Creator · jianshuo
Last updated · Sep 6, 2026
Use when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — and wants to mine it into multiple standalone 微信公众号 articles, one article per distinct topic. Triggers — "把这个视频写成文章", "从字幕里挖文章", "这个 SRT 能写几篇", "把对谈写成文章", "/w
Sandbox only
Install targets
Codex install prompt
Install the "wjs-mining-articles" agent skill from https://github.com/jianshuo/claude-skills/tree/main/wjs-mining-articles. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — and wants to mine it into multiple standalone 微信公众号 articles, one article per distinct topic. Triggers — "把这个视频写成文章", "从字幕里挖文章", "这个 SRT 能写几篇", "把对谈写成文章", "/wjs-mining-articles <srt>". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"jianshuo-wjs-mining-articles","task":"Install wjs-mining-articles","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
Scenario
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add jianshuo/claude-skills --skill wjs-mining-articles
Maintenance
fresh
18d since push
Risk
Needs review
SKILL.md references external skill paths (~/.claude/skills/wjs-publishing-wechat/) which may not exist on user's system
GitHub quality
129
67/100 Quality · 70/100 Trust
Coverage tags
Review notes
SKILL.md references external skill paths (~/.claude/skills/wjs-publishing-wechat/) which may not exist on user's system · No explicit validation that the user has the required companion skills installed (wjs-publishing-wechat, wjs-tweeting-from-articles)
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
PromisingUseful candidate, but compare it with alternatives before adopting.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
129 GitHub stars
Repo activity
129 stars, 20 forks
Maintenance
18d since push
License
MIT
Install
npx skills add jianshuo/claude-skills --skill wjs-mining-articles
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add jianshuo/claude-skills --skill wjs-mining-articlesDo not use when
Alternative
175.1K Stars
npx skills add anthropics/skills --skill frontend-design
Alternative
85.2K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
Alternative
1.8K Stars
npx skills add Alisa0808/vox-director --skill vox-director
Alternative
175.1K Stars
npx skills add anthropics/skills --skill canvas-design
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20wjs-mining-articles%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20wjs-mining-articles%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/jianshuo-wjs-mining-articles/install
Agent should check
Copy prompt
Task: Use wjs-mining-articles in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20wjs-mining-articles%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/jianshuo-wjs-mining-articles/install
Install command: npx skills add jianshuo/claude-skills --skill wjs-mining-articles
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/jianshuo-wjs-mining-articles/install
LLM text format
/api/skills/jianshuo-wjs-mining-articles/install?format=text
Find alternatives
/api/skills/search?q=wjs-mining-articles&limit=3
Agent prompt
Use wjs-mining-articles for this task. Review https://www.openagentskill.com/api/skills/jianshuo-wjs-mining-articles/install, then install with: npx skills add jianshuo/claude-skills --skill wjs-mining-articlesRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/jianshuo-wjs-mining-articles
LLM text
/api/registry/manifest/jianshuo-wjs-mining-articles?format=text
Install alias
/api/registry/install/jianshuo-wjs-mining-articles
Recommend
/api/registry/recommend?task=Use%20wjs-mining-articles%20in%20an%20agent%20workflow&limit=3
Agent fit
Document processing
Platforms
Claude Code, OpenAI Agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Document processing
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO129 GitHub stars
Stars/forks activity
CHECK129 stars, 20 forks; issue activity unavailable in current metadata
Recent maintenance
PASS18d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Useful candidate, but compare it with alternatives before adopting.
Workflow fit
Parse messy files
I need my agent to read PDFs, extract tables, and turn documents into structured data.
Investigate faster
I need my agent to research a topic, compare sources, and produce a concise report.
Automate repeated work
I need my agent to automate a repeated workflow across tools and files.
Workflow fit
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Design, build, test, and ship interfaces
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Alternative shortlist
Similar skills that may fit this task.
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
--- name: wjs-mining-articles description: Use when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — and wants to mine it into multiple standalone 微信公众号 articles, one article per distinct topic. Triggers — "把这个视频写成文章", "从字幕里挖文章", "这个 SRT 能写几篇", "把对谈写成文章", "/wjs-mining-articles <srt>". ---
# 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`):
```bash 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):
1. **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。 2. **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**。 3. 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」)。
只有选中的进入 Step 3。用户说「全要」就全写。
### Step 3 · 每个选中话题写成 article.md + meta.json
写正文前载入 `wangjianshuo-perspective` 保证语气是本人。按 **`wjs-publishing-wechat` 的硬约束**写(那是单一事实源,这里只复述要点):
- 默认 **800–1000 字**,超 1200 回去再砍 - **红色加粗 `**...**` 2–4 处**,打在点睛句/关键结论/核心概念词。一处都没有 = 没写完 - **不加 AI 连接词**(首先/其次/综上所述/值得注意的是)、不加 emoji、不把口语强行八股化 - 默认不写 `## 后注`,正文最后落点收束
写完每篇 article.md 后,**跑一遍盘古之白**(中英文之间补空格,机械活、不靠自己记):
```bash python3 ~/.claude/skills/wjs-publishing-wechat/scripts/pangu.py <folder>/article.md # 幂等 ```
**对谈成文额外规则(归属红线)**:文章是**王建硕第一人称**,主体是他的观点和思考。对方(如汤维维)的话**只作引子/背景**——「有人问我…」「聊到 X 的时候」——绝不把对方的独到观点写成王建硕自己的主张。对方提了一个王建硕没正面回应的点,就别写进这篇。`source.srt.md` 里要注明本篇基于对谈、对方是谁、引用了对方哪几句作引子。
**选中很多篇时(长对谈)用并行 agent 批量写**:每个 agent 载入 `wangjianshuo-perspective`、拿到对应的逐字稿行区间和上面全部硬约束,各写 2–3 篇,落 `article.md`+`meta.json`+`source.srt.md`。一条 1–2 小时的对谈一次写 10+ 篇,串行太慢,并行又快又互不干扰(每篇独立)。**派 agent 前先把全片通读一遍、把归属和事实更正都定下来**(比如这次「黄一孟」被 ASR 听成「黄一梦」,得在派单时就写明),否则每个 agent 各猜一遍容易出错。
每篇落到一个**新文件夹** `<workspace>/articles/YYYY-MM-DD-{slug}/`,写两个文件:
| 文件 | 内容 | |---|---| | `article.md` | 正文 | | `meta.json` | `{ "title", "summary", "author": "王建硕", "date", "slug" }` — 三个复用脚本都靠它 | | `source.srt.md` | 原料备份:SRT 来源路径 + 本篇对应时间段 + 抽出的原始口语片段(可追溯) |
`<workspace>` 默认 `~/Library/Mobile Documents/com~apple~CloudDocs/my/我的项目/我的创作/wechat-publish/`,与 publishing 一致。
### Step 4 · 直接建草稿(全自动)
对每个选中文件夹依次调 publishing 的**现成脚本**(不重写),路径 `~/.claude/skills/wjs-publishing-wechat/scripts/`:
```bash gen-cover-ai.sh <folder> # 题图 cover.png(读 meta.json 的 title 当目标字词) gen-illustration.sh <folder> # 解释图 illustration.png + 确保 article.md 引用  upload-draft.sh <folder> # 上传到微信后台建草稿(只建草稿,不群发) ```
交付:每篇都是「微信后台已有草稿、可一键发布」状态。**群发由用户在后台手动点**——本 skill 到草稿为止。
**配图/建草稿是重活,长对谈十几篇要跑很久**:gen-cover / gen-illustration 都走 codex 出图,每篇约 1–3 分钟。串成一个后台批处理脚本一次跑完(逐篇记成功/失败、出错不影响其他篇),别一篇篇手动等。脚本里给 gen-cover / gen-illustration 加「图已存在就跳过」,这样中途失败重跑不浪费已生成的图。
### Step 5 · (可选)排期发到 X
用户要把这些文章也发成 tweet 时,交给 `wjs-tweeting-from-articles`:
- 发 1 条 → 它的默认流程(挑一篇、起 A/B/C 候选、用户选、`xurl` 发)。 - **一次要发很多篇**(长对谈挖出的十几篇)→ 它的**批量排期模式**:每篇抠一条 ≤120 字的 tweet 排进队列,`post-next-from-queue.sh` + 每小时 cron(脚本自己节流)按「每 N 小时一条」自动发,避免一次连发被 X 判刷屏。详见该 skill。
## 复用边界
| 复用 | 用法 | |---|---| | `wjs-publishing-wechat` 三个脚本 | 题图/解释图/建草稿,直接调,不重写 | | `wjs-publishing-wechat` 字数/加粗/无 AI 味规则 | 单一事实源,本 skill 不另立标准 | | `wjs-publishing-wechat/scripts/pangu.py` | 盘古之白,每篇 article.md 写完跑一遍 | | `wangjianshuo-perspective` | 写正文时载入,保语气 | | `wjs-tweeting-from-articles` | (可选)Step 5 把文章排期发到 X |
**本 skill 唯一新增代码**:`scripts/parse-srt.sh`。
## Common Mistakes
- **把多个话题硬塞成一篇长文** —— 违背「一篇一个核心」。识别出几个独立话题就出几个候选,让用户挑 - **照搬口语,留着「呃/然后/就是说」** —— 字幕是原料不是成稿,必须彻底书面化 - **忘了写 `meta.json`** —— 三个复用脚本全靠它,缺了题图和草稿都建不出来 - **忘了红色加粗** —— 一处都没有就是没写完 - **自动跑去群发** —— 本 skill 只建草稿,真正发布是用户的手动决定 - **对谈里默认「说得最多的就是王建硕」** —— 大错。必须让用户确认身份;说不定主讲人是嘉宾,王建硕才是提问的一方 - **把对方的观点写成王建硕的主张** —— 归属红线。对方的话只能作引子,拿不准是谁说的就标存疑
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for wjs-mining-articles, ready for a manual X post.
A practical pick for design or creative work: wjs-mining-articles: Use when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — a... 129 stars https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles?ref=x
Listing + install path for wjs-mining-articles: https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles?ref=x Install: npx skills add jianshuo/claude-skills --skill wjs-mining-articles
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to jianshuo but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles/audit)
[](https://www.openagentskill.com/skills/jianshuo-wjs-mining-articles?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)jianshuo
@jianshuo
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
175.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
85.2K StarsVox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
1.8K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
175.1K StarsPermission surface
shell or command execution, filesystem or document access
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Install readiness