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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/baidubce/skills --skill baidu-search命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Manage public and hybrid Famou experiments via famou-ctl: submit config.yaml tasks; inspect status, manifests, leaderboards, logs, and reports; fetch ranked or top results; pause, resume, update, continue, cancel, or delete runs; and check account quota or credits. Use for Famou experiment lifecycle and result-management requests, including short requests such as "submit", "run experiment", or "download the top result".
Interactive end-to-end Famou workflow for defining, implementing, and solving optimization tasks. The workflow typically proceeds in three stages: (1) understand the data and define the task, producing `problem.md`; (2) implement and validate `evaluator.py`, `init.py`, and `prompt.md` from the task definition; (3) run deep solving through Famou. Trigger this skill whenever the user wants to define, clarify, create, or fix a Famou task; prepare Famou experiment artifacts; write or update `problem.md`, `evaluator.py`, `init.py`, or `prompt.md`; run Famou; do deep solving; or solve an optimization, ML, or search problem with evolutionary methods. Even if the user simply says "help me make a Famou task", "help me solve this", or "run Famou", trigger this skill whenever the surrounding context indicates an optimization or search task. Also trigger when the user describes a combinatorial optimization, scheduling, routing, or ML problem without mentioning Famou — treat it as a potential Famou task.
Diagnose a Famou experiment on explicit user request by inspecting its current status, latest leaderboard and result code, score improvement, candidate diversity, evaluator reward hacking, and signs of local convergence. Use when the user asks whether an experiment is healthy, improving, hacked, plateaued, stuck in a local optimum, or needs a diagnostic recommendation. Default to one read-only diagnosis; monitor repeatedly only when the user explicitly requests continuous diagnosis.
基于 SOC 职业分类
正在显示 SKILL.md
| name | baidu-search |
| description | Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics. |
| metadata | {"openclaw":{"emoji":"🔍︎","requires":{"bins":"[Truncated]","env":"[Truncated]"},"primaryEnv":"BAIDU_API_KEY"}} |
Search the web via Baidu AI Search API.
This skill requires a BAIDU_API_KEY to be configured in OpenClaw.
If you don't have an API key yet, please visit: https://console.bce.baidu.com/ai-search/qianfan/ais/console/apiKey
For detailed setup instructions, see: references/apikey-fetch.md
python3 skills/baidu-search/scripts/search.py '<JSON>'
| Param | Type | Required | Default | Description |
|---|---|---|---|---|
| query | str | yes | - | Search query |
| count | int | no | 10 | Number of results to return, range 1-50 |
| freshness | str | no | Null | Time range, two formats: format one is ”YYYY-MM-DDtoYYYY-MM-DD“, and format two includes pd, pw, pm, and py, representing the past 24 hours, past 7 days, past 31 days, and past 365 days respectively |
# Basic search
python3 scripts/search.py '{"query":"人工智能"}'
# Freshness first format "YYYY-MM-DDtoYYYY-MM-DD" example
python3 scripts/search.py '{
"query":"最新新闻",
"freshness":"2025-09-01to2025-09-08"
}'
# Freshness second format pd、pw、pm、py example
python3 scripts/search.py '{
"query":"最新新闻",
"freshness":"pd"
}'
# set count, the number of results to return
python3 scripts/search.py '{
"query":"旅游景点",
"count": 20,
}'
Fully functional.