Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jianshuo/claude-skillsnpx agentmods add skills/jianshuo/claude-skills/wjs-tweeting-from-articlesWrote 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-tweeting-from-articles)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-tweeting-from-articles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-tweeting-from-articles/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-tweeting-from-articles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-tweeting-from-articles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 134 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00106 | $0.02356 |
| Opus 5 | $0.00053 | $0.01178 |
| Sonnet 5 | $0.00021 | $0.00471 |
| Haiku 4.5 | $0.00011 | $0.00236 |
Grade A, and why
wjs-tweeting-from-articles 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wjs-tweeting-from-articles
每天一条 X tweet，灵感直接从最近发的公众号文章里抠。文章是源头，tweet 是更短的萃取。
Core Principle
文章已经过了一轮王建硕式的精炼，tweet 只是再短一格的版本。 不要重新构思——从 article.md 里直接抠最 quotable 的一句 / 一段，按 X 的节奏切。
一天最多一条，一篇文章只推一次。 状态文件 state/history.jsonl 记录哪些 article 已经推过；不重复。（例外:批量排期模式——一次把多篇排进队列、按每 N 小时一条自动发,见下文。）
真发，不暂存。 用户确认后立刻 xurl POST。失败原文 dump 给用户重试。
When This Skill Fires
- 用户说「今天的 tweet」/「发一条 X」/「从文章里发推」
- 用户跑
/wjs-tweeting-from-articles - 用户设了
/schedule daily /wjs-tweeting-from-articles之后每天自动调
When NOT to use
- 用户要发的内容和最近的公众号文章无关——直接
xurl POST /2/tweets即可 - 用户要发的是产品 / skill 推广——用
/publish-skill或/wjs-promoting-skills
Workflow
Step 1: 挑今天要推的文章
scripts/pick-next-article.sh
输出最新一篇还没推过的文章的 folder 路径（最近一周内，按日期倒序找第一个未推的）。已经全推完 → 退出 0、空输出，告诉用户「最近 7 天的文章都推过了，今天 rest day」。
如果用户想推特定那一篇：跳过此脚本，直接用 <folder>。
Step 2: 读文章 + 草拟 3 条 tweet 候选
读 <folder>/article.md，按下面三个角度各起草一条：
| 角度 | 选材 | 例子 |
|---|---|---|
| A · 金句 | 从文中挑一句最 quotable 的，可以加一句铺垫 | "笔头钝了，写不出锋——蘸点墨，在砚台上转两圈，重新有了尖。" |
| B · 比喻 | 文章的核心比喻 + 一句把比喻落到读者头上 | "写 prompt 跟画画一样，是手感活儿。每天都得写点。" |
| C · 反差 | 「不是 X，是 Y」式的认知翻转 | "不是变聪明，是手感来了。" |
长度硬约束：tweet ≤ 280 字符（X 限制；中文每字算 2）——所以中文 tweet 实际 ≤ 140 字。留 buffer 到 120 字以内比较稳。
风格：保留王建硕语气——平实、家常比喻、不写营销腔。不要加 hashtags、不要加 @、不要加 emoji（除非原文有）。不要加 mp.weixin 链接（默认）；如果用户问要不要带链接，提示可以 reply 里附。
Step 3: 让用户挑一条
用 AskUserQuestion 给出 A/B/C 三条候选 + 「四选其他」。用户选一条之后进入 Step 4。
Step 4: 真发 X
TWEET_TEXT='<picked text>'
JSON=$(jq -nc --arg text "$TWEET_TEXT" '{text:$text}')
resp=$(xurl -X POST -d "$JSON" /2/tweets)
# Don't use `jq -r '.data.id'` here — X API returns raw newlines in the echoed
# `text` field, which strict jq rejects with "control characters must be escaped".
# Grep the id directly instead.
TWEET_ID=$(printf '%s' "$resp" | grep -oE '"id":"[0-9]+"' | head -1 | sed -E 's/.*"([0-9]+)".*/\1/')
[[ -n "$TWEET_ID" ]] || { echo "POST failed: $resp"; exit 1; }
echo "https://x.com/jianshuo/status/$TWEET_ID"
What ships with it
9 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.
- com.jianshuo.wjs-tweeting-from-articles.plist.template 1.0 KB
- daily.sh 6.0 KB runs code
- scripts/mirror-articles.py 2.1 KB runs code
- scripts/pick-next-article.sh 2.7 KB runs code
- scripts/pick-next-article.sh.bak.1779689674 1.7 KB
- setup.sh 2.4 KB runs code
- state/.gitignore 8 B
- state/queue-2026-05-24.tsv 4.4 KB
- uninstall.sh 510 B runs code
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 · 166 lines · 106 tokens per session scan A 5d9e36de8a81
wjs-tweeting-from-articles is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 22d ago), licensed MIT. It adds 106 tokens to every session and 2,356 once invoked, about $0.0005 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.