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 jianshuo/claude-skills --skill wjs-polishing-x-engagementgit clone --depth 1 https://github.com/jianshuo/claude-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/jianshuo/claude-skills/wjs-polishing-x-engagement)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-polishing-x-engagement"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-polishing-x-engagement/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/jianshuo/claude-skills/wjs-polishing-x-engagement"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-polishing-x-engagement.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 | $0.00175 | $0.02058 |
| Opus 5 | $0.00088 | $0.01029 |
| Sonnet 5 | $0.00035 | $0.00412 |
| Haiku 4.5 | $0.00017 | $0.00206 |
Grade A, and why
wjs-polishing-x-engagement 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tweet Engagement Polish(中文推文互动化改写)
把一句平淡的话,变成读者忍不住接话的一条推文。两件事叠在一起就行:一个真事实(可信、有料)+ 一个钩子(留个缺口让人补)。
风格铁律:短、白、日常 ⚠️ 最重要
这是最容易翻车的地方,优先级最高:
- 越短越好。 一条推文最好一两句读完,能删的字一律删。长 = 劝退。
- 说人话。 日常口语,像微信里跟朋友讲话。不用书面腔、文艺腔,不堆形容词。
- 不煽情、不上价值、不排比。 别"走心""恍如隔世""那一下的心跳"这种文青腔。平淡日常的事就平淡地说。
- 钩子直给。 想问就直接问,别绕弯子铺垫。
正反对照(同一条虹桥怀旧帖):
- ❌ 太文青:「变的是机场,没变的是走出航站楼那一下的心跳。」
- ✅ 短而白:「那会儿这还是上海唯一的机场,浦东 1999 年才开。你第一次坐飞机去哪儿?」
工作流程
第 1 步:抓核心
原文到底想说什么?找出那个可以被一个真事实坐实的点(一个观点、一种感受、一个人/事/地)。
第 2 步:联网查一个真事实 ⚠️ 必做
整条推文的可信度全靠这个事实是真的。
- 用
web_search查一个具体到能核实的事实:确切年份/数字/人名/地名、"第一/最后/唯一"、纪录、反常识的真相。 - 优先挑反常识或大家"似懂非懂"的——最容易勾起"我知道!"或"真的假的?"。
- 绝不编造、不夸大、不张冠李戴。 查不到就换角度,或直说"没查到可靠事实"。宁可换角度,也别拿假事实当钩子——那是造谣、毁号。
- 数字、年份、人名落笔前再核一遍。
第 3 步:套不同钩子,写 2-3 个版本
同一个真事实,写 2-3 个钩子不同的版本(换的是参与方式,不是换语气)。每版都遵守上面的风格铁律。钩子类型:
- 历史规律外推钩(最强):用 2 个以上真事实摆出一条暗规律,外推到当下,结论留空让人猜。例:"存储便宜,出了 Gmail;带宽便宜,出了 YouTube。智能便宜,会出什么?"
- 提问钩:抛一个人人都有答案、零成本就能甩一句的问题。例:"你第一次坐飞机去哪儿?"
- 填空钩:挖空一个"答案就在嘴边"的词/数字让人补(挖空的必须是真正确的)。例:"贝多芬写《第九》时已经完全 ___ 了。"
- 反常识钩:先甩一个反直觉的真相,引人反驳或验证。例:"以为 X,其实是 Y。"
- 二选一/站队钩:给两个选项让人选边,比开放回答门槛更低。例:"A 还是 B?报个数。"
不要每版都用同一种钩子;别牺牲原意(是给原话加可信度和钩子,不是换话题)。
输出格式
【版本 1 · 提问钩】
<推文正文>
↳ 钩子:一句话说明为什么勾人
【版本 2 · 填空钩】
<推文正文>
↳ 钩子:……
末尾附一行事实来源,方便用户核实。
第 4 步:配图提示(有就提,没有就跳过)
带图传播力更强,史实型推文往往正好有经典照片/对照图。产出后判断有没有现成的、画面感强的图(老照片、前后对照、数据图);有就用 image_search 找出来给用户,并提醒优先用公共领域来源(国会图书馆、国家档案馆、Wikimedia)、附上出处。没有合适的就别硬凑。
标杆示例
一条真实爆款,也是本 skill 的风格范本(短、白、有事实、有缺口):
存储便宜,出了 Gmail;带宽便宜,出了 YouTube。智能便宜,会出什么?
为什么爆:两个真事实(Gmail 2004 年 1GB、约 100 倍于竞品;YouTube 2005 年)摆出"成本暴跌→催生时代级产品"的规律,再把结论留空,读者忍不住接话、还能借预测显见识。全程没有一句多余的形容词。
改写示例
原文(观点型): AI 越来越便宜了,以后肯定会冒出很厉害的新产品。
【版本 1 · 历史规律外推钩】
存储便宜,出了 Gmail;带宽便宜,出了 YouTube。
智能便宜,会出什么?
↳ 钩子:真事实摆规律 + 结论留空,接话门槛极低。
【版本 2 · 反常识钩】
Gmail、YouTube 不是靠想法赢的,是踩中了成本暴跌。
这轮暴跌的是"智能",下一个 Gmail 你押谁?
↳ 钩子:打破"靠创意取胜"的直觉 + 站队式开放问题。
事实来源:Gmail 2004/4/1 上线、1GB 免费存储(约竞品 100 倍);YouTube 2005 年创立、当年 12 月上线。(发前用 web_search 复核)
原文(日常型): 忽然感觉刚出虹桥机场,如同 30 年前第一次坐飞机来虹桥。
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 · 121 lines · 175 tokens per session scan A f3f08c73d449
wjs-polishing-x-engagement is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 175 tokens to every session and 2,058 once invoked, about $0.0009 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.