Agent skill

Skill Data Tracker

by ZJU-REAL in ZJU-REAL/Easel

社媒数据记录与趋势分析。三种模式:(A) 记录快照 — 记录当日粉丝数、互动量等指标快照; (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测;(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化,判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。

Apache-2.0Auto-check passed

Install Skill Data Tracker

skills CLI
$ npx skills add ZJU-REAL/Easel --skill skill-data-tracker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel skill-data-tracker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/skill-data-tracker .claude/skills/skill-data-tracker && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-data-tracker
GitHub stars
3.2k
Token cost
~1.2k tokens
SKILL.md length
209 words
Files
3 (incl. scripts)
Skills in repo
113
Repo updated
First seen
Licence
Apache-2.0

At a glance

社媒数据记录与趋势分析。三种模式:(A) 记录快照 — 记录当日粉丝数、互动量等指标快照; (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测;(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化,判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。

  • Works in 3 steps: 从 Profile(identity.md 取 profile… → 调用脚本(一天一快照,同日覆盖;自动计算与上次快照的 delta) → 展示脚本返回的 snapshot + delta_vs_last + 保存路径。
  • SKILL.md covers 数据层定位, 输入, 输出 and 数据存储, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Skill Data Tracker is an agent skill from ZJU-REAL/Easel. 社媒数据记录与趋势分析。三种模式:(A) 记录快照 — 记录当日粉丝数、互动量等指标快照; (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测;(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化,判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `EASEL-META.md` and `scripts/track.py`).

The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

Example prompts

  • “内容生命周期”
  • “这条笔记数据变化”
  • “/skill-data-tracker”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 从 Profile(identity.md 取 profile 名、platforms.md 取平台)或用户输入采集指标;缺失字段询问一次。
  2. 调用脚本(一天一快照,同日覆盖;自动计算与上次快照的 delta)
  3. 展示脚本返回的 snapshot + delta_vs_last + 保存路径。

What it can do on your machine

Read from SKILL.md and the folder at commit fb80ae6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Data Tracker loads about 1.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 209 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit fb80ae6, republished under its Apache-2.0 licence (© ZJU-REAL). 209 words, ~1,215 tokens.

Download SKILL.mdSave it as .claude/skills/skill-data-tracker/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
skill-data-tracker
description
社媒数据记录与趋势分析。三种模式:(A) 记录快照 — 记录当日粉丝数、互动量等指标快照; (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测;(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化,判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。
layer
attribute

社媒数据记录与趋势分析

记录社媒指标快照、分析粉丝增长趋势、追踪内容生命周期,用时间序列数据驱动运营决策。

数据层定位

本 SKILL 是归因链的粉丝 / 时序快照底座,唯一权威存储粉丝数、互动量、内容生命周期的时间序列快照(outputs/_analytics/snapshots/{profile}/{platform}/{date}.json)。

  • 只存时序快照,不存发布事件 — 每次发布的元信息(标题 / 链接 / 类型 / 来源 SKILL)由 skill-publish-log 维护(outputs/_analytics/publish-log.json)。本底座不重复记录发布事件,避免同一事实两处存储。
  • 消费方(读,不回写) — skill-publish-analytics 模式 D(增长归因)与 skill-social-performance-review(环比 / 粉丝趋势)以本快照为粉丝时序的权威来源。
底座存什么谁维护
outputs/_analytics/snapshots/{profile}/{platform}/{date}.json粉丝 / 互动时序快照(本 SKILL)skill-data-tracker
outputs/_analytics/publish-log.json发布事件skill-publish-log

输入

字段必填说明
mode是record / growth / lifecycle
platformMode A: 是平台名(小红书/抖音/微博/B站/公众号等)
followersMode A: 是当前粉丝数
total_likesMode A: 否总获赞数
total_postsMode A: 否总笔记/视频数
post_snapshotsMode A: 否近期帖子的逐条数据(用于生命周期追踪)
post_titleMode C: 是要追踪的帖子标题或标识
time_rangeMode B: 否分析窗口(默认近 30 天)

输出

Mode A — 记录快照
markdown
# 数据快照记录
- 日期: {date} | 平台: {platform} | Profile: {profile_name}

## 账号指标
| 指标 | 当前值 | 上次记录 | 变化 |
|------|--------|---------|------|

## 帖子快照(如有)
| 标题 | 发布日期 | 点赞 | 收藏 | 评论 | 转发 |

快照已保存至: outputs/_analytics/snapshots/{profile}/{platform}/{date}.json
Mode B — 增长趋势
markdown
# 增长趋势分析
- 平台: {platform} | 区间: {start} → {end} | 数据点: {count}

## 粉丝增长趋势
| 日期 | 粉丝数 | 日增长 | 日增长率 |

## 关键指标
- 日均/周均增长 | 趋势方向: 加速/稳定/减速
- 最高/最低单日增长
- 里程碑预测: 照此速度,{X} 天后破 {milestone} 粉
- 趋势洞察: {增长加速/减速原因分析与建议}
Mode C — 内容生命周期
markdown
# 内容生命周期分析
- 帖子: {post_title} | 发布: {published_at} | 平台: {platform}

## 生命周期数据
| 天数 | 日期 | 点赞 | 收藏 | 评论 | 转发 | 日增量 |
(Day 0 / 1 / 3 / 7 / 14 / 30 各行)

## 分类与洞察
- 类型: 速爆型/稳增型/长尾型 | 峰值日: Day {peak} | 半衰期: {days} 天
- 判定依据与后续策略启示

数据存储

快照文件路径:outputs/_analytics/snapshots/{profile}/{platform}/{date}.json

json
{
  "date": "2026-07-22",
  "platform": "xiaohongshu",
  "profile": "科技数码达人",
  "account_metrics": {
    "followers": 5200,
    "total_likes": 42000,
    "total_posts": 89
  },
  "post_snapshots": [
    {
      "post_id": "用户提供或自动编号",
      "title": "帖子标题",
      "published_at": "2026-07-20",
      "likes": 350,
      "collects": 120,
      "comments": 28,
      "shares": 15
    }
  ]
}

执行步骤

快照读写、增长率/移动平均/里程碑外推、生命周期分类全部由 scripts/track.py 确定性完成。LLM 负责补全参数(从 Profile/用户输入)、解读脚本 JSON、写增长建议。 不要手动算增长率、不要心算移动平均、不要手改快照 JSON。

Mode A — 记录快照
  1. 从 Profile(identity.md 取 profile 名、platforms.md 取平台)或用户输入采集指标;缺失字段询问一次。
  2. 调用脚本(一天一快照,同日覆盖;自动计算与上次快照的 delta):
bash
python3 skills/openclaw/skill-data-tracker/scripts/track.py snapshot --profile "科技数码达人" --platform xiaohongshu \
  --followers 5200 --total-likes 42000 --total-posts 89 [--date 2026-07-22] \
  [--posts 帖子逐条数据.json]   # --posts 为数组,含 post_id/title/published_at/likes/collects/comments/shares
  1. 展示脚本返回的 snapshot + delta_vs_last + 保存路径。
Mode B — 增长趋势
bash
python3 skills/openclaw/skill-data-tracker/scripts/track.py trend --profile "科技数码达人" --metric followers \
  [--platform xiaohongshu] [--since 2026-07-01] [--until 2026-07-31]

脚本返回:逐点日增长/日增长率、7 日移动平均、trend_direction(加速/稳定/减速)、 milestone + milestone_eta_days(≤30 天,超出返回 null)、warning(<3 点样本不足)。 LLM 据此写趋势洞察与受众相关建议(有 Profile 时读 audience.md)。

Mode C — 内容生命周期
bash
python3 skills/openclaw/skill-data-tracker/scripts/track.py lifecycle --profile "科技数码达人" \
  --platform xiaohongshu --post-title "露营装备" --metric likes

脚本跨快照重建帖子时间序列,返回逐日增量、peak_day、half_life_days、 lifecycle_type(速爆型/稳增型/长尾型/数据不足)。LLM 据类型写后续内容策略。

导出增长归因视图

记录快照后生成 skill-publish-analytics 模式 D 所需的派生视图;不要手工维护另一份粉丝台账:

bash
python3 skills/openclaw/skill-data-tracker/scripts/track.py export-followers

默认汇总全部画像和平台到 outputs/_analytics/follower-log.json;可用 --profile 或 --platform 过滤。

Profile 感知

有 Profile 时:

  • 读取 identity.md 获取 profile 名称,用作快照目录名
  • 读取 platforms.md 自动填充 platform 参数,支持多平台同时记录
  • 读取 audience.md 在增长分析中给出受众相关的增长建议
  • 快照目录按 profile/platform 隔离:outputs/_analytics/snapshots/{profile_name}/{platform}/

无 Profile 时:

  • 要求用户显式提供 platform 参数
  • 快照目录使用 "default":outputs/_analytics/snapshots/default/{platform}/
  • 增长分析不做受众关联判断
  • 附注"提供 Profile 可自动关联平台和账号信息"

规则

  1. 不修改不删除 — 已有快照文件只读不改,同一天同一平台的重复记录是唯一允许的覆盖情况
  2. 一天一快照 — 同一平台每天最多一个快照,当天重复记录会覆盖当天数据
  3. 最少 3 个数据点 — 增长率计算至少需要 3 个数据点,不足时输出警告而非空洞的趋势判断
  4. 预测不超 30 天 — 里程碑预测基于近期趋势外推,不超过 30 天,避免误导
  5. 数据来源透明 — 所有指标来自用户输入或快照文件,不编造数据,不假设未提供的指标

自研溯源与参考项目见同目录 EASEL-META.md。

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/openclaw/skill-data-tracker of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md
  • scripts/track.py

Open the folder on GitHubat commit fb80ae6

Compare with similar skills

Skill Data Tracker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Data Tracker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Data Tracker this skillZJU-REAL/Easel3.2k—~1.2kAutomated safety check: PassApache-2.0
Agent Issue Trackerruvnet/ruflo74k3 repos~2.4kAutomated safety check: PassMIT
Kpi Trackersickn33/agentic-awesome-skills47k1 repos~3.6kAutomated safety check: PassMIT
Probation Trackersickn33/agentic-awesome-skills47k1 repos~3.8kAutomated safety check: PassMIT
Tc Trackeralirezarezvani/claude-skills28k—~2.6kAutomated safety check: PassMIT
Investment Thesis TrackerHKUDS/Vibe-Trading35k—~2.2kAutomated safety check: PassMIT

Similar skills

  • Agent skill for issue-tracker - invoke with $agent-issue-tracker

    74k GitHub starsUsed in 3 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Kpi Tracker

    sickn33/agentic-awesome-skills

    KPI register: metric by level, department, job title and employee, linked OKR, unit and direction, target against actual, achievement and weight percentages, period and owner.

    47k GitHub starsUsed in 1 repo~3.6k tokens
    Business, Finance & HRAuto-check passed
  • Probation Tracker

    sickn33/agentic-awesome-skills

    Probation register: employee, start and end dates, 30, 60 and 90-day review scores, overall score and confirmation letter.

    47k GitHub starsUsed in 1 repo~3.8k tokens
    Auto-check passed
  • Tc Tracker

    alirezarezvani/claude-skills

    A skill your agent uses when the user asks to track technical changes, create change records, manage TC lifecycles, or hand off work between AI sessions.

    28k GitHub stars~2.6k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Investment Thesis Tracker

    HKUDS/Vibe-Trading

    Keeps a written investment thesis for each stock you hold and re-checks it every quarter against new earnings, scoring its health and recommending hold, add, trim or exit.

    35k GitHub stars~2.2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Technical Change Tracker

    sickn33/agentic-awesome-skills

    Track code changes with structured JSON records, state machine enforcement, and AI session handoff for bot continuity

    47k GitHub starsUsed in 2 repos~559 tokens
    Agent WorkflowsAuto-check passed

More from ZJU-REAL/Easel

All 113 skills in this repo
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.2k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.2k GitHub stars~657 tokensUpdated yesterday
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.2k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.2k GitHub stars~643 tokensUpdated yesterday
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.2k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Paper Explainer

    ZJU-REAL/Easel

    科研论文解读:解析 arXiv/PDF 的公式与图表,提炼问题、贡献、方法、关键图和结论,再产出 B站/视频号解读视频或知乎/公众号图文。

    3.2k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Skill Data Tracker

What does Skill Data Tracker do?

社媒数据记录与趋势分析。三种模式:(A) 记录快照 — 记录当日粉丝数、互动量等指标快照; (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测;(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化,判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。. Skill Data Tracker is an agent skill from ZJU-REAL/Easel.

How do I install Skill Data Tracker in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill skill-data-tracker -a claude-code`. Or copy the skill folder (skills/openclaw/skill-data-tracker in ZJU-REAL/Easel) into .claude/skills/skill-data-tracker in your project. Claude Code loads it when a task matches its description.

How do I install Skill Data Tracker in Codex?

Run `npx skills add ZJU-REAL/Easel --skill skill-data-tracker -a codex`. Or copy the skill folder (skills/openclaw/skill-data-tracker in ZJU-REAL/Easel) into .agents/skills/skill-data-tracker in your project. Codex loads it when a task matches its description.

Can I use Skill Data Tracker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill skill-data-tracker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-data-tracker, .gemini/skills/skill-data-tracker, .github/skills/skill-data-tracker and .opencode/skills/skill-data-tracker in your project.

What does Skill Data Tracker need to run?

Going by SKILL.md and its folder, Skill Data Tracker needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Skill Data Tracker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Data Tracker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Skill Data Tracker use?

Skill Data Tracker is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Data Tracker use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Data Tracker?

Skills that share tags, products or a category with Skill Data Tracker: Agent Issue Tracker (ruvnet/ruflo, 74k stars), Kpi Tracker (sickn33/agentic-awesome-skills, 47k stars), Probation Tracker (sickn33/agentic-awesome-skills, 47k stars) and Tc Tracker (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Data Tracker?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,230 GitHub stars. The repository holds 113 skills in this directory. The repository was last updated on October 7, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.