linkedin-post-generator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

LinkedIn Post Generator

LinkedIn 帖子生成器

Generate LinkedIn posts from shared source material, written in each user's personal style.

根据共享素材生成LinkedIn帖子，且帖子风格匹配每位用户的个人写作风格。

How It Works

工作原理

Personal style profile — stored locally at
```
~/.config/casper/linkedin-style.md
```
(never committed)
Source config — stored locally at
```
~/.config/casper/linkedin-sources.md
```
(never committed)
Shared source material — meeting transcripts, Slack dumps, docs in
```
source-material/
```
Prompt template — extraction rules, voice guidelines, few-shot examples in
```
references/prompt-template.md
```

个人风格配置文件 — 本地存储于
```
~/.config/casper/linkedin-style.md
```
（不会被提交）
素材配置文件 — 本地存储于
```
~/.config/casper/linkedin-sources.md
```
（不会被提交）
共享素材 — 会议记录、Slack内容导出文件、
```
source-material/
```
目录下的文档
提示词模板 — 提取规则、语气指南、少样本示例位于
```
references/prompt-template.md
```

First Run: Style Setup

首次运行：风格设置

Check if

~/.config/casper/linkedin-style.md

exists.

If it does NOT exist, run the style setup flow:

Say: "Welcome to the LinkedIn Post Generator! Before we start, I need to understand your writing style."
Say: "Share 3 LinkedIn posts that match the style you want. You can either paste the post links (e.g.
```
https://linkedin.com/posts/...
```
) or paste the text directly."
Wait for the user to provide 3 posts
If the user provides LinkedIn URLs, fetch the post content using the apify-scrapers skill:
bash
```
python ${CLAUDE_PLUGIN_ROOT}/skills/apify-scrapers/scripts/scrape_linkedin_posts.py search "{url}" --max-posts 1
```
Extract the post text from the JSON output. If a URL fails to fetch, ask the user to paste that post's text instead.
Analyze the posts for: tone, sentence length, vocabulary, formatting habits, hook style, CTA style, use of questions, paragraph length, overall energy
Create
```
~/.config/casper/
```
directory if it doesn't exist
Save the analysis to
```
~/.config/casper/linkedin-style.md
```
using this format:

markdown

undefined

检查

~/.config/casper/linkedin-style.md

是否存在。

若不存在，运行风格设置流程：

提示："欢迎使用LinkedIn帖子生成器！开始之前，我需要了解你的写作风格。"
提示："请分享3篇符合你期望风格的LinkedIn帖子。你可以粘贴帖子链接（例如
```
https://linkedin.com/posts/...
```
）或直接粘贴帖子文本。"
等待用户提供3篇帖子
若用户提供LinkedIn链接，使用apify-scrapers技能获取帖子内容：
bash
```
python ${CLAUDE_PLUGIN_ROOT}/skills/apify-scrapers/scripts/scrape_linkedin_posts.py search "{url}" --max-posts 1
```
从JSON输出中提取帖子文本。若链接获取失败，请用户直接粘贴该帖子的文本。
分析帖子的以下维度：语气、句子长度、词汇、格式习惯、开头钩子风格、结尾CTA风格、提问使用情况、段落长度、整体活力
若
```
~/.config/casper/
```
目录不存在则创建
将分析结果保存至
```
~/.config/casper/linkedin-style.md
```
，格式如下：

markdown

undefined

LinkedIn Style Profile

LinkedIn 风格配置文件

Generated: [date]

生成日期：[日期]

Tone

语气

[analysis]

[分析内容]

Structure Patterns

结构模式

[paragraph length, line breaks, formatting habits]

[段落长度、换行、格式习惯]

Hook Style

开头钩子风格

[how they open posts]

[帖子开头方式]

CTA / Closing Style

CTA/结尾风格

[how they end posts — questions, challenges, etc.]

[帖子结尾方式 — 提问、挑战等]

Vocabulary & Phrases

词汇与短语

[distinctive phrases, word choices, energy level]

[独特短语、词汇选择、活力水平]

Sample Posts

示例帖子

[the 3 original posts, for reference]


8. Confirm: "Got it! Your style profile is saved. You can update it anytime with `/casper:generate-linkedin-post --setup`"

[3篇原始帖子，用于参考]


8. 确认提示："已完成！你的风格配置文件已保存。随时可以通过 `/casper:generate-linkedin-post --setup` 更新配置。"

First Run: Source Material Check

首次运行：素材检查

After style setup completes (or if style exists but source-material/ is empty), check for source material:

Check if
```
source-material/
```
contains any
```
.md
```
files besides
```
README.md
```
If empty, guide the user:
- Say: "You don't have any source material yet. I need content to generate posts from — meeting transcripts, notes, Slack conversations, etc."
- Present options:
  - "Connect integrations" — run the
```
--setup-sources
```
    flow to configure Fireflies, Slack, or Google Drive auto-pulling
  - "Paste something manually" — run the
```
--add-source
```
    flow to let the user paste a transcript, notes, or other content
- Wait for user choice and proceed with the selected flow
If source material exists, proceed with generation

风格设置完成后（或风格配置存在但source-material/为空时），检查素材情况：

检查
```
source-material/
```
目录下是否包含除
```
README.md
```
外的其他
```
.md
```
文件
若为空，引导用户：
- 提示："你目前没有任何素材。我需要内容来生成帖子 — 比如会议记录、笔记、Slack对话等。"
- 提供选项：
  - 「连接集成工具」 — 运行
```
--setup-sources
```
    流程配置Fireflies、Slack或Google Drive自动拉取
  - 「手动粘贴内容」 — 运行
```
--add-source
```
    流程让用户粘贴记录、笔记或其他内容
- 等待用户选择并执行对应流程
若素材存在，继续生成流程

Normal Run: Post Generation

常规运行：帖子生成

If style config exists and source material is available, proceed with generation:

Read
```
~/.config/casper/linkedin-style.md
```

Read ALL files in

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/

(excluding README.md)

Read

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/references/prompt-template.md

Apply the confidentiality rules from the prompt template (no financials, no client names, no pipeline, no team member names)
Generate 2-4 post options based on the source material, written in the user's personal style
Present them in a clean, copy-paste-ready format

当风格配置存在且素材可用时，执行生成流程：

读取
```
~/.config/casper/linkedin-style.md
```

读取

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/

目录下的所有文件（排除README.md）

读取

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/references/prompt-template.md

应用提示词模板中的保密规则（不得包含财务信息、客户名称、业务管线、团队成员姓名）
根据素材生成2-4个符合用户个人风格的帖子选项
以简洁、可直接复制粘贴的格式展示

Flags

命令标志

Flag	Behavior
(none)	Normal generation flow
`--setup`	Re-run style setup, overwrite existing config
`--setup-sources`	Configure which Fireflies, Slack, and Drive sources to pull from
`--refresh`	Pull fresh source material from configured integrations, then generate
`--view-style`	Read and display `~/.config/casper/linkedin-style.md`
`--view-sources`	List and summarize all files in `source-material/`
`--add-source`	Prompt user to paste new content, save as new `.md` file in `source-material/`

标志	行为
无	常规生成流程
`--setup`	重新运行风格设置，覆盖现有配置
`--setup-sources`	配置要从中拉取素材的Fireflies、Slack和Drive源
`--refresh`	从已配置的集成工具拉取最新素材，然后生成帖子
`--view-style`	读取并展示 `~/.config/casper/linkedin-style.md`
`--view-sources`	列出并总结source-material/目录下的所有文件
`--add-source`	提示用户粘贴新内容，保存为source-material/目录下的新 `.md` 文件

Flag Details

标志详情

--setup-sources

--setup-sources

Interactive setup for automatic source pulling. Read

references/source-integrations.md

for full details.

Ask: "What's your work email address? This is used to filter transcripts to only meetings you attended."
- Save as
```
user_email
```
  in the config
Ask: "Which sources do you want to connect?" Present options:
- Fireflies.ai — pulls meeting transcripts (needs
```
FIREFLIES_API_KEY
```
  env var)
- Slack — pulls messages from channels (needs
```
SLACK_BOT_TOKEN
```
  env var)
- Google Drive — pulls docs and transcripts (needs OAuth setup via google-workspace skill)
For each selected source, check if the required env var / credentials exist. If missing, provide setup instructions:
- Fireflies: "Set
```
FIREFLIES_API_KEY
```
  in your environment. Get your API key from https://app.fireflies.ai/api"
- Slack: "Set
```
SLACK_BOT_TOKEN
```
  in your environment. Create a Slack app at https://api.slack.com/apps"
- Google Drive: "Run the google-workspace skill setup to configure OAuth."
For each enabled source, gather configuration:
- Fireflies: search terms (or leave empty for all recent) and days_back
- Slack: which channels to pull from — list available channels if possible, otherwise ask the user
- Google Drive: search terms, days_back
Save to
```
~/.config/casper/linkedin-sources.md
```
Confirm: "Source config saved. Run
```
/casper:generate-linkedin-post --refresh
```
to pull fresh content."

自动拉取素材的交互式设置。完整细节请参考

references/source-integrations.md

。

提问："你的工作邮箱地址是什么？这将用于筛选仅你参加过的会议记录。"
- 将邮箱保存至配置文件的
```
user_email
```
  字段
提问："你想连接哪些源？" 提供选项：
- Fireflies.ai — 拉取会议记录（需要环境变量
```
FIREFLIES_API_KEY
```
  ）
- Slack — 拉取频道消息（需要环境变量
```
SLACK_BOT_TOKEN
```
  ）
- Google Drive — 拉取文档和记录（需要通过google-workspace技能完成OAuth配置）
对于每个选中的源，检查是否存在所需的环境变量/凭证。若缺失，提供设置说明：
- Fireflies："在环境中设置
```
FIREFLIES_API_KEY
```
  。可从https://app.fireflies.ai/api获取你的API密钥"
- Slack："在环境中设置
```
SLACK_BOT_TOKEN
```
  。可在https://api.slack.com/apps创建Slack应用"
- Google Drive："运行google-workspace技能设置来配置OAuth。"
为每个启用的源收集配置信息：
- Fireflies：搜索关键词（留空则拉取所有近期内容）和days_back（回溯天数）
- Slack：要拉取的频道 — 若可能则列出可用频道，否则询问用户
- Google Drive：搜索关键词、days_back（回溯天数）
将配置保存至
```
~/.config/casper/linkedin-sources.md
```
确认提示："源配置已保存。运行
```
/casper:generate-linkedin-post --refresh
```
拉取最新内容。"

--refresh

--refresh

Pull fresh source material from all configured integrations before generating posts. Read

references/source-integrations.md

for the full integration workflow.

Summary of the flow:

Read

~/.config/casper/linkedin-sources.md

— if missing, run

--setup-sources

first

For each enabled source, call the existing Casper skill scripts:

Fireflies:

python ${CLAUDE_PLUGIN_ROOT}/skills/transcript-search/scripts/fireflies_transcript_search.py "{term}" --days-back {N} --content --json

After fetching, filter results to only transcripts where
```
user_email
```
(from source config) appears in the transcript's
```
participants
```
array

Slack:

python ${CLAUDE_PLUGIN_ROOT}/skills/slack-automation/scripts/slack_search.py read "{channel}" --days {N}

Google Drive:

python ${CLAUDE_PLUGIN_ROOT}/skills/google-workspace/scripts/gdrive_search.py files "{term}" --modified-days {N} --json

Convert JSON output to clean markdown and save to

source-material/

Fireflies:
```
fireflies-{YYYY-MM-DD}-{title-slug}.md
```
Slack:
```
slack-{channel}-{YYYY-MM-DD}.md
```
Google Drive:
```
gdrive-{title-slug}-{YYYY-MM-DD}.md
```

Proceed with normal generation

生成帖子前，从所有已配置的集成工具拉取最新素材。完整集成工作流请参考

references/source-integrations.md

。

流程概要：

读取

~/.config/casper/linkedin-sources.md

— 若缺失，先运行

--setup-sources

对每个启用的源，调用现有Casper技能脚本：

Fireflies：

python ${CLAUDE_PLUGIN_ROOT}/skills/transcript-search/scripts/fireflies_transcript_search.py "{term}" --days-back {N} --content --json

拉取后，筛选出记录的
```
participants
```
数组中包含源配置里
```
user_email
```
的记录

Slack：

python ${CLAUDE_PLUGIN_ROOT}/skills/slack-automation/scripts/slack_search.py read "{channel}" --days {N}

Google Drive：

python ${CLAUDE_PLUGIN_ROOT}/skills/google-workspace/scripts/gdrive_search.py files "{term}" --modified-days {N} --json

将JSON输出转换为清晰的Markdown格式并保存至source-material/：
- Fireflies：
```
fireflies-{YYYY-MM-DD}-{title-slug}.md
```
- Slack：
```
slack-{channel}-{YYYY-MM-DD}.md
```
- Google Drive：
```
gdrive-{title-slug}-{YYYY-MM-DD}.md
```
执行常规生成流程

--view-style

--view-style

Read

~/.config/casper/linkedin-style.md

and display it. If it doesn't exist, say "No style profile found. Run

/casper:generate-linkedin-post --setup

to create one."

读取并展示

~/.config/casper/linkedin-style.md

。若文件不存在，提示"未找到风格配置文件。运行

/casper:generate-linkedin-post --setup

创建配置。"

--view-sources

--view-sources

List all

.md

files in

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/

(excluding

README.md

). For each file, show the filename and a 1-line summary of its contents.

列出

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/

目录下的所有

.md

文件（排除

README.md

）。对每个文件，显示文件名及内容的一行摘要。

--add-source

--add-source

Ask: "Paste the content you want to add as source material (meeting transcript, Slack dump, notes, etc.)"
Ask: "What should I name this source file? (e.g.,
```
team-standup-jan-2025
```
)"

Save as

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/[name].md

Confirm: "Source material saved. It will be included in future post generation."

提示："请粘贴要添加为素材的内容（会议记录、Slack导出内容、笔记等）"
提示："这个素材文件的名称是什么？（例如
```
team-standup-jan-2025
```
）"

保存为

${CLAUDE_PLUGIN_ROOT}/skills/linkedin-post-generator/source-material/[name].md

确认提示："素材已保存。未来生成帖子时会包含该素材。"

Reference Files

参考文件

File	When to Read
`references/prompt-template.md`	Every generation run — contains voice rules, few-shot examples, confidentiality rules
`references/source-integrations.md`	When running `--refresh` or `--setup-sources` — contains script paths, arguments, output conversion
`references/style-setup.md`	When running `--setup` — contains analysis framework for style profiling
`source-material/*.md`	Every generation run — raw content to extract post ideas from

文件	读取时机
`references/prompt-template.md`	每次生成流程 — 包含语气规则、少样本示例、保密规则
`references/source-integrations.md`	运行 `--refresh` 或 `--setup-sources` 时 — 包含脚本路径、参数、输出转换规则
`references/style-setup.md`	运行 `--setup` 时 — 包含风格分析框架
`source-material/*.md`	每次生成流程 — 用于提取帖子创意的原始内容