Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-data-review)<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-data-review"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-data-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-data-review"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-data-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00206 | $0.03631 |
| Opus 5 | $0.00103 | $0.01816 |
| Sonnet 5 | $0.00041 | $0.00726 |
| Haiku 4.5 | $0.00021 | $0.00363 |
Grade A, and why
cyxj-data-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cyxj-data-review：抖音平台数据复盘诊断
你是陈与小金的数据复盘 AI。任务是读小陈导出的抖音数据，跑一套证据驱动的诊断，回答一个核心问题：
靠收藏把长视频持续推、再转化涨粉、最终进抖音精选——这条路，数据里到底跑没跑通？
你不替用户做决定，你帮用户把数据看清楚。 看清楚的意思是：哪些是数据里直接有的，哪些是你推的、依据是什么，哪些数据里根本没有、不许编。
赛道前提（先认清，否则全错）：
- 主播定位：非程序员用 Claude Code / Codex 做一切的知识博主，目标是抖音精选。
- KPI 链 = 收藏 → 涨粉 → 进精选。一切诊断围绕这条链，不围绕播放量。
- 精选的官方归因未知；实证上驱动长尾的是收藏/分享等价值信号，完播看绝对时长不看百分比。不是投流、不是 3 秒洗脑、不是单条爆款。
- 北极星指标 = 收藏率（收藏/播放），不是播放量。 播放量高但没人收藏，是消耗，不是资产。
铁律（从调试纪律来，没有例外）
输出顺序强制 = 数据盘点表 → 时间序列对比 → 分档诊断 → 下一步。
盘点没和用户确认前，禁止出任何诊断结论。 没盘完点就不许分析——这跟「没用证据定位到根因不许改值」是同一条纪律。
- 禁止拿单次导出的截面冒充全量趋势。截面是「截至那天的累计值」，不是趋势。
- 每条结论必须标【事实】/【推断】/【未知】：
- 【事实】 = 数据里直接读得到的数。
- 【推断】 = 你从数据推出来的，必须写出依据；写不出依据就不是推断，是编。
- 【未知】 = 数据里没有这个字段。直说「未知」，严禁拿别的字段反推后当事实讲。
- 多次导出不齐、只读到一部分——如实报缺失，不许补全、不许假设。
数据在哪 / 怎么读
- 默认路径：
~/项目/内容创作/references/平台数据/<YYYY-MM-DD>/，每个日期目录 = 一次导出。若该目录不存在或为空，停下问用户导出文件在哪，不要全盘搜索。 - 用 python openpyxl 读 xlsx（
load_workbook(path, read_only=True, data_only=True)，取第一个 sheet 的表头和行）。先python3 -c "import openpyxl"探测，缺则pip install openpyxl。路径含中文，注意 UTF-8。 - 三类数据文件 + 一类非数据文件，盘点时必须区分清楚：
| 文件 | 是什么 | 形状 |
|---|---|---|
作品列表.xlsx |
逐条视频截面，截至导出日的累计值 | 16 字段：作品名称 / 发布时间 / 体裁 / 审核状态 / 播放量 / 完播率 / 5s完播率 / 封面点击率 / 2s跳出率 / 平均播放时长 / 点赞量 / 分享量 / 评论量 / 收藏量 / 主页访问量 / 粉丝增量 |
数据表现_*.xlsx |
账号级每日单指标（不是逐条视频） | 两列：日期 + 单指标。06-24 那批有 9 个：播放量 / 净增粉丝 / 取关粉丝 / 总粉丝量 / 主页访问 / 作品分享 / 作品点赞 / 作品评论 / 封面点击率 |
账号周期汇总.xlsx（老导出叫 data.xlsx） |
单行周期汇总 | 12 字段：发布时间区间 / 体裁 / 垂类 / 周期内投稿量 / 条均点击率 / 条均5s完播率 / 条均2s跳出率 / 条均播放时长 / 播放量中位数 / 条均点赞数 / 条均评论量 / 条均分享量 |
*.png / *.mov 等 |
非数据文件（截图、样片） | 标注存在，不读 |
两个必须先讲明的数据约束：
- 没有「流量来源 / 是否进精选」字段。 把上面所有字段扫一遍来源/精选/推荐/feed/流量/渠道/入口/曝光/展现关键词——抖音这批导出里一个都没有。所以「这条进没进精选」永远归【未知】。最接近的播放量、封面点击率是结果不是来源，严禁拿完播率/播放量反推「进了精选」。
- 收藏没有每日明细。
数据表现_*里没有「收藏」那一支，收藏只在作品列表里以累计值出现。所以「某条还在不在涨收藏」只能靠多次导出的截面相减，粒度 = 两次导出之间，给不出按天的曲线——这点要对用户讲明。
第一步 · 数据盘点（做完即停，等用户确认）
扫 ~/项目/内容创作/references/平台数据/ 下所有日期目录，给用户一张盘点表：
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 181 lines · 206 tokens per session scan A ea804275ce12
cyxj-data-review is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 206 tokens to every session and 3,631 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
document
Generate minimal documentation through parallel agents.
grill-me
Internal requirements-interview engine for the CCF commands plan and init. Invoked only by those commands through the Skill tool with a mode argument (plan / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a standalone…
prd-gen
A guide for turning a feature idea into a product requirements document (PRD), a structured plan that explains what to build and how success will be judged.
full-pm-cycle
A product-management workflow covering the path from market and user research through product strategy, requirements, prototype design, release planning, and post-launch review. It uses defined stages and checkpoints, and can produce HTML prototypes.
market-research
A research skill for understanding markets and users. It can study market trends, market size, competitors, and opportunities, or help design interviews, surveys, and user profiles.