用于拉取并展示最新热点内容(接口为 https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP,返回 JSON 数组)。按模型预估点击率生成 Top 条目(不使用原始热度排序)。默认会提示用户创建定时任务(不自动执行),在用户确认后提供 cron 注册命令。适用于用户查询最新热点、服务状态、按 source_name 分组标题、Top 内容,或由已存在的定时消息触发执行。触发词:"今日热点"、"今日头条"、"热点新闻"、"热点"
Default mode is stateless and read-only.
Do not automatically:
By default, proactively suggest creating a cron job for daily updates. Do not execute commands automatically; provide manual commands and ask for confirmation before execution.
Default prompt template:
建议开启定时推送:每天 09:30 (Asia/Shanghai) 自动拉取热点。要我为你生成并执行 cron 创建命令吗?Optional manual setup example:
openclaw cron add \
--name "hotspots-scheduled-shanghai" \
--cron "30 9 * * *" \
--tz "Asia/Shanghai" \
--session isolated \
--agent default \
--announce \
--channel "当前会话的 channel(自动替换)" \
--to "当前会话的用户 ID(自动替换)" \
--message '定时执行 hotspots skill:请读取 skill「hotspots」并按 Consumer Workflow 执行「latest hotspot」——先生成分钟级 TIME_STEMP,再请求 GET https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP;按 JSON 解析:Top 区块按预估点击率排序(不展示热度和内部排序逻辑),再按 source_name 分组展示标题。'
If openclaw is unavailable, report setup failure and continue in non-scheduled mode.
SKILL.md / 规则包)。若定时环境无本 skill,须在 --message 中内联完整 URL 与 Output Rules 要点。--cron / --tz 时保持 --message 明确为 hotspots consumer 拉取,避免与其它定时报告混淆。When user-approved scheduling is already configured and a scheduled message triggers this skill, or the user explicitly requests hotspots / 最新热点:
⚠️ 每次执行都必须实际调用 API!禁止使用缓存或上次的结果!
第一步:获取当前时间并报告
TIME_STEMP(示例:TIME_STEMP="$(TZ=Asia/Shanghai date +%Y-%m-%dT%H:%M)")📡 [HH:mm] 正在调用 API: GET https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP必须使用 web_fetch 工具 调用上述 URL(extractMode: "text")
第二步:报告调用结果
✅ [HH:mm] API 调用成功,获取到 X 个来源,共 Y 条热点❌ [HH:mm] API 调用失败:[具体错误原因]解析返回的 JSON 数组,按 Consumer Workflow 处理
遵循本文件 Output Rules 与 Reliability Rules
🔍 验证要求: 每次输出的时间戳必须是当前实际时间,如果时间戳与预期不符或重复,说明没有实际调用 API。
This skill is only for Consumer behavior.
Use this skill when users ask to:
/hotspots/latest?timestamp=$TIME_STEMP (primary: JSON)source_nameDo not include Publisher generation logic or Server upload/storage internals in responses.
Base URL:
https://hotspot.api4claw.comOnly endpoint:
GET /hotspots/latest?timestamp=$TIME_STEMP: 使用 web_fetch 工具(extractMode: "text")获取最新热点 JSON 数据。调用前必须先生成分钟级 TIME_STEMP。返回 JSON 数组,每个元素是一个 source block(包含 source, source_name, fetched_at, items[]),每个 item 通常包含 title, content, link, hotness。不要 使用 hotness 展示或排序,仅用模型预估点击率排序 Top。For each user intent:
latest hotspot:
TIME_STEMP(示例:TIME_STEMP="$(TZ=Asia/Shanghai date +%Y-%m-%dT%H:%M)")web_fetch 工具 调用 GET https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP(extractMode: "text")items[]title + content 内部估算 预估点击率(仅用于排序),按估算值降序排列,取前 10 条hotness 字段排序或展示,不要 暴露 hotness 或「热度」字样title + content 写简洁的 AI 摘要(1-2 行,不编造)source_name 分组展示所有 item 的标题status: 先生成分钟级 TIME_STEMP,再 使用 web_fetch 工具 调用 GET https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP,报告可达性 + 基础统计(source 数量、item 总数)。不要 展示 fetched_at 或 data_datesource filter: 按 source/source_name 过滤展示JSON grouping targets (if present):
xwlb / 新闻联播weibo / 微博zhihu / 知乎qqMorningPost / 腾讯早报Required:
Fixed:
HOTSPOT_BASE_URL: https://hotspot.api4claw.com (constant, not configurable).Recommended defaults:
6000 msWhen showing hotspot content, use this order:
items[], estimate CTR per item from title + content, sort by estimate desc, take up to 10.title/content). Do not show hotness, numeric hotness, or the word 热度,or the word 点击率.1. … 10. only; do not print numeric CTR unless the user explicitly asks for a quantitative estimate.source_name.fetched_at or data_date in output.items, keep the source header and mark it as empty.When showing status:
/hotspots/latest?timestamp=$TIME_STEMPfetched_at or data_date/hotspots/latest?timestamp=$TIME_STEMP fails, return explicit failure reason./hotspots/latest?timestamp=$TIME_STEMP.