一键导入
web-scraping
Extract and summarize content from the currently opened web view with robust fallback.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Extract and summarize content from the currently opened web view with robust fallback.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Label video behavior segments from frame-grid images with a defined behavior list, model-ready JSON, resumable outputs, and no_behavior handling for sparse labels.
Use Annolid GUI tools for robust automation across web, PDF, video, and chat controls.
Infer the assay or paradigm from video context, task text, tracked entities, and experimental cues such as social interaction, open field, courtship, resident-intruder, and novel object recognition.
Choose assay-specific features and measurable objectives for behavior analysis, including distances, zones, speed, contact, orientation, and object interaction.
Segment behavior timelines from tracks, pose, contact, speed, and proximity signals into typed intervals with stable labels and rationales.
Keep behavior analysis aligned with assay objectives, controls, reproducibility, and measurable outputs instead of ad hoc summaries.
| name | web-scraping |
| description | Extract and summarize content from the currently opened web view with robust fallback. |
| metadata | {"annolid":{"always":true}} |
Use this skill when the user asks about the currently opened web page, says "this page/current page", or asks for web extraction/summarization.
Primary goal: return grounded page content quickly, with source links and minimal hallucination.
gui_web_get_state().gui_web_run_steps or web_search) and then continue.gui_web_get_dom_text(max_chars=9000) first.gui_web_extract_structured(fields=[...]) for schema-shaped answers.selector_hints (CSS-like or keyword hints) and set extraction_mode="hint" for resilient line-level extraction.gui_web_run_steps with get_text after a short wait and optional scroll.gui_web_capture_screenshot(max_width=1600) and then gui_web_describe_view(max_width=1600).web_search(query, count) (Scrapling-first backend).web_fetch(url, extractMode="text") when a target URL is known.