社交媒体互动数据分析

SKILL研究检索
研究检索 未标注权限 许可证不明确
安装这个技能

从内容URL获取公共社交媒体帖子或视频互动快照,包括播放、点赞、评论、收藏、分享、作者、标题、标签、时长和可用时戳字段。用于内容表现总结、帖子对比、活动报告和互动研究,同时保留原始平台指标并保存本地JSON结果。

一句话选型结论

按资料字段整理

社交媒体互动数据分析是研究检索类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类研究检索 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_fabd0a58/unityclaw-media-data-engagement
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

研究检索
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_fabd0a58仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验2026-11-06上游最后核验时间 · 数据更新 2026-11-06
正文体量6.2 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
查资料并整理出处

让模型按主题查资料,并把引用来源整理成清单。

网页与文献要点提炼

把长文、论文、网页压成能直接看的要点。

竞品与行业汇总

按关键词汇总竞品动态与行业信息。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在研究检索场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
社交媒体互动数据分析当前 未标注权限 未标注 未标注 未标注 有
寻找技能 浏览器控制 GitHub 仓库 3120.0 万 Codex、Claude、Cursor 有
自我改进 Agent 接触敏感数据 ClawHub 市场 1646.4 万 OpenClaw 有
灵魂追踪 联网访问 GitHub 仓库 758.9 万 Codex、Claude、Cursor 有
自我完善 联网访问 ClawHub 市场 682.9 万 OpenClaw 有
微软代工厂 调用外部服务 GitHub 仓库 661.4 万 Codex、Claude、Cursor 有

SKILL.md 全文

6.2 KB
模型实际读到的说明书原文,来自技能仓库

UnityClaw Media Engagement Snapshot

Retrieve a structured snapshot for one public social-media post or video. Preserve platform values, localize labels, flag incomplete results, and save engagement.json in the task folder.

Agent Workflow

1. Confirm the content URL

Accept one public post or video URL per invocation. Do not pass a creator homepage, search page, private network address, or URL containing credentials. Use the content-specific form for the platform, such as a Xiaohongshu /explore/ link or TikTok /@user/video/ link. A Douyin user URL is accepted only when it contains a numeric vid query parameter; the CLI converts it to the canonical /video/{vid} request URL while preserving the original source URL.

Use this skill only for public content metrics. Do not bypass authentication, access private content, or infer sensitive traits about viewers or creators.

2. Execute the snapshot

Run scripts/generate.js with --json and an explicit --output-dir. Quote the URL and select --lang from the user's conversation language.

Fetch each content URL once. Allow the CLI to perform transient retries, but do not launch duplicate concurrent requests. For comparisons, capture every URL separately and retain its source URL and update fields.

3. Preserve metric meaning

Use data as the raw platform snapshot. Do not silently convert abbreviated values, round counts, replace missing fields with zero, or merge different metrics. Use localized fields only for presentation; every field retains its raw key.

Metrics are time-dependent and platform-specific. A play, view, collect, share, or like may be defined differently across platforms. Do not present cross-platform counts as directly equivalent without explaining this limitation.

4. Calculate ratios carefully

Do not label a number “engagement rate” without naming the formula and denominator. When the user requests analysis, calculate only from available raw fields and show the formula, for example:

visible interaction rate by plays = (likes + comments + collects + shares) / plays

This is a derived ratio, not a platform-certified metric. Do not calculate it when play_count is missing or zero. Never infer reach, unique viewers, conversions, audience authenticity, or campaign ROI from these counts alone.

5. Validate and deliver

Inspect missingCoreFields and warnings. The CLI warns when no engagement metric or content identity is returned, and when the platform is unrecognized. Accept completion only when success is true and resultPath points to a non-empty engagement.json.

Present requested fields in the user's language, identify the platform, retain the source URL, and distinguish raw values from any calculated ratios.

6. Handle failures deliberately

Retry only when error.retryable is true; respect the CLI retry limit. Correct invalid URLs and homepage/content-page mistakes before retrying. If content is deleted, private, region-restricted, or blocked by the platform, report that limitation instead of fabricating metrics.

Authorization

Provide the API key through the fixed UNITYCLAW_KEY environment variable. Obtain a key from UnityClaw if needed. The runtime installation declaration installs @unityclaw/sdk; for manual execution, run npm install @unityclaw/sdk when the package is unavailable.

Usage

node scripts/generate.js --url "https://www.xiaohongshu.com/explore/xxxx"
node scripts/generate.js --url "https://www.tiktok.com/@user/video/123456" --lang zh --json --output-dir ./tasks
node scripts/generate.js --url "https://www.douyin.com/user/example?vid=123456" --json

Parameters

Parameter Short Required Default Description
--url -u Yes - One public social-media post or video URL
--lang -l No auto Presentation-label language: auto, zh, en, or ja; locale variants are accepted
--output-dir - No ./tasks Task output directory; resolved to an absolute path
--timeout - No 900000 SDK request timeout in milliseconds, from 1,000 to 3,600,000
--retries - No 1 Retry count for transient failures, from 0 to 3
--json - No false Emit one machine-readable JSON result without progress output
--help -h No - Show help

Known Fields

Raw key Meaning
author_name Public author name
title Post or video title
tag_text Tags returned by the platform
play_count Plays or views under the platform's definition
like_count Likes
comment_count Comments
collect_count Collections or saves
share_count Shares
duration Content duration
created, updated Platform-provided time values
cover Cover URL
download_urls Download URL data when returned

Extra fields returned by the service are preserved.

Output Contract

With --json, the command emits exactly one JSON object. A successful result contains task metadata, resultPath, resultBytes, original sourceUrl, normalized requestUrl, platform, language, raw data, localized fields, missingCoreFields, and warnings. The task folder contains engagement.json plus SDK request and response logs.

A failed result contains a stable error.code, human-readable error.message, error.retryable, attempts, and available task or log information. The process exits non-zero on failure.

Resource Index

  • Run scripts/generate.js for engagement retrieval.

常见问题

5 问
答案由本站依据条目字段整理
社交媒体互动数据分析怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_fabd0a58/unityclaw-media-data-engagement。安装方式为未标注。装完刷新技能列表或重开客户端。

社交媒体互动数据分析支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

社交媒体互动数据分析权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

社交媒体互动数据分析收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

社交媒体互动数据分析用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 2026-11-06。