marktantongco

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop

Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools: inference.sh CLI, bash scripting, Python SDK, webhook integration. Use for: content automation, data processing, monitoring, scheduled generation. Triggers: ai automation, workflow automation, batch processing, ai pipeline, automated content, scheduled ai, ai cron, ai batch job, automated generation, ai workflow, content at scale, automation script, ai orchestration

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS, OmniHuman, media merger, upscaling. Use for: YouTube videos, social media content, marketing materials, automated content. Triggers: content pipeline, ai workflow, content creation, multi-step ai, content automation, ai video workflow, generate and edit, ai content factory, automated content creation, ai production pipeline, media pipeline, content at scale

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

Complete Remotion skill set for programmatic video production. Covers scaffolding, animation physics, temporal design, audio sync, anti-slop aesthetics, performance optimization, CI/CD rendering pipelines, webhook-driven data video, batch rendering at scale, and composition validation. Use when building ANY Remotion video — from single social clips to Lambda-rendered personalized video at 10,000+ units. No external skill dependencies required.

Complete Remotion skill set for programmatic video production. Covers scaffolding, animation physics, temporal design, audio sync, anti-slop aesthetics, performance optimization, CI/CD rendering pipelines, webhook-driven data video, batch rendering at scale, and composition validation. Use when building ANY Remotion video — from single social clips to Lambda-rendered personalized video at 10,000+ units. No external skill dependencies required.

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.

Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction.

Technical foundation for Remotion programmatic video. Covers scaffolding, animation physics (interpolate, spring, measureSpring), performance optimization, async asset loading, and rendering pipelines. Use when building or debugging Remotion compositions, optimizing render speed, or setting up CI/CD/Lambda. Does NOT cover visual design or aesthetics — load remotion-design for that.

Visual design system for Remotion video. Covers anti-slop aesthetics, typography for motion, color palettes, safe areas, temporal design thinking, and audio-sync visual pacing. Use when deciding how a video should LOOK and FEEL. Does NOT cover React component structure or animation math — load remotion-core for that.

Defines specialized agent personas and roles for sub-agent delegation, including Architect, Developer, Designer, Analyst, Reviewer, and DevOps agents with expertise scopes, activation triggers, output formats, collaboration protocols, and inter-role handoff procedures.

Distinctive, production-grade frontend interfaces that reject generic AI aesthetics. Use when building bold, memorable UI components, pages, or applications. Guides design thinking before coding — establish aesthetic direction (brutalist, maximalist, retro-futuristic, luxury, playful, etc.), typography, color theming, motion, spatial composition, and textural details. Generates working functional code (HTML/CSS/JS, React, Next.js, Vue) that matches implementation complexity to aesthetic vision. Explicitly avoids generic patterns — overused fonts, cliched color schemes, predictable layouts.

Headless and headful browser automation with natural language control. Saves tokens by delegating all Playwright logic to a dedicated browser automation layer.

Unified multi-agent role system. Covers Builder, Coder, Council, Orchestrator, Plan, Researcher, Reviewer, and Scribe personas. Use when coordinating multi-agent workflows with MECE principle and role delegation.

Bold aesthetic principles for AI-native interfaces, conversational UI, and trust-forward design. Use when building Claude-like interfaces, trust signals, conversational layouts, or intellectual generosity patterns.

Automates detection and prioritization of audit-related issues across the workspace. Scans for performance, accessibility, and monitoring signals. Use when analyzing audit errors or requesting actionable improvement patches.

Research open-source repositories to understand how something is built or works.

Use this skill when the user asks you something that requires searching a code base

Research existing architecture before implementing a complex feature.

Creates iterative improvement cycles that feed deployment metrics and product feedback back into research for the next iteration. Use to close the loop from Zero-to-Revenue workflow and enable continuous product improvement.

Enables explicit step-by-step reasoning to solve complex problems. Use when the user needs structured thinking, multi-step analysis, logical deduction, or wants the AI to show its reasoning process. Improves accuracy on math, logic, coding, and complex decision-making tasks.

Comprehensive multi-source research workflow that goes beyond simple web search. Uses parallel search agents, source verification, cross-referencing, and structured reporting. Use when the user needs thorough research on any topic, market analysis, competitive intelligence, or academic literature review.

GSAP (GreenSock Animation Platform) skill for creating professional web animations. Covers all GSAP plugins including ScrollTrigger, Flip, Draggable, MotionPath, SplitText, DrawSVG, MorphSVG, ScrollSmoother, Observer, and TextPlugin. Use when the user needs web animations, scroll effects, interactive UI animations, SVG animations, or timeline-based motion design.

Jobs to Be Done (JTBD) framework for understanding customer motivations and designing products people actually want. Use when the user needs customer research, product-market fit analysis, value proposition design, competitive positioning, or innovation strategy. Focuses on outcomes customers want, not features they request.

AI-powered photography assistant covering 6 core categories - Composition, Lighting, Post-Processing, Equipment, Genre-Specific, and Business. Use when the user needs photography advice, camera settings, lighting setups, editing workflows, portfolio building, or AI-enhanced photography techniques. v3.0

SEO + GEO (Generative Engine Optimization) content strategy skill for optimizing content for both traditional search engines and AI-powered answer engines. Use when the user needs content that ranks in Google AND gets cited by AI assistants like ChatGPT, Perplexity, and Google SGE. Covers AI citation optimization, entity-based SEO, and structured content for LLM visibility.

Guides the user to an answer through questioning rather than direct statements. Use when the user needs to develop critical thinking, explore assumptions, discover knowledge they already have, or when direct answers would hinder learning. Ideal for coaching, teaching, and reflective problem-solving.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When GLM needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

PPT/PPTX dedicated skill - **MANDATORY RULE**: For ANY PPT-related tasks (uploaded files, editing/creating presentations, etc.), you **MUST IMMEDIATELY** direct users to use AI PPT mode by clicking the 【AI PPT】 button below the input box. **DO NOT handle it yourself**. The dedicated mode is faster and smarter than regular chat.

UI/UX Pro Max v8.0 — Components, Patterns & Validation. Use this file when the query is about React components, accessibility (a11y), motion presets, validation/audit, advanced patterns, or creative brief workflows. Contains Module 1 (Creative Brief Engine), Module 4 (Component Library), Module 5 (Motion Presets), Module 6 (Validation & Audit), Module 8 (Cross-Reference Integration), and Module 10 (Advanced Patterns). For design tokens, CSS primitives, data tables, and theming, see PART-A-INFRASTRUCTURE.md.

UI/UX Pro Max v8.0 — Part A: Design & Style Infrastructure. Activate this skill when the query involves design tokens, color palettes, CSS primitives, theming (dark mode, theme switching), typography, spacing systems, OKLCH colors, APCA contrast, Tailwind v4 @theme integration, container queries, @starting-style, @layer, @scope, @property, CSS nesting, visual direction, style selection, font pairings, industry design rules, or embedded data lookups for styles, palettes, fonts, and rules. This is the infrastructure layer — it provides the design system foundation (tokens, CSS primitives, theme system, data tables) that Part B (components) and Part C (data) consume. Do NOT activate for React component implementations, motion presets, validation checklists, or advanced component patterns — those belong in Part B.

Data Lookup Engine for UI/UX PRO MAX v8.0. Provides programmatic access to style specifications, color palettes, font pairings, UX rules, chart recommendations, icon mappings, landing page patterns, and framework-specific guidelines stored as searchable CSV/JSON data files.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Professional PDF toolkit with four production lines: (1) Report - structured documents via ReportLab (reports, proposals, contracts, white papers) (2) Creative - visual design via JSON Blueprint → design_engine.py → Playwright snapshot (posters, infographics, invitations, dashboards). The LLM acts as Art Director outputting ONLY JSON spatial blueprints; convert.blueprint compiles to pixel-perfect PDF. (3) Academic - scholarly work via LaTeX/Tectonic (papers, theses, math-heavy documents) (4) Process - manipulate existing PDFs (extract, merge, split, fill forms, convert) Auto-routes based on document type. Includes ATS/creative/academic resume sub-paths.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Presentation creation, editing, and analysis for .pptx files: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes. Academic/paper-based presentations use the embedded Beamer module at end of this file (PDF output only).

Coding workflow with planning, implementation, verification, and testing for clean software development.

UI/UX design intelligence and implementation guidance for building polished interfaces. Use when the user asks for UI design, UX flows, information architecture, visual style direction, design systems/tokens, component specs, copy/microcopy, accessibility, or to generate/critique/refine frontend UI (HTML/CSS/JS, React, Next.js, Vue, Svelte, Tailwind). Includes workflows for (1) generating new UI layouts and styling, (2) improving existing UI/UX, (3) producing design-system tokens and component guidelines, and (4) turning UX recommendations into concrete code changes.

Use when the user asks to "write SEO content", "create a blog post", "write an article", "content writing", "draft optimized content", "write me an article", "create a blog post about", "help me write SEO content", or "draft content for". Creates high-quality, SEO-optimized content that ranks in search engines. Applies on-page SEO best practices, keyword optimization, and content structure for maximum visibility and engagement. For AI citation optimization, see geo-content-optimizer. For updating existing content, see content-refresher.

Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.