onestopnews

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Build, port, or remediate an avant-garde, anti-generic personal portfolio using Next.js 16 App Router with a Tactile Brutalism + High-End Editorial design system. Covers the complete architectural lifecycle from Vite SPA migration through four remediation phases to production: CSS-first design tokens with dual-theme (Night/Day), client-side SPA orchestrator embedded in Next.js, hash-based routing with keyboard focus management, lazy-loaded sections with ErrorBoundary + Suspense, optional database with graceful null handling, WCAG AAA accessibility (discriminated union API responses, ARIA, reduced motion, skip links, focus management), strict TypeScript with noUncheckedIndexedAccess, rate-limited API routes, security headers, OG/Twitter metadata + JSON-LD, centralized site configuration, dead code archival strategy, and a complete iterative remediation workflow. Use this skill whenever building or porting a portfolio, personal site, creative showcase, or any web project that demands distinctive brutalist/edito

Comprehensive skill document for a Next.js 16 brutalist portfolio. Covers the complete architecture, design system, 16 active components, 8+ remediation phases, 52 lessons learnt, and every coding pattern/anti-pattern discovered. Any coding agent should be able to reconstruct this exact codebase from this document alone.

Professional chart and diagram creation skill. Covers all types of visual data representation and structural diagrams: - **Data charts**: bar charts, line charts, pie charts, scatter plots, heatmaps, radar charts, candlestick charts, boxplots, histograms, area charts, waterfall charts, regression plots, distribution plots, and statistical visualizations. - **Structural diagrams**: flowcharts, mind maps, tree diagrams, org charts, architecture diagrams, network/relationship graphs, ER diagrams, class diagrams, Gantt charts, swimlane diagrams, and sequence diagrams. - **Dashboards**: data dashboards, KPI panels, multi-chart compositions, and interactive visualizations. - **Design quality**: professional color systems, anti-overlap rules, layout optimization, scene-based framework routing (matplotlib, seaborn, ECharts, D3.js, Mermaid, Playwright+CSS), and publication-ready output.

Content extraction and analysis — wisdom extraction from videos, podcasts, articles, and YouTube. USE WHEN extract wisdom, content analysis, analyze content, insight report, analyze video, analyze podcast, extract insights, key takeaways, what did I miss, extract from YouTube.

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

Comprehensive DOCX Generation & Conversion Skill

Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.

Design and scaffold an agent "loop" — an unattended, scheduled, self-verifying agent workflow. Use this whenever the user wants to automate a recurring task, schedule an agent, run an agent unattended or overnight, set up monitoring, triage, or alerting, poll something on a cadence, or turn a manual repeated workflow into a self-running one — even if they never say the word "loop." If a request implies "do this every day / on a schedule / until some condition holds, without me typing each time," reach for this skill. It walks the seven-question blueprint, picks the simplest loop pattern, and scaffolds the six building blocks (schedule, isolation, skill, connectors, verifier, state) with a human-gate list and a budget.

Comprehensive Architectural & Execution Framework for Cinematic, Production-Grade, Anti-Generic Web Platforms

LuxeVerse Architect Skill Comprehensive Architectural & Execution Framework for Cinematic, Production-Grade, Anti-Generic Web Platforms

Professional PDF toolkit with four production lines: Report - structured documents via ReportLab (reports, proposals, contracts, white papers) Creative - visual design via JSON Blueprint → design_engine.py → Playwright snapshot (posters, infographics, invitations, dashboards). Academic - scholarly work via LaTeX/Tectonic (papers, theses, math-heavy documents) Process - manipulate existing PDFs (extract, merge, split, fill forms, convert) Auto-routes based on document type. Includes ATS/creative/academic resume sub-paths.

guide for customizing the Pi Agent system prompt to add custom tools and workflow instructions

Comprehensive stock market analysis skill covering A-share (China), Hong Kong, and US equities. Priority use cases: stock analysis and buy/sell/hold recommendations by ticker code, generating decision dashboards and research reports with technical/fundamental/sentiment analysis, position-aware investment strategies based on user's cost price, dividend income scoring and safety analysis, rumor and early market signal scanning (M&A, insider activity, analyst actions), watchlist management with price target and stop-loss alerts, and K-line chart pattern recognition from images. This skill should be the primary choice whenever users mention a stock ticker, ask whether to buy or sell a stock, reference their holding cost or position, request dividend analysis, ask about market rumors or early signals, want to add/check/manage a watchlist, or upload a chart image for technical analysis.

Standalone CLI wrapper exposing Claude Code's core file operations (read, glob, grep, edit, write) as command-line utilities. Use for scripting and automation without requiring a full Claude session.

独立通用 Skill：管理前端项目全生命周期。只要任务**可能**写出 .html/.jsx/.tsx/.vue 入口文件，就必须在写出第一个文件**之前**读取并遵循本 Skill（用于确定落盘路径与项目目录），而不是产出之后才补救；即使用户没有提到"项目"或"版本"也要使用。同时响应用户的版本相关操作（查看历史、恢复版本、切换项目等）。

Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

Creates or updates a compact, high-signal AGENTS.md instruction file for a repository, helping future AI coding agents avoid mistakes and onboard faster.

Elite web design skill for producing distinctive, production-grade frontend interfaces. Use when: (1) Building new web UI from scratch, (2) Creating luxury/premium brand experiences, (3) Designing landing pages, marketing sites, or product showcases, (4) Reviewing UI designs for Anti-Generic compliance, (5) Establishing design direction for a project, (6) Migrating from Tailwind v3 to v4, (7) Debugging mobile navigation issues, (8) User asks for "avant-garde", "distinctive", "non-generic", "luxury", or "premium" design. Triggers on phrases like "create a beautiful website", "design a landing page", "build a luxury UI", "make it distinctive", "avoid generic design", "mobile nav not working", "tailwind v4 migration".

Fast browser automation CLI for AI agents using Chrome/Chromium via CDP. Use when automating web interactions, taking snapshots, filling forms, navigating pages, or testing web applications without Playwright/Puppeteer dependency.

Google-official MCP server providing full Chrome DevTools Protocol access (29 tools). Use for Lighthouse audits, performance traces, network inspection, console log access, JavaScript evaluation, mobile emulation, and memory snapshots.

Produce thoughtful, high-fidelity design artifacts in HTML — landing pages, slide decks, interactive prototypes, animated videos, posters, wireframes, and visual explorations. Use for tasks like "design a landing page," "make a deck," "prototype this flow," "visualize this idea," or "create a poster." Enforces fact verification (WebSearch before assuming product details), Core Asset Protocol for branded work (logo/product shots/UI screenshots are first-class), Design Direction Advisor offering 3 directions when briefs are vague, and avoids AI-design tropes (aggressive gradients, emoji bullets, rounded-card-with-left-border).

Generate proper CLAUDE.md files for any codebase. Analyzes codebase structure, detects frameworks and languages, and produces a comprehensive CLAUDE.md following the Meticulous Approach framework.

Add new local services to an existing Cloudflare Tunnel for secure public access. Use when you need to expose a local development server, web application, or service running on localhost to the public internet via Cloudflare's tunnel infrastructure. Prerequisites: cloudflared installed and authenticated, existing tunnel created. Triggers: "add tunnel", "expose local service", "cloudflare tunnel", "port forward", "public access to localhost", "expose localhost".

The absolute constitution for code quality and design rigor. Enforces a Six-Axis review (Correctness, Readability, Architecture, Security, Performance, and Aesthetic/UX Rigor). Use before merging any change, evaluating AI-generated code, or assessing technical debt. Rejects generic 'AI slop' aesthetics and enforces intentional, bespoke design.

Unified code review and security audit orchestration skill. Coordinates static analysis, security scanning, code quality checks, test coverage, performance profiling, and expert review into a single tiered pipeline. Use when reviewing code, preparing for release, conducting security audits, or running pre-merge gates. Triggers on: review, audit, code review, security scan, quality gate, pre-merge, checklist, lint, vulnerability.

Lightweight quick-reference checklist for code review. Tactical 12-category scan used by the Orchestrator's Phase 3. For the comprehensive quality constitution (Six-Axis review), see `code-quality-standards`. For verification gates and the Iron Law, see `verification-and-review-protocol`.

Recover from context compaction by scanning memory files and surfacing where you left off. Use when waking up fresh, after compaction, or when you feel lost about what you were doing. Now supports both flat (YYYY-MM-DD.md) and QMD hierarchical (daily/YYYY/MM/DD.md) memory structures.

Search and retrieve up-to-date curated documentation from Context7 for any software, library, or package. Use when: (1) Need latest documentation for a specific library or tool, (2) Looking for code examples and patterns, (3) Need accurate API reference information, (4) Building workflows with specific tools like n8n, (5) Want to avoid hallucinated or outdated documentation. Triggers on phrases like "search Context7 for", "get documentation for", "find latest docs", "n8n workflow", "package documentation".

Programmatic document lookup via Context7 API and MCP server. Use when: (1) Need structured documentation for any library/package/framework, (2) Want code examples without browser automation, (3) Building with specific tools and need accurate API references, (4) Avoiding hallucinated or outdated docs. Priority: API (fastest) → MCP Server → Browser (fallback) Triggers: "lookup docs for", "get Context7 docs", "find documentation", "API reference for", "code examples for [library]"

Condensed experience from 15-phase E2E testing initiative covering authentication, API contracts, tool selection, and hybrid testing methodology. Use when planning E2E tests, selecting testing tools, or debugging test failures.

Deep reference library for framework-specific CLAUDE.md sections. Contains production-ready templates for Next.js, Laravel, Rails, Django, React Native, Flutter, Go, Rust, and more. Use alongside the claude-md skill for complete CLAUDE.md generation.

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

Complete frontend UI testing, verification, troubleshooting, and resolution journey. Covers testing methodology, browser automation with four tools (OpenClaw browser, agent-browser CLI, chrome-devtools-mcp, @playwright/mcp), common patterns, troubleshooting guides, and lessons learned from real-world testing.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers on keywords: lint, format, check, validate, types, static analysis.

Bootstrap, audit, and recover the OpenClaw 3-layer memory architecture (workspace files, LCM database, QMD semantic index). Use when: (1) Setting up memory on a new OpenClaw instance, (2) Auditing existing memory health, (3) Recovering from corruption or system crash, (4) Migrating or restructuring memory layout, (5) User asks about memory architecture setup or health. Triggers on phrases like 'bootstrap memory', 'audit memory', 'memory architecture', 'memory setup', 'LCM configuration', 'QMD setup', 'memory recovery', 'check memory health'.

OpenClaw memory system architecture, setup guide, and troubleshooting reference. Use when configuring memory on a new machine, diagnosing memory issues after updates, or understanding how workspace files, LCM, and QMD work together.

Build and automate n8n workflows using JSON specification. Use when: (1) Creating n8n workflows programmatically, (2) Converting workflows to/from JSON, (3) Understanding n8n node types and connections, (4) Writing n8n expressions, (5) Debugging workflow JSON structure, (6) Building workflow templates. Triggers on phrases like "n8n workflow", "n8n JSON", "n8n expression", "webhook workflow", "n8n automation".

Comprehensive skill for building luxury-grade Next.js applications with Tailwind CSS v4, Radix UI (shadcn), and Framer Motion. Covers CSS-first theming, avant-garde UI design, code review, security audits, performance optimisation, and advanced debugging for high‑end web experiences.