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-benchmark-researchgit 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-benchmark-research)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-benchmark-research"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-benchmark-research/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-benchmark-research"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-benchmark-research.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 | $0.00169 | $0.03726 |
| Opus 5 | $0.00084 | $0.01863 |
| Sonnet 5 | $0.00034 | $0.00745 |
| Haiku 4.5 | $0.00017 | $0.00373 |
Grade A, and why
x-benchmark-research 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
对标账号研究 — 5步法+变形出差异
R — 原文 (Reading)
找对标不是抄内容,而是借别人验证过的流量逻辑。5步:1.找到3-5个对标账号(搜索from:xxx min_faves:10);2.分析近90天爆款;3.学互动策略(前30分钟积极互动);4.拆变现模式(bio+置顶);5.找差异化定位。变形三公式:场景细化、人群聚焦、观点反转。
— AIP出海教程 2.3 对标账号研究5步法 / 9.1 看对标:从爆款里挖"可复用的需求"
I — 方法论骨架 (Interpretation)
对标研究的核心不是"抄谁的内容",而是"借谁验证过的流量逻辑"——别人已用真实数据证明某类需求存在,你借这个验证结果,用自己的差异化重新填空。
5步层层递进:
- 找对标:选3-5个"低粉高爆"账号(粉丝不多但单条爆款多=流量逻辑可迁移,而非靠粉丝基数),用高级搜索
from:xxx min_faves:10筛爆款,优先用户重合度80%+、近60天有3篇以上爆文的账号,避免"伪对标" - 拆爆款:分析近90天爆款,抓隐性需求(标题高频痛点词、数据爆发的关键段落),而非只看表面内容
- 学互动:观察前30分钟积极互动+社群加热的冷启动模式
- 拆变现:从bio和置顶帖看出变现路径(广告/课程/咨询/订阅/带货)
- 变形出差异:用三公式在已验证需求上创新——场景细化、人群聚焦、观点反转
关键原则:"借别人验证过的流量逻辑,不抄内容"。前4步是手段,第5步(差异化)才是目的。
A1 — 书中的应用 (Past Application)
案例 1: @dotey(宝玉) — 深层干货赛道 0→15万粉拆解
- 问题: 想在AI深层干货赛道找到增长路径和变现模式
- 方法论的使用: AIP教程用5步法拆解@dotey的三阶段增长——找对标(深层干货赛道低粉高爆账号)→拆90天爆款(发现nano banana prompt是爆发点,抓到"可复用的prompt工程"隐性需求)→学互动(教程型+观点型组合,前30分钟社群加热)→拆变现(bio显示咨询/课程/赞助三层)→变形(在深层干货基础上加个人工程经验差异化,而非纯搬运prompt)
- 结论: 0-1w靠教程型(提示词入门,转化率10%)→1-5w增加观点型+争议(模型能力论,转化率18%,推付费课程)→5-10w深层干货(nano banana prompt病毒教程10万+浏览,转化率25%,开发咨询+会员)
- 结果: 15万粉,收入结构:咨询40%+课程30%+赞助30%
案例 2: @ahhhhfs — 搬运赛道 0→73万粉拆解
- 问题: 想用搬运路线快速涨粉,但需要找到差异化避免同质化
- 方法论的使用: AIP教程拆解——找对标(资源搬运类高收藏账号)→拆爆款(列表型结构化整理"10个AI工具"转发率10%,隐性需求=读者要的是"整理好的入口"不是"更多信息")→学互动(高收藏型+CTA订阅TG)→拆变现(广告+TG付费频道)→变形(从纯搬运升级为搬运+整合,加教程元素做差异化)
- 结论: 0-1w列表型+免费实用→1-5w优化为高收藏型+教程→5-10w病毒帖55万浏览。从第一级(纯搬运)升级到第二级(搬运+整合资讯)
- 结果: 73万粉(泛流量路线),收入结构:广告50%+订阅30%+赞助20%
案例 3: @dontbesilent12 — 赚钱赛道 0→5.7万粉拆解
- 问题: 想在赚钱赛道找到差异化定位(赛道拥挤,如何不沦为营销号)
- 方法论的使用: AIP教程拆解——找对标→拆90天爆款(故事型+痛点钩子,隐性需求=读者要"可执行的赚钱思路"不是"鸡汤")→学互动(引入争议观点激发辩论,回复率20%)→拆变现(免费小贴士→咨询→课程逐步升级)→变形(从纯故事型引入观点型+教程元素混合,做"有态度的活人"而非千篇一律的营销号)
- 结论: 0-1w故事型+高频(每周5-7帖,转化率10-15%)→1-5w引入争议观点(回复率20%,推付费咨询)→5-10w混合型+教程(转化率20%+,开发千元级课程)
- 结果: 5.7万粉,收入结构:课程40%+咨询30%+广告/合作30%
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 用户刚开始做X或重新定位,不知道找谁对标学习
- 用户已有赛道方向(如AI工具),问"怎么找差异化""别人已经做了我怎么不同"
- 用户想系统分析某个竞品账号的爆款逻辑和变现模式
- 用户发了一段时间内容效果不好,想找对标看看自己缺什么
- 用户想从已验证的爆款需求出发,生成有差异化的原创选题
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 · 167 lines · 169 tokens per session scan A e4347e26dcb4
x-benchmark-research is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 3,726 once invoked, about $0.0008 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
purple-cow-audit
Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product…
niche-positioning-brief
Writes a concise positioning brief that defines a newsletter's niche, primary differentiator, target reader, editorial promise, and what the publication refuses to do — giving the editor a clear decision-making framework and a document that can anchor copy across subscribe pages, pitches, and About pages.
purple-cow-audit
Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product…
purple-cow-audit
Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product…
purple-cow-audit
Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product…
outlier-post-finder
Use when the user wants to find posts, videos, reels, shorts, tweets, or social content that overperformed versus a creator, brand, or competitor baseline. Finds outliers, explains why they worked, extracts hooks and formats, and produces a practical swipe file.