Vision-based browser automation CLI — LLM sees screenshot, clicks coordinates, repeats. No selectors. Supports Claude, Gemini, OpenAI, Ollama (local/free).
npx skills add rajpra808/browser-agentVision-based browser automation CLI — LLM sees screenshot, clicks coordinates, repeats. No selectors. Supports Claude, Gemini, OpenAI, Ollama (local/free).
Source: https://github.com/rajpra808/browser-agent
Discovered during the daily awesomeskills.dev agent-skill hunt.
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.
Automate a personal Markdown knowledge base with Spring AI agents that curate, link, and maintain your notes using a schema-driven workflow.
Software-engineering principles in Anthropic SKILL.md format. Loadable by Claude / Claude Code at the moment they apply, so the AI co-author has the same hard-won principles in working context as the human.
Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai
Claude Code sessions are stateless. Continuum fixes that. 7 skills + 5 zero-cost hooks for crash recovery, session resume, and cognitive checkpoints.
Copilot customization files (agents, skills, instructions) distributed via reusable GitHub Actions workflow