Token导航 LogoToken导航

Agent Skill · 开发

client-package-notion(client package Notion 开发)

用于处理 Notion 页面、数据库、工作区内容和结构化记录。它适合让 Agent 查询知识库、整理页面内容、创建记录或把外部信息同步到 Notion。使用时需要确认集成是否已被授权到目标页面或数据库,并区分读取、追加和覆盖更新;涉及批量写入或修改数据库属性时,应先核对字段名称、属性类型和目标页面。

client-package-notion 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 20,882。

总安装 210周安装 9GitHub Stars 607下载 73核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:client-package-notion(client package Notion 开发)
来源仓库:https://github.com/athina-ai/goose-skills
仓库路径:skills/client-package-notion
安装命令:
npx skills add https://github.com/athina-ai/goose-skills --skill client-package-notion
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/athina-ai/goose-skills --skill client-package-notion

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

client-package-notion 用于将客户工作打包成结构化的 Notion 页面,包含子页面和 Google Sheets。适合在 Codex、Claude、Cursor、Gemini CLI 中将成果同步至知识库,适用于项目汇报和协作管理。

通过读取本地文件夹自动生成导航式交付包,支持自定义介绍语和接收人信息。使用前需确保 Notion 集成已授权到目标页面,并注意字段匹配与更新方式。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/client-package-notion

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/athina-ai/goose-skills --skill client-package-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

client-package-notion 怎么安装?

在终端执行 npx skills add https://github.com/athina-ai/goose-skills --skill client-package-notion。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

client-package-notion 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

client-package-notion 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

client-package-notion 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

client-package-notion 用的人多吗?

公开数据是累计安装 210 次,近一周安装 9 次,下载 73 次,GitHub 607 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

client-package-notion 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
client-package-notion

client package Notion 开发 · 本页

210607调用外部服务未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

create-client-package-notion

Package all GTM work for a client into a structured, shareable Notion page with subpages and Google Sheets. Reads the client's workspace folder and builds a navigable delivery package.

Inputs

InputRequiredDefaultDescription
client_nameYes--Client folder name under clients/ (e.g., truewind)
intro_messageNo--Custom introduction message for the top-level page. If not provided, generate a professional intro based on the assets found.
recipient_nameNo--Name of the person receiving the package (used in intro)
recipient_contextNo--Any framing context for the delivery (e.g., "we built these to capitalize on the Botkeeper shutdown")
include_strategiesNotrueWhether to include strategy documents
include_campaignsNotrueWhether to include campaign assets
include_contentNotrueWhether to include content drafts
include_leadsNotrueWhether to include lead lists (uploaded to Google Sheets)
include_conference_speakersNotrueWhether to include conference speaker data

Setup

Requires access to:

  • Notion MCP server — for creating pages and subpages
  • Rube MCP server — for creating Google Sheets (via Composio GOOGLESHEETS tools)

No API keys need to be set manually — both are accessed through MCP.

Procedure

Step 1: Scan the Client Folder

Read the client folder at clients/<client_name>/ and inventory all available assets:

clients/<client_name>/
├── context.md          # Client context, ICP, positioning
├── competitors.md      # Competitive landscape (optional)
├── notes.md            # Running log of decisions
├── strategies/         # Strategy documents (*.md)
├── campaigns/          # Campaign assets (folders or *.md)
├── content/            # Content drafts (blog posts, comparison pages, etc.)
└── leads/              # Lead lists (*.csv and *.md)

For each directory, list all files and read their contents. Build an inventory:

  • Strategies: List of .md files in strategies/ (skip orchestration prompts or internal-only files)
  • Campaigns: List of campaign folders or .md files in campaigns/
  • Content: List of .md files in content/
  • Leads: List of .csv files (for Google Sheets upload) and .md files (for Notion pages) in leads/

If a directory doesn't exist or is empty, skip it in the output.

Step 2: Upload Lead Lists to Google Sheets

For each .csv file found in leads/:

  1. Create a new Google Sheet using GOOGLESHEETS_CREATE_GOOGLE_SHEET1

- Title format: <Client Name> — <Lead List Name> (derive from filename) - Example: Truewind — Botkeeper LinkedIn Leads

  1. Parse the CSV and write data using GOOGLESHEETS_BATCH_UPDATE

- First row = headers - Remaining rows = data - Use first_cell_location: "A1" and valueInputOption: "USER_ENTERED"

  1. Record the spreadsheet URL for linking in Notion pages later

If there are multiple CSVs, create sheets in parallel.

Step 3: Plan the Notion Page Structure

Design the page hierarchy based on what assets exist. The general pattern is:

Top-Level Page: "<Client Name> — GTM Engineering Package"
├── Introduction (on the top-level page itself)
├── Strategies (subpage — all strategy docs combined or as separate child pages)
├── <Signal-Specific Section> (subpage — groups campaigns + content for a specific signal)
│   ├── Campaign 1 (subpage)
│   ├── Campaign 2 (subpage)
│   ├── Content Asset 1 (subpage)
│   └── Content Asset 2 (subpage)
├── Conference Speakers (subpage — if speaker data exists)
└── Lead Lists (linked as Google Sheets from relevant pages)

Grouping logic:

  • If campaigns and content assets share a common theme (e.g., "botkeeper"), group them under a themed section
  • If campaigns are standalone, list them at the top level
  • Lead list Google Sheet links should appear on the pages where they're most relevant (e.g., LinkedIn leads linked from the LinkedIn engagement page)
  • Conference/speaker data gets its own top-level subpage

When assets don't fit a theme: Create a "Campaigns" subpage and a "Content" subpage as catch-all sections.

Present the planned structure to the user and confirm before creating pages.

Step 4: Create the Top-Level Notion Page

Create a standalone workspace-level page with:

Title: <Client Name> — GTM Engineering: Growth Strategies & Execution (or similar)

Content: An introduction section that includes:

  • A greeting to the recipient (if recipient_name provided)
  • A summary of what's inside (list the sections with brief descriptions)
  • Links to the Google Sheets with lead lists
  • Any framing context from recipient_context
  • A closing line

If intro_message is provided, use it as-is. Otherwise, generate a professional intro based on:

  • What asset types exist (strategies, campaigns, content, leads)
  • How many leads were found
  • What the key themes are (inferred from strategy/campaign filenames)

Use Notion-flavored Markdown. Do NOT include the page title in the content (Notion renders it automatically from properties).

Step 5: Create Subpages

For each section in the planned structure, create subpages under the top-level page:

For strategy documents:

  • Read the full .md content from the file
  • Convert to Notion-flavored Markdown (adjust table syntax, escape special characters)
  • Create as a subpage with the strategy title

For campaign documents:

  • Read the full .md content
  • Insert Google Sheet links where lead lists are referenced
  • Create as a subpage

For content assets (blog posts, comparison pages):

  • Read the full .md content
  • Create as a subpage with the article title

For lead/conference data in .md format:

  • Read the full .md content
  • Create as a subpage

For grouped sections (e.g., "Botkeeper Strategies"):

  • Create a parent subpage with a summary/index of what's inside
  • Create child subpages under the parent for each individual asset
  • Link relevant Google Sheets from the parent summary

Create pages in batches where possible (the Notion API supports creating multiple pages in one call when they share a parent).

Step 6: Verify and Report

After all pages are created, output a summary:

## Package Created

**Top-level page:** [<title>](<notion-url>)

**Subpages:**
- [Strategies](<url>) — 2 strategy documents
- [Botkeeper Strategies](<url>) — 4 assets (2 campaigns, 2 content pieces)
  - [LinkedIn Engagement](<url>)
  - [Listicle Author Outreach](<url>)
  - [SEO Article](<url>)
  - [Comparison Page](<url>)
- [Conference Speakers](<url>)

**Google Sheets:**
- [Lead List 1](<sheets-url>) — 12 leads
- [Lead List 2](<sheets-url>) — 9 leads

**Total:** X pages created, Y Google Sheets created

Notion Markdown Notes

When converting client .md files to Notion content, keep these in mind:

  • Tables: Notion uses <table> XML syntax, but standard markdown tables (| col | col |) also work
  • Escape special characters: \* \~ \ $ [] < > {} | ^`
  • Links: Standard markdown [text](url) works
  • No H1 in content: The page title is rendered automatically — start content at H2 or below
  • Empty lines: Use <empty-block/> for intentional blank lines (regular blank lines are stripped)
  • Code blocks: Do NOT escape characters inside code blocks
  • Subpages: Use <page url="...">Title</page> to reference existing child pages (but pages are created via the API, not inline)

Output Format

The skill produces:

  1. A Notion page URL (top-level) that can be shared with the client
  2. A list of all subpage URLs
  3. A list of Google Sheet URLs with lead data

Example Prompts

  • "Package everything we've done for Truewind into a Notion page I can send to the founder"
  • "Create a client delivery package for Acme Corp with all our campaign work"
  • "Build a Notion package for [client] — include strategies, campaigns, and lead lists"
  • "Take our work in clients/truewind and create a shareable Notion workspace"
  • "Package the client folder into something I can send to the CEO"

Troubleshooting

ProblemSolution
Notion page creation failsCheck that the Notion MCP server is connected. Try creating a simple test page first.
Google Sheets creation failsVerify the Rube MCP server is connected and Google Sheets has an active connection. Run RUBE_MANAGE_CONNECTIONS with toolkits: ["googlesheets"].
CSV parsing errorsCheck the CSV for encoding issues. The skill expects UTF-8 CSVs with a header row.
Notion content looks wrongReview Notion-flavored Markdown spec. Common issues: unescaped special characters, H1 in content (conflicts with page title), or raw HTML that Notion doesn't support.
Too many pages to createNotion API supports batch page creation (up to 100 pages per call with shared parent). Group subpages by parent and batch create.
Lead list is empty or malformedSkip that CSV and note it in the summary. Don't create an empty Google Sheet.

Metadata

metadata:
  requires:
    mcp_servers: ["notion", "rube"]
  cost: "Free (Notion API + Google Sheets via Composio)"

平台分布

Codex

38.49%
按下载量换算28

Claude

28.36%
按下载量换算21

Cursor

19.27%
按下载量换算14

Gemini CLI

8.85%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills