sn-code-video
Create and revise code-driven videos with Canvas, SVG, HTML/CSS, Three.js, Remotion, Manim, or p5.js, including sound,…
USE FOR Google-backed image discovery via Serper.dev. Returns image URLs, page URLs, titles, and source domains.
Claude Code
$ npx -y skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image --agent claude-code
Codex
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a codex -y
Cursor
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a cursor -y
Gemini CLI
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a gemini-cli -y
GitHub Copilot
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a github-copilot -y
OpenCode
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a opencode -y
Windsurf
$ npx skills add OpenSenseNova/SenseNova-Skills --skill sn-search-image -a windsurf -y
name: sn-search-image
description: USE FOR Google-backed image discovery via Serper.dev. Returns image URLs, page URLs, titles, and source domains.
metadata: {"openclaw":{"requires":{"bins":["python3"],"env":["SERPER_API_KEY"]},"primaryEnv":"SERPER_API_KEY"}}Use this skill to search for candidate images via Serper.dev.
Standard image search:
python3 {baseDir}/scripts/serper_image_search.py "QUERY" --num 10Image URLs only:
python3 {baseDir}/scripts/serper_image_search.py "QUERY" --num 10 --image-urls-only --limit 5Page URLs only:
python3 {baseDir}/scripts/serper_image_search.py "QUERY" --num 10 --page-urls-only --limit 5Raw JSON:
python3 {baseDir}/scripts/serper_image_search.py "QUERY" --num 10 --jsonSave raw JSON to a file for later inspection:
python3 {baseDir}/scripts/serper_image_search.py "QUERY" --num 10 --save-json /tmp/serper-images.jsonThe SenseNova model family plugs directly into agent runtimes such as OpenClaw and hermes-agent, with the skills in this repository extending the models with concrete, end-to-end office capabilities.
Create and revise code-driven videos with Canvas, SVG, HTML/CSS, Three.js, Remotion, Manim, or p5.js, including sound,…
Excel 数据分析多步编排器。覆盖:(1) 读取多 Sheet Excel 文件并统计行数,(2) 大文件检测(≥10k 行自动 Parquet 优化),(3) 数据清洗(缺失值、文本标准化、无效字符),(4) 条件筛选与分类提取,(5) 跨 Sheet…
当Excel文件总行数超过1万行时,通过转换为Parquet格式提升读取性能,提取目标指标并计算最大值,最后将结果输出为Excel并对特定行进行高亮标注。
根据Excel总行数自动切换Parquet加速读取,计算特定维度的时间序列平均值,并使用openpyxl输出带有条件格式(如低于均值标绿)和自定义样式的分析报告。
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…