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-five-piece-checklistgit 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-five-piece-checklist)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-five-piece-checklist"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-five-piece-checklist/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-five-piece-checklist"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-five-piece-checklist.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 | $0.00203 | $0.03020 |
| Opus 5 | $0.00102 | $0.01510 |
| Sonnet 5 | $0.00041 | $0.00604 |
| Haiku 4.5 | $0.00020 | $0.00302 |
Grade A, and why
x-five-piece-checklist 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
五件套检查清单 — 内容完备性 + 证据标准
R — 原文 (Reading)
"一条强X内容往往像一个小型信息产品:①第一眼能看懂的价值承诺——这和我有什么关系;②一个具体使用场景——我什么时候会用到;③降低门槛的步骤、入口或解释——我现在能不能开始;④截图、数字、案例这样的证据——我凭什么相信;⑤一个值得收藏或转发的理由——我为什么要留着它。"证据须满足"三个可":可见(截图/录屏)、可点(链接/工具名)、可算(数字/成本/步骤)。带"地址见评论"进前10%概率约40%。
— 向阳乔木, X爆款秘籍分享 · 五件套检查清单 / 三个可
I — 方法论骨架 (Interpretation)
把一条推文当"小型信息产品"做发布前自检。五件套是五个读者决策点,每件回答一个问题:
- 价值承诺 → "这和我有什么关系?" — 第一眼能看懂能拿走什么,不是标题党而是价值预览
- 使用场景 → "我什么时候会用到?" — 具体场景而非抽象功能描述
- 低门槛入口 → "我现在能不能开始?" — 步骤/链接/搜索路径,降低行动成本
- 证据(三个可) → "我凭什么相信?" — 可见(截图/录屏/对比图)、可点(链接/工具名/搜索路径)、可算(数字/时间/成本/步骤),至少满足一个;数据表明带"地址见评论"进前10%概率约40%,带资源词约35%,带"免费/简单"低门槛信号约30%
- 收藏理由 → "我为什么要留着它?" — 读者未来还会用到才会收藏,收藏>点赞是信任信号
核心洞察:五件套是检查工具不是写作模板 — 先写完初稿,再逐件查缺哪补哪。缺任一件不是"少了一点",而是读者在该决策环节直接流失。
A1 — 书中的应用 (Past Application)
案例 1: 飞书博物馆文档帖 (26.3 万浏览)
- 问题: 如何让一个资源分享帖获得高传播
- 方法论的使用: 逐件对照——价值承诺="全球博物馆155万份藏品整理进飞书,直接可用入口"(第一眼看懂);场景=查博物馆藏品;入口="网址见评论区"(地址见评论→进前10%概率约40%);证据=155万份(可算)+"直接可用"(可点);收藏理由=未来查藏品要用
- 结论: 五件齐全,尤其第4件满足"可算+可点",第3件用"地址见评论"降低门槛
- 结果: 26.3 万浏览,资源入口型中位互动 2965 的代表案例
案例 2: Claude Code 爬虫抓取 Paul Graham 文章帖 (171 万浏览,最高)
- 问题: 如何演示 AI 工具能力同时获得最高传播
- 方法论的使用: 逐件对照——价值承诺="提示词抓取 PG 所有文章做成 epub";场景=想把作者全集合做成电子书;入口=提示词直接给出(可复制);证据=三个可全满足(可见=结果截图,可点=提示词可复制,可算="4 分钟"时间数字);收藏理由=提示词可反复用
- 结论: 五件齐全且第4件"三个可"全满足,是全部案例中曝光最高的
- 结果: 171 万浏览,400 转发,2293 收藏
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 初稿写完、发布前做完备性检查 — "帮我看看这条推文还缺什么"
- 纠结"这条推文发出去会有人收藏吗" — 需要逐件查哪件缺导致不收藏
- 帖子已写好但感觉"差点什么",说不清缺什么 — 需要结构化检查工具定位
- 想确认证据是否够强 — 需要用"三个可"检验证据质量
语言信号 (用户的话里出现这些就应激活)
- "帮我检查这条推文还缺什么" / "checklist for tweet"
- "这条推文发出去会有人收藏吗" / "worth saving"
- "这条内容够不够完整" / "is this tweet complete"
- "证据够不够" / "need more evidence" / "三个可"
- "五件套" / "five-piece checklist"
与相邻 skill 的区分
- 与
x-four-saves(四省模型) 的区别: 四省模型是估值工具——"值不值得发"(帮读者省几步路);五件套是检查工具——"发之前查缺补漏"(五件是否齐全)。先用四省估值决定发,再用五件套查完备性。若用户还在纠结"值不值得发",应触发四省而非五件套。 - 与
x-short-content-craft(短内容工艺) 的区别: 短内容工艺是起草工具——"怎么写"(选类型 + Hook-Body-CTA);五件套是检查工具——"起草完检查"(五件是否齐全)。若用户还没写初稿,应触发短内容工艺而非五件套。 - 与
x-three-translations(三次翻译) 的区别: 三次翻译是改写工具——把公告式语言翻译成读者语言;五件套第4件(证据)是三次翻译第3次(结论→证据)的检验标准。若用户的问题是"怎么把公告改成帮助式表达",应触发三次翻译。
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 · 149 lines · 203 tokens per session scan A f47167fed95f
x-five-piece-checklist is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 203 tokens to every session and 3,020 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
credibility-evidence-selector
Pick the strongest credibility evidence for a claim and kill weak evidence chains with the Sinatra Test. Use this skill whenever the user asks 'how do I prove this?', 'how do I make this more credible?', 'which statistic should I cite?', 'do I need a source for this?', 'how do I build trust?', 'this claim sounds…
mira-annotation-review
Review MIRA annotations in Markdown documents for semantic correctness, Markdown dialect validity, preservation, and relation integrity. Use for md, smd, qmd, and myst files containing research objects such as claims, evidence, questions, protocols, requests, typed claims, ids, and relations. Produces actionable…
Release Checklist
Check release readiness and record a release note. Use for release and rollback requests.
contract
Outcome-driven Cortex function development — declares a behavioral contract before generation begins, enforces evidence-tiered proof before $ship, and defends against the self-oracle evaluation failure mode.
humble-header-analyst
Expert-level parsing and remediation of 'humble' HTTP security header reports. Use this skill whenever the user provides a report generated by 'humble' (https://github.com/rfc-st/humble), mentions analyzing HTTP response headers, security header grades (A-E), or asks for remediation of findings such as missing…
improve-rule
Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.