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-cold-start-playbookgit 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-cold-start-playbook)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-cold-start-playbook"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-cold-start-playbook/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-cold-start-playbook"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-cold-start-playbook.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 | $0.00191 | $0.03879 |
| Opus 5 | $0.00096 | $0.01939 |
| Sonnet 5 | $0.00038 | $0.00776 |
| Haiku 4.5 | $0.00019 | $0.00388 |
Grade A, and why
x-cold-start-playbook 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 13d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
冷启动六策略 + 涨粉转化漏斗
R — 原文 (Reading)
"策略1大V评论区抢占(最有效⭐⭐⭐⭐⭐):关注10个中小V,开通知,5分钟内评论,每天10条,日涨5-15粉。策略5引用转发+深度观点,和策略1一样有效。帖子靠前24小时尤其前几小时;前面安安静静,系统觉得没人感兴趣,它就沉了。涨粉四步:曝光→展开完读→进Profile看门面→关注。"
— AIP出海教程·5.1 Step5/5.2; X起号避坑指南·四
I — 方法论骨架 (Interpretation)
冷启动不是"发好内容等它自然火",而是新号没粉丝时按边际回报排序主动投时间。两个工具配合使用:
涨粉四步漏斗(诊断工具): 推文曝光→展开/完读→进Profile看门面→关注。每步都有流失。先诊断你丢在哪步:推文没曝光(用策略1抢大V评论区借大V的流量)/展开了不进Profile(推文没引导"看我主页"的钩子)/进了不关注(门面四要素没到位,转x-account-setup)。
六策略(按边际回报排序):
- 大V评论区抢占(最高)——关注10个1w-10w中小V,开通知,5分钟内评论,模板=重述观点+补充经验,每天10条
- 引用转发+深度观点(同级)——Quote大V推文+300字增量观点
- 每日发推——每天1-3条,先跑起来不追求完美
- 互关社区——前3天快速获30-50粉,但每天≤15人防风控
- 热门蹭流量——搜索+trending
- 互动率优先——积极回复每条评论
前24h加热机制: 帖子发出后系统给一点初始曝光,前几小时如果有互动就进入更大流量池;安安静静就沉了。发完不能不管——主动找朋友转、社群加热、大V帮忙转。
核心决策逻辑:把有限时间投到边际回报最高的地方(评论区抢占+引用转发>被动发推),而非均匀分配。
A1 — 书中的应用 (Past Application)
案例 1: 木马人21天0→4200(起号帖28万曝光靠朋友帮转)
- 问题: 被封号后新号重启,0粉丝,怎么度过冷启动?
- 方法论的使用: 用前24h加热机制——起号帖发出后靠朋友们(社群成员)互相转发加热,主动突破初始流量池;配合装修好主页+开蓝V,让漏斗第3步Profile门面能接住流量。他付费加入Panda老师增长群,群内小伙伴互相加热帖子快速过渡冷启动。
- 结论: 冷启动期主动找人帮忙转比被动等自然流量有效得多;前几小时的社群加热能突破初始池,让帖子进入更大推荐池。
- 结果: 起号帖28万曝光,粉丝从16涨到700+,21天做到4200粉,成功度过冷启动。
案例 2: 向阳乔木被tw93和宝玉推荐涨到1万Followers
- 问题: 冷启动期最早的1万粉从哪来?
- 方法论的使用: 策略1(大V评论区抢占)+策略5(引用转发)的变体——坚持每天刷Product Hunt、海外Newsletter,测试AI工具写反馈,通过"准备干货+被动传播+主动评论"让KOL看到优质内容并主动转发。tw93和宝玉转发他的内容后,粉丝涨到1万。
- 结论: 大V评论区抢占的本质不是"蹭",而是在有大V曝光的地方展示增量价值,让KOL主动注意到你并帮你放大——冷启动期的被动传播来自主动准备。
- 结果: 被tw93和宝玉推荐后涨到1万Followers,完成冷启动。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 新号没粉丝,发了推文没人看——需要漏斗诊断丢在哪步+六策略选优先级。
- 有少量粉丝(几十到几百)但帖子曝光仍然很低——判断是否还在冷启动期+选策略突破。
- 发完推文不知道要不要主动加热/怎么加热——需要前24h加热机制的具体操作。
- 时间有限,冷启动阶段不知道该优先做什么——需要按边际回报排序策略组合。
- 互关社区/社群加热想用但怕触发风控——需要安全红线(每天≤15互关)和正确用法。
语言信号 (用户的话里出现这些就应激活)
- "没粉丝怎么办" / "帖子没人看" / "0粉丝怎么起号"
- "冷启动怎么过" / "怎么起量" / "怎么破零"
- "发了推文没人理" / "曝光个位数" / "新号没流量"
- "互关群有用吗" / "要不要找朋友帮转" / "发完推文要做什么"
- "0 followers" / "no engagement" / "cold start" / "new account no views" / "how to get first 100 followers"
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.
- 13d ago First seen · 155 lines · 191 tokens per session scan A c2a63f6c7c79
x-cold-start-playbook is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 191 tokens to every session and 3,879 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 2026-08-30.
Other skills, from other repositories
prioritization
Prioritization frameworks — RICE, WSJF, ICE, MoSCoW, and opportunity cost scoring for backlog ranking. Use when prioritizing features, comparing initiatives, justifying roadmap decisions, or evaluating trade-offs between competing work items.
product-frameworks
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
open-source-marketing-playbook
Marketing playbook for open-source projects led by non-technical founders. Covers README optimization, community building, contributor attraction, and translating OSS traction into revenue. By @WeiYipei.
eisenhower-matrix
Prioritizes tasks and time allocation using the Eisenhower Matrix, classifying activities into four quadrants by urgency and importance: Do (urgent and important), Schedule (important but not urgent), Delegate (urgent but not important), and Eliminate (neither). Use when overwhelmed by competing demands, auditing how…
interpret-results
Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.
Risk Assessment
Use when applying a structured, jurisdiction-agnostic method to identify, rate, and prioritize legal risks in a situation, producing a risk register with severity bands and a prioritized summary for attorney review.