x-longtail-strategy

x-longtail-strategy is a skill for Claude Code, Codex from kangarooking/X-growth-skills. It costs 235 tokens per session (2,945 once invoked), scanned A, original, MIT.

A strategy for understanding why most posts on X, formerly known as Twitter, receive ordinary engagement while a small number receive much more. It treats growth as improving the chance of producing posts in the top group rather than expecting every post to go viral.

In plain words
What is it for?
Use it when reviewing weak post performance, setting growth goals, choosing content formats, or planning data-based experiments on X. A long-tail distribution means that a few unusually successful results account for much of the total attention.
Why use it?
It removes the assumption that a post with little response proves the content or creator has failed. It gives a way to evaluate a batch of posts and improve the overall process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it when reviewing weak post performance, setting growth goals, choosing content formats, or planning data-based experiments on X. A long-tail distribution means that a few unusually successful results account for much of the total attention.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kangarooking/x-growth-skills/x-longtail-strategy
Install

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.

Any agent
npx skills add kangarooking/X-growth-skills --skill x-longtail-strategy
Clone the repo
git clone --depth 1 https://github.com/kangarooking/X-growth-skills

Made for: Claude Code, Codex.

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.

agentmods badge for x-longtail-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-longtail-strategy/github.svg)](https://agentmods.dev/skills/kangarooking/x-growth-skills/x-longtail-strategy)
Your own site
<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-longtail-strategy"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-longtail-strategy/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.

agentmods 80×15 button for x-longtail-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-longtail-strategy"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-longtail-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,945 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00235 $0.02945
Opus 5 $0.00118 $0.01473
Sonnet 5 $0.00047 $0.00589
Haiku 4.5 $0.00023 $0.00295

Measured 12d ago against content hash c81c1489f101, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

x-longtail-strategy 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.

x-longtail-strategy/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

长尾分布策略 — 系统性提高进前 10%

R — 原文 (Reading)

样本 3861 条主帖,平均互动分 188.4,中位数只有 42。大多数帖子表现普通,少数帖子承担大部分增长。公共平台的传播本就是长尾分布。真正的问题不是怎样让每条都爆,而是怎样系统性提高内容进入前 10% 的概率。

— 向阳乔木, X爆款秘籍分享 · 增长的真相:长尾分布


I — 方法论骨架 (Interpretation)

这是一个面向公共平台传播的战略心智模型,核心是一次问题转换。

公共平台的传播天然是长尾分布,不是正态分布——大多数人以为"只要内容好就该有流量",但数据显示 3861 条帖子里中位数只有 42 互动,均值却被少数爆款拉到 188。这意味着:绝大多数帖子表现普通是常态,不是你的失败。

关键转换:把"怎么让每条都爆"(不可能的问题)换成"怎么系统性提高进前 10% 的概率"(可工程化的问题)。这把努力方向从"赌单条爆款"转向"建可重复的系统"——选对内容原型、匹配发布时间、强化证据可信度,都是提高概率的杠杆,而非保证爆款的公式。

它同时是一个抗焦虑工具:一条表现普通的帖子不是失败,而是预期的中位数。


A1 — 书中的应用 (Past Application)

案例 1: 向阳乔木 3861 帖样本统计

  • 问题: 理解 X 内容传播的真实分布规律,回答"一条帖子表现普通到底正不正常"
  • 方法论的使用: 用 3 年 3.4G 自有数据,统计 3861 条主帖的互动分(点赞 + 3 倍转发),画出分布
  • 结论: 均值 188、中位数仅 42,典型长尾——少数帖子承担大部分增长,大多数帖子表现普通是结构性常态
  • 结果: 战略从"赌单条爆款"转向"系统性提高进前 10% 概率",后续内容选择(资源入口型 51%、工具教程型 39%)和数据复盘都围绕这一目标展开

案例 2: 向阳乔木增长节点(2026.1 连续爆款)

  • 问题: 在长尾分布中,增长到底怎么发生——是线性累积还是节点突破
  • 方法论的使用: 观察自己账号的增长曲线,发现增长不是每天均匀发生,而是在"连续出现值得收藏的单位"时触发节点式突破
  • 结论: 长尾分布下,增长靠的是少数高质量帖集中爆发,而非每条均匀贡献;目标是让这批"值得收藏的单位"连续出现
  • 结果: 2026 年 1 月连续爆款,账号从 100 粉增长到 11 万——验证了"系统性提高进前 10% 概率"比"每条都追爆款"更有效

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 帖子没爆感到焦虑 — 发了几条内容互动很低,开始怀疑自己"是不是不适合做 X""一条没爆就怀疑人生"
  2. 连发一批内容后评估整体表现 — "我连发 20 条只有 2 条过百,该放弃吗?"需要用长尾基准校准预期
  3. 设定增长目标时 — 用户问"怎么让每条都爆",需要把目标从不可能的问题转换为可工程化的问题
  4. 对比他人爆款产生落差 — 看到别人爆款觉得自己差很远,需要理解长尾分布下"别人的爆款也是少数"

语言信号 (用户的话里出现这些就应激活)

  • "我连发 20 条只有 2 条过百,该放弃吗?"
  • "怎么让每条都爆" / "how to make every post go viral"
  • "一条没爆就怀疑人生" / "发了这么多条都没什么水花"
  • "是不是我不适合做 X" / "my posts get no engagement"
  • "为什么我的帖子互动这么低" / "only 2 out of 20 hit 100, should I quit"
  • "别人一发就爆,我怎么都不行"

与相邻 skill 的区分

  • x-data-review 的区别: data-review 是"怎么复盘数据找 80/20"(操作方法),本 skill 是"怎么定增长目标和心态"(心智模型)。数据复盘是手段,长尾心态是前提——先接受长尾,再用数据复盘优化系统。
  • x-foryou-algorithm 的区别: foryou-algorithm 是"理解推荐机制怎么工作"(算法知识),本 skill 是"面对传播结果怎么调整心态和目标"(战略心智)。一个是底层机制,一个是面对结果的战略转换。
  • x-content-archetypes 的区别: content-archetypes 是"选什么类型内容提高传播上限"(内容选择手段),本 skill 是"接受大多数内容不会爆这个前提"(心态基准)。原型选择是提高概率的杠杆之一,长尾心态是使用杠杆的前提。

Read the full file on GitHub · 143 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 143 lines · 235 tokens per session scan A c81c1489f101

Subscribe to this mod's changes

x-longtail-strategy is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 1mo ago), licensed MIT. It adds 235 tokens to every session and 2,945 once invoked, about $0.0012 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.

Related

Other skills, from other repositories

festival-strategy-brief

Produces a festival submission strategy brief for a documentary or short film, identifying target festivals by tier, submission windows, positioning priorities, and a recommended sequencing plan.

ur-grue/autopunk-media-skills · 37 tokens

multi-channel-publishing

Use when repurposing long-form content into channel-specific formats — LinkedIn posts, conference abstracts, podcast briefs, newsletter summaries, tweet threads, or spoken scripts. Encodes compression methodology, channel format rules, evidence density calibration, and audience adaptation. Produces channel-ready…

Avyayalaya/agent-prime · 64 tokens

multi-channel-publishing

Use when repurposing long-form content into channel-specific formats — LinkedIn posts, conference abstracts, podcast briefs, newsletter summaries, tweet threads, or spoken scripts. Encodes compression methodology, channel format rules, evidence density calibration, and audience adaptation. Produces channel-ready…

Avyayalaya/pm-skills-arsenal · 64 tokens

html-ppt-zhangzara-blue-professional

OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.

nexu-io/open-design · 47 tokens

html-ppt-zhangzara-mat

A margin-recovery diagnosis for a regional grocery chain — the governing thought, the driver tree, the priorities, and the roadmap. Built as a decision-grade consulting deck for client sponsor, steering committee.

nexu-io/open-design · 51 tokens

html-ppt-zhangzara-soft-editorial

A digital-transformation roadmap for a legacy insurer — the diagnosis, the sequenced bets, and the operating rhythm to land them. Built as a decision-grade consulting deck for client executives.

nexu-io/open-design · 49 tokens