similarweb
Skill9 starsChanged 8 months agoMITView on GitHub
SimilarWeb 网站分析连接器 — 流量、排名、营销渠道、受众画像等数据
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- chart-creationSkill
- code-rulesSkill
- conditional-formattingSkill
- data-analysisSkill
- data-cleaningSkill
- equity-valuationSkill
- financial-modelingSkill
- formula-operationsSkill
- local-accessSkill
- sandbox-executorSkill
- template-generationSkill
- wps-core-apiSkill
- connector-managerSkill
- financial-dataSkill
- knowledge-baseSkill
- sensortowerSkill
- web-searchSkill
- equity-valuation-frameworkSkill
- agent-modeSkill
- ask-modeSkill
- plan-modeSkill
- memory-managerSkill
- onboardingSkill
- soul-engineSkill
- monthly-reportSkill
The file
Files
SimilarWeb 网站分析连接器
通过 dataBridgePull() 获取网站流量、排名、营销渠道等分析数据。
获取网站流量与互动
var resp = dataBridgePull("similarweb", "traffic_engagement", {
domain: "google.com",
start_date: "2025-01",
end_date: "2025-12",
granularity: "monthly",
country: "world"
});
if (!resp || !resp.ok) return "获取数据失败: " + (resp ? resp.error : "网络错误");
// resp.data.data 是月度数组,每个元素包含:
// date, visits, bounce_rate, average_visit_duration, pages_per_visit, unique_visitors
var rows = resp.data.data; // Array: [{date:"2025-01-01", visits:723462947, ...}, ...]
for (var i = 0; i < rows.length; i++) {
var r = rows[i];
// r.date (日期), r.visits (访问量), r.bounce_rate (跳出率 0-1),
// r.average_visit_duration (秒), r.pages_per_visit, r.unique_visitors
}获取网站排名
var resp = dataBridgePull("similarweb", "website_ranking", {
domain: "google.com"
});
if (!resp || !resp.ok) return "获取失败: " + (resp ? resp.error : "网络错误");
// resp.data.data 是数组: [{date, rank_global, rank_country, rank_category, ...}]
var rank = resp.data.data[0]; // rank.rank_global, rank.rank_country获取流量来源
var resp = dataBridgePull("similarweb", "traffic_sources", {
domain: "google.com",
start_date: "2025-01",
end_date: "2025-12",
country: "world"
});
// 各渠道(直接/搜索/社交/引荐/邮件/展示广告)的流量占比获取流量地域分布
var resp = dataBridgePull("similarweb", "traffic_geography", {
domain: "google.com",
start_date: "2025-01",
end_date: "2025-12"
});
// 按国家的流量占比获取应用详情
var resp = dataBridgePull("similarweb", "app_details", {
app_id: "com.google.android.gm",
store: "google"
});可用 Actions
| Action | 说明 | 必需参数 |
traffic_engagement | 流量与互动 | domain, start_date, end_date |
website_ranking | 网站排名 | domain |
traffic_sources | 流量来源 | domain, start_date, end_date |
traffic_geography | 流量地域分布 | domain, start_date, end_date |
app_details | 应用详情 | app_id, store |
参数说明
| 参数 | 说明 | 示例 |
| domain | 网站域名(不含 www) | "google.com", "baidu.com" |
| start_date | 开始月份 | "2024-01" |
| end_date | 结束月份 | "2024-12" |
| granularity | 时间粒度 | "daily" / "weekly" / "monthly" |
| country | 国家/地区 | "world", "us", "cn", "gb" |
| store | 应用商店 | "google" / "apple" |
重要规则
- 日期格式 YYYY-MM:SimilarWeb 使用月份粒度的日期(非 YYYY-MM-DD)
- 日期范围限制:数据通常只覆盖最近 24 个月(约 2024-02 到 2026-02)。推荐使用
start_date: "2025-01",end_date: "2025-12"或"2026-01"等近期日期。不要用超出范围的日期。 - 国家小写:使用小写国家代码(
"us"而非"US"),或"world"表示全球 - 域名不含协议:传入
"google.com"而非"https://www.google.com" - 检查
resp.ok:必须检查返回状态 - API 限流:每秒最多 10 次请求,系统已内置缓存(1 小时 TTL)
- ⚠️ 单次代码块最多查询 3 个域名:每个 API 调用是同步阻塞的(5-15 秒/次),超过 3 个域名会导致执行超时。多域名研究应分批执行(第一批 3 个 → 写入表格 → 第二批 3 个)。
- 仅使用
traffic_engagement和website_rankingaction:traffic_sources和traffic_geography在当前 API 计划下不可用(返回 404)。不要使用它们。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

