Workflow Automation

Automate existing Electron desktop apps like VS Code, Slack, Discord, Figma, Notion, and Spotify via agent-browser and Chrome DevTools Protocol (CDP). This skill helps you connect to a running Electron app, take snapshots, and interact with its UI as part of end-to-end desktop and workflow automation.

Automate Slack from the command line using browser automation. The slack skill connects to an existing Slack web session via agent-browser so you can check unread channels, scan DMs, search conversations, extract data, and capture structured reports as part of larger workflows.

agent-browser lets AI agents control a Playwright-powered browser via inference.sh. Open pages, use @e element refs to click, type, drag, upload files, scrape content, and capture screenshots or video. Ideal for web automation, data extraction, and agent-driven browsing workflows.

agent-browser is a Chrome/Chromium automation CLI for AI agents and shell scripts. Use it to open pages, navigate, click, fill forms, capture snapshots, take screenshots, record video, profile performance, manage sessions, handle authentication, and automate end-to-end browser workflows.

agent-tools exposes the inference.sh CLI inside your agent so you can run 150+ AI apps from one place: image generation, video creation, LLMs, search, 3D, and Twitter automation. Ideal when you need a unified workflow runner for FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and more without managing GPUs or complex integrations.

Install ai-automation-workflows to build automated AI workflows with the inference.sh CLI. Learn batch processing, scheduled jobs, event-driven pipelines, and agent-style loops for content generation, data processing, and monitoring at scale.

Generate AI avatar and talking head videos from an image and audio track using the inference.sh CLI. ai-avatar-video wraps OmniHuman, Fabric, and PixVerse Lipsync apps for audio-driven avatars, lipsync videos, and virtual presenters, ideal for marketing, explainers, and social content workflows.

Design and run multi-step AI content pipelines that chain image, video, audio, and text tools together via the inference.sh CLI. Use ai-content-pipeline to automate workflows like: generate an image, animate it to video, add sound or voiceover, and prepare content for YouTube, social media, and marketing campaigns.

Assess and upgrade existing Azure workloads between plans, tiers, and SKUs with a guided, multi-phase workflow. azure-upgrade helps you move from Consumption to Flex Consumption, switch Azure Functions plans, change hosting tiers, and migrate from App Service to Container Apps with assessment reports and automated upgrade steps.

Design and run multiple independent AI agents in parallel, each with its own focused context and task domain.

Use the executing-plans skill to load a written implementation plan, review it critically, and execute bite-sized development tasks with checkpoints and status tracking.

End-to-end guidance to create, deploy, evaluate, observe, and troubleshoot Azure AI Foundry agents and projects, including RBAC, quota, standard/private-network setups, and agent metadata layout.

Orchestrate development work by dispatching fresh, specialized subagents per task with separate spec and code-quality review inside a single session.

Enforce a strict rule that no work is declared done, fixed, or passing until you run the actual verification command, inspect the output, and base your claim on fresh evidence.