xlang-ai

How to programmatically create, modify, and verify Blender 3D scenes using Python bpy (headless background mode, .blend files, render output). For setup-gen and reward-gen agents.

How to programmatically set up, control, and verify Google Chrome browser state using Python (Playwright CDP, SQLite, JSON configs). For setup-gen and reward-gen agents.

How to programmatically set up, manipulate, and verify draw.io diagram state using Python (Playwright CDP, XML injection via Edit Diagram menu, DOM verification). For setup-gen and reward-gen agents.

How to programmatically set up, manipulate, and verify Excalidraw whiteboard state using Python (Playwright CDP, localStorage JSON, scene elements). For setup-gen and reward-gen agents.

How to programmatically create, modify, and verify images using Python Pillow, NumPy, OpenCV, and scikit-image. For setup-gen and reward-gen agents.

How to set up and manipulate Grafana dashboard, alerting, and admin state via HTTP APIs for CUA-Gym tasks. For setup-gen and reward-gen agents.

How to programmatically create, modify, and verify LibreOffice Calc (.xlsx) files using Python openpyxl. For setup-gen and reward-gen agents.

How to programmatically create, modify, and verify LibreOffice Impress (.pptx) files using Python python-pptx. For setup-gen and reward-gen agents.

Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding, AWS provider setup, Docker provider setup, mocked website server setup, GitLab server setup, gated task download, or a final runnable export block. The skill should install/configure the selected supported infrastructure where possible, ask for user confirmation or credentials when required, and report what is fully configured versus still blocked.

Provision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding, AWS provider setup, Docker provider setup, mocked website server setup, GitLab server setup, gated task download, or a final runnable export block. The skill should install/configure the selected supported infrastructure where possible, ask for user confirmation or credentials when required, and report what is fully configured versus still blocked.

Migrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the integration.

Check OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and agent-visible files, inspect setup artifacts when needed, and produce both markdown and structured JSON reports.

Analyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants to understand agent performance on OSWorld tasks — including analyzing trajectories, reviewing task results, finding error patterns, comparing code vs GUI strategies, identifying which tools/commands the agent used, or deciding which task types to scale up in the benchmark.

Search and download UI screenshots from the web using image search. Use when you need reference screenshots of real websites/apps (e.g., Gmail, Slack, Notion) for building mock applications. Downloads high-resolution images to a local directory.