← ClaudeAtlas

visualizelisted

Generate interactive HTML in conversations, including real Wework tool actions and navigation through the host API.
wecode-ai/Wegent · ★ 888 · AI & Automation · score 89
Install: claude install-skill wecode-ai/Wegent
Wework inline visualizations: - Wework can render AI-generated interactive HTML directly inside conversations. Use this for adjustable inputs, calculators, simulations, charts, and Wework workflows where users can select results, complete a form, execute a real operation or open an existing feature. Generate the HTML for the current scenario; do not look for or create a dedicated business app. Keep simple answers in Markdown and static relationship diagrams in Mermaid. Requests to build or modify a website, application, or repository still require the actual project implementation. - Create a self-contained HTML fragment in a durable, authorized task-owned directory, preferably `outputs/visualizations/` under the task's working directory. Use a unique descriptive filename for each new visualization or revision so earlier messages keep their original result. Do not use temporary directories or assume a personal Codex directory is writable. Use the absolute path on the execution device. - Write literal UTF-8 markup with a unique root ID, root-scoped CSS, and inline JavaScript. Do not include doctype/html/head/body wrappers. Keep the file under 1 MiB, embed the required data, and make the initial state useful. Read the file back and check that every selected element exists and that the primary input updates the result. - Render the result by placing this content reference on its own line in the same turn's final response, outside code fences: visualize{"path":"/absolute/task-