Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kangarooking/X-growth-skills --skill x-data-reviewgit clone --depth 1 https://github.com/kangarooking/X-growth-skillsWrote 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/kangarooking/x-growth-skills/x-data-review)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-data-review"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-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/kangarooking/x-growth-skills/x-data-review"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-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 | $0.00215 | $0.03401 |
| Opus 5 | $0.00108 | $0.01700 |
| Sonnet 5 | $0.00043 | $0.00680 |
| Haiku 4.5 | $0.00021 | $0.00340 |
Grade A, and why
x-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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
80/20 数据复盘四步闭环
R — 原文 (Reading)
步骤1数据收集(What Happened);步骤2分析原因(Why);步骤3优化迭代(How to Improve);步骤4记录与追踪。使用数据驱动,避免主观臆断。目标:找出80/20法则(20%内容贡献80%价值)。小复盘聚焦数据(周复盘互动率),大复盘审视战略(月复盘变现路径)。
— AIP出海教程, 9.3 内容数据复盘
I — 方法论骨架 (Interpretation)
这是一个结构化的内容数据复盘框架,核心是用"布局-执行-复盘-迭代"闭环替代流水账式记录。
四步依次推进:(1) 数据收集——拉取周期内所有帖子的曝光/互动/收藏,按内容类型(故事/列表/观点/教程)分组,记录外部因素(热点/算法变化);(2) 原因分析——对比各类型表现,检查 Hook 是否抓痛点、Body 是否有深度、CTA 是否引导行动,分析受众活跃时段;(3) 优化迭代——问"如果重来怎么做更好",设定可执行的行动计划(调频率/测新角度/加倍高效类型);(4) 记录追踪——用 Notion 或 Excel 建复盘模板,长期追踪形成闭环。
指导原则是 80/20:找到 20% 贡献 80% 价值的内容加倍投入,而非平均用力。
复盘时有两组参考指标:(1) 生命周期——推文自然生命周期 1-3 天,复盘前至少等 3-4 天让数据跑完;(2) 黄金长度——120-220 字的帖子进前 10% 概率更高,可作长度与表现的相关性参考。但两者都是参考而非硬指标,不同赛道数据分布不同,直接套用等于过拟合。
频率分层:周复盘聚焦数据(互动率是否>2%),月复盘审视战略(变现路径/定位是否需调整)。
A1 — 书中的应用 (Past Application)
案例 1: 向阳乔木 3 年数据复盘
- 问题: 3 年发了 3861 条帖子,如何从海量数据中找到内容增长的关键规律
- 方法论的使用: 用 3.4G 自有数据做系统复盘——步骤1收集全部帖子互动分(点赞+3倍转发);步骤2按内容原型分类(资源入口型51%/工具教程型39%/AI工具发现型24%/普通表达型9%),对比中位互动和进前10%概率;步骤3发现资源入口型和工具教程型是贡献80%价值的20%内容,加倍投入这两类;步骤4持续追踪形成3年 longitudinal data
- 结论: 20% 的内容(资源入口型+工具教程型)贡献了 80% 的增长;收藏>点赞(37万>31万)说明读者把账号当"工具箱"而非"内容源"
- 结果: 账号从 100 粉增长到 11 万;增长节点出现在"连续出现值得收藏的单位"时,验证了 80/20 加倍投入的方向正确
案例 2: AIP 教程复盘指标体系
- 问题: 复盘时该看哪些指标、目标值是多少
- 方法论的使用: 定义四类核心 KPI——印象数(曝光效率)、互动率((点赞+回复+转发+引用)/印象数,目标>2%)、收藏率(高=干货价值)、回复深度(社区黏性);周复盘查互动率,月复盘查变现路径
- 结论: 互动率>2% 是健康基线;收藏率比点赞率更能反映长期价值;回复深度反映社区黏性而非单条表现
- 结果: 形成可复用的复盘模板(Notion+AI 双重复盘),包含"做对了什么""哪里优化""下步计划"三栏,长期追踪形成闭环
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 周/月复盘周期到了 — "这周发了15条,帮我复盘一下数据"——用户需要一个结构化流程来分析周期内所有帖子的表现并决定下步策略
- 批量内容表现差异大,需要找原因 — "同样是教程型,为什么有的收藏高有的没人理?"——需要按内容类型分组对比,查 Hook/Body/CTA 差异
- 决定下步内容策略调整方向 — "下周该多发什么类型?频率怎么调?"——需要基于数据找到20%贡献80%的内容加倍投入
- 复盘指标不健康需要诊断 — "互动率只有1.2%,低于2%目标,哪里出了问题?"——需要系统性排查是曝光不够(算法/时间)、还是展开不够(Hook弱)、还是不进Profile(门面差)
语言信号 (用户的话里出现这些就应激活)
- "这周发了15条怎么复盘" / "weekly content review"
- "哪些内容类型互动高" / "which content type performs better"
- "下周内容策略怎么调" / "optimize next week's content strategy"
- "帮我分析数据" / "help me analyze my content data"
- "收藏率高的是哪种类型" / "which posts get more saves"
- "月复盘看一下变现路径" / "monthly review conversion path"
- "如果重来怎么做更好" — 原文步骤3的核心措辞
What ships with it
2 files 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 · 149 lines · 215 tokens per session scan A 0d25743962ae
x-data-review is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 3,401 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
html-ppt-zhangzara-vellum
A humanities lecture: how Renaissance linear perspective reshaped early cartography — sources, argument, and evidence. Built as a decision-grade academic research deck for faculty, graduate seminar.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
ralphex-adopt
Convert plans from various source formats (OpenSpec, spec-kit, GitHub/GitLab issues with checklists, generic task-lists, free-form markdown) into ralphex-format plans in docs/plans/. Triggers on "ralphex-adopt", "adopt plan", "convert plan to ralphex", "import plan as ralphex".
ralphex
Run ralphex autonomous plan execution with progress monitoring.