/Comps/LBO/3-Stmt/Merger) + 7 种研究产物 (首次覆盖/财报解读/催化剂日历/投资逻辑追踪/晨报/量化筛选/行业综述) + 6 种决策方法 (IC Memo/DD/Porter/单位经济/VCP/再平衡) + 杀猪盘检测，最终生成 Bloomberg 风格 HTML 报告 + 社交分享战报。关键词：股票、个股、深度分析、估值、DCF、comps、首次覆盖、IC memo、杀猪盘、龙虎榜、akshare。

undermybelt Bundle

Use when producing visual creative artifacts: ASCII art/video, diagrams, comics, article illustrations, pixel art, p5.js/Manim animations, HTML mockups, design systems, ComfyUI media, or style-guided web visuals.

ferroxlabs Bundle

Organizational accessibility culture building expertise covering champion network design, accessibility training curricula, audit cadence and methodology, KPI definition and tracking, executive buy-in strategies, embedding accessibility in development workflows, and sustaining long-term accessibility commitment across teams. Use when the user asks about accessibility champion program, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of accessibility champion program or requires a different specialized skill.

adu2021 Skill

Enable LLM agents to autonomously retrieve information across multiple granularities using keyword search, semantic search, and chunk read tools. Simple ReAct-based loop with hierarchical interfaces outperforms dense retrieval by allowing adaptive information seeking without complex graph construction.

adu2021 Skill

Use component-based markup with CSS-like styling to structure complex prompts, integrate diverse data types, and separate content from formatting for maintainable, version-control-friendly LLM applications.

adu2021 Skill

Use a lightweight LLM to filter accessibility tree observations by task relevance, reducing agent context size by 50-80% while maintaining equivalent task performance.

undermybelt Skill

EMR/EHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry.

undermybelt Skill

Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

undermybelt Skill

Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.

undermybelt Bundle

生成单文件的交互式数据结构/算法可视化 HTML 教学页面。适用场景：用户提供 PDF/教材要求生成知识点讲解、给出主题要求做动画演示（如"演示快排"、"做个队列动画"）、提供代码或算法要求可视化执行过程、要求对比两个概念或解释原理。即使用户没有明确说"HTML"或"可视化"，只要涉及"知识点总结"、"教学页面"、"动画演示"、"算法执行过程"、"PDF 讲解"、"SVG 图示"、"逐步执行"等场景也应触发。

adu2021 Skill

Enable safe and efficient AI agent interactions with websites via declarative HTML extensions—define agent-executable tools and context using <tool> and <context> tags instead of relying on brittle UI inference.

adu2021 Skill

Improve LLM agents operating under strict feasibility constraints (budget limits, tool usage caps) by separating planning from execution. Generate multiple candidate plans, merge into plan graph, then use external solver (ILP) to find optimal feasible path. Constrained decoding forces execution of planned actions, eliminating sampling errors. Adaptive replanning handles observation surprises. Achieves 21+ pp improvements on constrained tasks vs. ReAct.

nota-america Bundle

Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites. Use when the user asks to turn the daily inspiration references, a five-item UI prompt pack, or a dated `*-ui-inspiration-capture` article into distinct HTML landing pages while changing the source brands, names, copy, people, numbers, pricing, claims, and imagery.

nota-america Bundle

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

nota-america Skill

Build or extend a playable isometric action RPG in Three.js, React, or similar web technology. Use for game-loop architecture, camera and movement, zones, combat integration, content data, progression, saves, or production-ready vertical slices.

nota-america Bundle

Suite of tools for creating elaborate, multi-component claude.ai 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.

nota-america Skill

Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.

nota-america Skill

Design or implement responsive audio feedback for a Three.js or web game. Use for action sounds, combat layers, music states, spatial audio, mix priorities, mute controls, accessibility, mobile audio unlock, and audio performance.

nota-america Skill

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.