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-mining-articlesgit 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-mining-articles)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-mining-articles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-mining-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-mining-articles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-mining-articles.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 | $0.00113 | $0.03219 |
| Opus 5 | $0.00056 | $0.01610 |
| Sonnet 5 | $0.00023 | $0.00644 |
| Haiku 4.5 | $0.00011 | $0.00322 |
Grade A, and why
wjs-mining-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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wjs-mining-articles
一个视频的 SRT(独白或对谈)→ 一桌选题 → 用户勾几个(长对谈可「全要」)→ 每个长成一篇可发布的公众号文章,自动建好微信草稿,可选再排期发到 X。
Core Principle
口语是矿,文章是提炼出来的金属。 一段王建硕的独白里通常讲了好几个各自独立、各自值得成文的点;每个点单独成一篇,比硬塞成一篇长文更符合公众号「800–1000 字、一篇一个核心」的节奏。
字幕只是原料,成文要彻底书面化——去掉「呃、那个、就是说、然后」这类口头碎屑,把口语逻辑理成书面段落;但保留作者的用词偏好、家常比喻和语气,绝不改成营销腔或书面八股。
When This Skill Fires
- 用户给一个 SRT 路径,说「把这个视频写成文章」/「从字幕里挖文章」/「能写几篇」
- 用户跑
/wjs-mining-articles <srt-path>
支持两种源:独白/讲解(你一个人说)和对谈/访谈(你和别人对话)。两种走不同的识别路径(见 Step 1),但成文标准一致。
When NOT to use
- 没有 SRT,只有视频/音频——先用
wjs-transcribing-audio出 SRT,再回来 - 对谈里王建硕根本没怎么说话(纯主持、对方独角戏)——挖不出他第一人称的文章,别硬写
- 已有一篇成稿要发——直接用
wjs-publishing-wechat
Workflow
Step 1 · 读 SRT,判断源类型,识别选题
脚本在本 skill 目录下,从 skill 根目录跑(或写全 ~/.claude/skills/wjs-mining-articles/scripts/parse-srt.sh):
scripts/parse-srt.sh <srt-path> # 句子合并、每块前缀 [起–止] 时间区间
scripts/parse-srt.sh <srt-path> --raw # 一行一 cue: HH:MM:SS<TAB>text(需要细看时)
先判断这是独白还是对谈。 SRT 没有说话人标记,从内容判断:有一问一答、现场寒暄/调设备、「你/我」互相称呼、有人反驳——就是对谈;从头到尾一个人连续讲就是独白。文件名/目录名带别人名字(如「汤维维」)是强信号。
跳过非正片的口水段:录制前的寒暄、调麦克风、「咱们聊啥」「这是播客还是视频」,以及中途「我去个洗手间」「换点水」这类——都不是内容,识别选题时直接略过(这次那条对谈开头约 5 分钟、中间几处都是这种)。
ASR 人名几乎一定有错:逐字稿里的人名先存疑,派 agent 写之前跟用户核对(这次「黄一孟」被听成「黄一梦」)。
独白路径:读输出全文,识别出 N 个独立的、各自值得成文的话题(典型 2–6 个)。每块前的 [HH:MM:SS–HH:MM:SS] 区间拿来标选题时间段——话题跨多块时取第一块起到最后一块止。没有「几个才算独立」的死规则:看作者是否真的换了一个能独立成文的点(他常自己数「第一个/第二个」,顺着切)。
对谈路径(多两步,顺序不能省):
- 先确认谁是王建硕 ⟵ 不许猜,也不许默认主讲人/说得最多的人就是王建硕。把开头一段对话原样贴给用户,标出你推断的两个角色(谁在问、谁在答),用
AskUserQuestion让用户确认哪一方是王建硕。用户没确认前,不进入识别选题。 - 只挖王建硕真正展开了观点的话题。对谈里的选题 = 王建硕给出了成段的、能独立成文的看法之处;对方纯提问、纯背景、纯附和的地方不算选题。读上下文判断每个点是谁说的——拿不准某句是不是王建硕说的,就标「存疑」交给用户判,绝不替他认领。
- 选题清单照常出(Step 2),但每条额外标一句「这个点里王建硕的核心主张是 X」,方便用户判断值不值得写。
Step 2 · 出选题清单,等用户勾选 ⟵ 唯一的人工闸
每个候选给三样:拟定标题 / 一句话梳理这个话题在讲什么 / 对应 SRT 时间段(如 03:12–06:40)。对谈每条再加一句「这个点里王建硕的核心主张是 X」。
清单怎么呈现,按候选数分两种:
- ≤4 篇:用
AskUserQuestion(multiSelect: true),勾选框最干净。 - >4 篇(长对谈常见,一场 1–2 小时能挖 10–16 篇):
AskUserQuestion一题最多 4 个选项,塞不下。改用文字表格(序号 | 标题 | 核心主张 | 时间段),按「多强 + 多像王建硕招牌观点」排序、标出 ⭐ 推荐,让用户直接报序号(「1 3 4」/「先写 ⭐ 那几篇」/「全要」)。
What ships with it
1 file 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.
- 11d ago First seen · 136 lines · 113 tokens per session scan A cb7c89b2b12a
wjs-mining-articles is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 21d ago), licensed MIT. It adds 113 tokens to every session and 3,219 once invoked, about $0.0006 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.