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-account-pitfallsgit 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-account-pitfalls)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-account-pitfalls"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-account-pitfalls/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-account-pitfalls"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-account-pitfalls.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.03774 |
| Opus 5 | $0.00084 | $0.01887 |
| Sonnet 5 | $0.00034 | $0.00755 |
| Haiku 4.5 | $0.00017 | $0.00377 |
Grade A, and why
x-account-pitfalls 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
账号健康与限流恢复
R — 原文 (Reading)
"频繁换IP或设备容易触发验证或临时标签,一般24h内解除。批量关注取关回复像脚本,严重时还会限流,封号。蓝V审核期乱改资料触发重新审核。检查限流:用另一账号搜from:@用户名,搜不到=被限流。先查Privacy设置;不行则写申诉邮件找@Support,48h不做任何账号操作。临时标签先不动账号,几小时结束。"
— 木马人, X起号避坑指南·7大坑; AIP出海教程·5.1.2账号检查
I — 方法论骨架 (Interpretation)
维护X账号健康分两层：预防（不让风控触发）和恢复（触发后怎么救）。
预防层 — 7大坑避免：
- 固定IP和设备，不频繁更换（触发验证/临时标签）
- 不批量关注/取关/回复（操作像脚本=判机器人）
- 蓝V审核期不改头像/昵称/简介（改资料触发重新审核，蓝V掉落）
- 发完推文前1小时盯数据、主动互动（不能发完就不管）
- 不硬蹭流量（在高流量帖下贴无关内容=被举报）
- 沉淀内容能力，不只追流量技巧（平台技巧会变，内容能力才可迁移）
- 封号不要怕，多申诉（申诉是常规恢复手段，不是绝路）
恢复层 — 限流自检与申诉：
- 自检：用另一个账号搜索
from:@你的用户名，搜不到=被限流 - 区分两个层级：临时标签（操作像脚本时被打上，几小时~24h自动解除，期间不动账号）vs 正式标签/限流（帖子搜不到，需写申诉邮件+48h不做任何账号操作）
- 申诉后复盘触发原因（换IP/批量操作/审核期改资料/关注粉丝比失衡），针对性预防复发
核心洞察：限流不等于封号——临时标签可自愈（等24h不动），正式标签可申诉（写邮件+48h静默）。恐慌中继续操作反而加重风控。
A1 — 书中的应用 (Past Application)
案例 1: 木马人11897粉一夜清零，申诉12次找回
- 问题: 账号突然被封，11897粉丝一夜清零，所有内容消失
- 方法论的使用: 7大坑第7条"封号不要怕，多申诉就好"——不放弃，反复向@Support提交申诉。每次申诉间隔适当，坚持12轮
- 结论: 封号不是终点，申诉是常规恢复手段；但需要有耐心，单次申诉不一定成功
- 结果: 经过12次申诉，账号最终找回
案例 2: 木马人21天0→4200重启，起号帖28万曝光
- 问题: 旧号找回后数据已废，需要从0重新起号
- 方法论的使用: 恢复后不急着重操旧打法，而是用"发完前1小时盯数据+主动找人帮转"度过冷启动。起号帖靠朋友们帮忙转发，一篇内容跑了28万曝光，粉丝从16个涨了700多
- 结论: 被限流/封号后重启，核心是靠朋友帮转度过冷启动黄金窗口，而非靠批量操作快速涨粉（那会再次触发风控）
- 结果: 21天从0做到4200粉，起号帖28万曝光
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 推文突然搜不到了/曝光断崖式下降——怀疑被限流，需要自检和排查
- 账号被提示有异常活动/临时标签——不知道该怎么办、会不会自己恢复
- 担心某个操作（换IP节点/批量关注/审核期改资料）会触发风控——需要知道红线在哪
- 账号被封/冻结后需要申诉恢复——需要申诉流程和文案模板
- 曾被限流/封号，想预防复发——需要建立日常操作安全清单
语言信号 (用户的话里出现这些就应激活)
- "推文搜不到了" / "被限流了" / "shadowbanned" / "tweets not showing up"
- "账号异常" / "触发风控" / "临时标签" / "account flagged"
- "被判机器人" / "account suspended" / "被封了怎么办"
- "怎么申诉" / "appeal suspension" / "申诉邮件怎么写"
- "频繁换IP会怎样" / "批量关注安全吗" / "审核期能改资料吗"
- "关注粉丝比" / "follow to follower ratio"
与相邻 skill 的区分
- 与
x-account-setup的区别: setup是"预防"——发内容前的开业准备（装修+蓝V+养号）；本skill是"治疗"——已出问题（限流/封号/标签）后的排查与申诉。用户说"新号第一天怎么准备"→setup；用户说"被限流了怎么办"→本skill。 - 与
x-cold-start-playbook的区别: cold-start是"获客"——没粉丝怎么起量（六策略+漏斗诊断）；本skill是"保命"——账号健康出问题时的恢复。用户说"发了推文没流量"→cold-start；用户说"推文搜不到了"→本skill。 - 与
x-comment-engagement的区别: engagement讲评论互动策略（怎么高质量回复）；本skill讲操作红线（批量回复=脚本特征，触发风控）。用户说"怎么写好评论"→engagement；用户说"回复太多被判脚本"→本skill。
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 · 187 lines · 169 tokens per session scan A 8735324dd5f5
x-account-pitfalls 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 3,774 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
meta-templates
Manage Meta WhatsApp templates — submit, status, audit, pull, appeal. Use for any WhatsApp BSP client with /.config/brana/meta/ .env provisioned.
stock-trading-analyst
Use when the user needs an A-share stock watchlist, short-term theme rotation review, or trading-plan risk audit based on user-provided market data. Produces evidence-based sector analysis, signal confidence, risk warnings, and a non-advisory action checklist for retail investors, research assistants, and trading…
quant-trading-researcher
Use when quant researchers or strategy developers need to evaluate factor ideas, backtest validity, statistical reliability, trading costs, implementation risk, and live monitoring readiness before paper trading or limited production deployment.
signal-flare
A 5-stage escalation framework for legitimate account holders whose recovery has failed through standard platform support — covering platform legal channels, state Attorneys General, the FTC, congressional offices, and attorney engagement. Use this skill when a user describes losing access to a social media or…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…