Agent skill · AI & Agents

wjs-voicedrop-choosing-cover

Use when 王建硕 wants to decide whether a VoiceDrop article should get an AI 题图 (公众号封面), and which style of image prompt to use — before generating any cover. Triggers — "这篇要不要配题图", "选个题图风格", "给这篇出个题图 prompt", "choosing cover", "/wjs-voicedrop-choosing-cover".

jianshuo112★ · 1 repos on radarProfile →
claude-codecodexMIT
Install
npx skills add jianshuo/claude-skills --skill wjs-voicedrop-choosing-cover --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 2 KB
Bundled scripts: none
Path: wjs-voicedrop-choosing-cover/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# wjs-voicedrop-choosing-cover 给一篇 VoiceDrop 文章做两个决定：**配不配题图**，以及**用哪种风格的 prompt 生成**。核心原则：真素材优先于 AI 画；风格跟着文章气质走，绝不一招鲜。 ## 输入 三种都接受：VoiceDrop 文章（MCP `read_article`，按标题或 ID）/ 本地 markdown / 直接粘贴的正文。`[[photo:KEY]]` 是文中已插入的用户实拍照片。 ## Step 1：配不配（先于一切风格讨论） | 情形 | 判断 | |------|------| | 文中已有实拍照片且与主题相关 | **不配**。首图即封面（真照片 > AI 画，AI 封面会把实拍正文的诚恳感冲掉）。指出用哪张 `[[photo:KEY]]`。 | | 无照片，会发布 / 分享 | **配** | | 无照片，极短碎碎念（<100 字） | 先问「这篇要单独发吗」；发才配 | | 实拍照片存在但与主题无关（截图、票据） | 视同无照片，配 | ## Step 2：风格选择（必须过这张表，禁止默认某一种） | 文章气质 | 风格 | 基调 | |----------|------|------| | 思辨 / 观点 / 方法论 | 极简概念图 | 一个具体物件当隐喻，大留白 | | 生活随笔 / 自然 / 散步 | 水彩淡彩 | 轻、透、浅色底 | | 怀旧 / 回忆 / 家人 | 胶片 / 油画 | 暖调、颗粒感 | | 科技 / 工具 / AI / 教程 | 编辑部封面 | 具体物件（卡片、面板、画布），忌泛泛机器人 | | 幽默 / 自嘲 | 卡通轻插画 | 松弛，不闹腾 | | 哀伤 / 悼念 / 疾病 | 素描或极淡水彩 | 低饱和、克制，不画人脸，**绝不卡通 / 广告风** | 拿不准气质时读全文再判，不按标题猜。 ## Step 3：拼 prompt（硬规格） - **比例 2.45:1，尺寸 1568x640**（VoiceDrop 题图规格；本地 wjs-publishing-wechat 线是 900×383，别抄混） - 题图主标题从文章标题提炼 **6–10 个汉字**（极简概念图可用 1–4 字大字），必须清晰可读 - 构图：大标题在上，主视觉在下，文字左右撑满 - 配色随主题变，默认浅色底；同一批文章不许撞色撞构图 - 避免清单（写进 prompt）：乱码文字、过多小字、真实品牌 logo、纯氛围壁纸、厚重蓝紫渐变、廉价营销海报感 ## Step 4：出图（用户要求时才做） `gpt-image-2-skill` 走 `--provider codex`，`--size 1568x640`；或在 VoiceDrop 内把 prompt 交给 `new_pho

What's inside
Steps it walks through
  1. 输入
  2. Step 1：配不配（先于一切风格讨论）
  3. Step 2：风格选择（必须过这张表，禁止默认某一种）
  4. Step 3：拼 prompt（硬规格）
  5. Step 4：出图（用户要求时才做）
  6. 输出契约（每篇固定这四行）
  7. Red Flags
More from claude-skills
All skills →
wangjianshuo-perspective王建硕的思维框架与表达方式。基于 7 份深度调研（约 100 万词英文博客 + 约 109 万字中文博客， 2002–2022，全部一手）提炼出 7 个核心心智模型、10…Otherwjs-dubbing-videoUse when the user has a video + a target-language SRT and wants the video to actually speak that…Media & Videowjs-cleaning-spamUse when the user complains about spam on his X/Twitter posts — 同城面付 / 寻固炮 / 线下上门 / 免费破处…Otherwjs-converting-wp-to-hugoUse when migrating a WordPress site to a Hugo static site on GitHub Pages from a WXR export (.xml)…Content & Marketingwjs-burning-subtitlesUse when the user has a video + an SRT and wants the subtitles either burned into the pixels…Media & Videowjs-looping-feedbackUse when the user wants to add an in-site feedback loop to a website repo — a floating "提个建议"…Data & Analytics
About this skill
What does the wjs-voicedrop-choosing-cover skill do?

Use when 王建硕 wants to decide whether a VoiceDrop article should get an AI 题图 (公众号封面), and which style of image prompt to use — before generating any cover. Triggers — "这篇要不要配题图", "选个题图风格", "给这篇出个题图 prompt", "choosing cover", "/wjs-voicedrop-choosing-cover".

How do I install it?

Run `npx skills add jianshuo/claude-skills --skill wjs-voicedrop-choosing-cover --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From jianshuo/claude-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.