用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill granola命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
| name | granola |
| description | Access Granola AI meeting notes - CSV import, shared note fetching, and MCP-ready for upcoming API support. |
| homepage | https://granola.ai |
| metadata | {"clawdbot":{"emoji":"🥣","requires":{}}} |
Access your Granola meeting notes. Granola is the AI notepad for people in back-to-back meetings.
Granola allows exporting historical notes as CSV. This skill can parse and search those exports.
# Parse a Granola CSV export
python3 {baseDir}/scripts/csv_import.py --file ~/Downloads/granola_export.csv
# Search parsed notes
python3 {baseDir}/scripts/csv_import.py --file ~/Downloads/granola_export.csv --search "quarterly review"
When you share a Granola note, it gets a public URL. This skill can fetch and parse shared notes.
# Fetch a shared note
python3 {baseDir}/scripts/fetch_shared.py --url "https://share.granola.ai/..."
Granola is building official MCP (Model Context Protocol) support for AI agent access. When available:
{
"mcpServers": {
"granola": {
"command": "granola-mcp",
"args": ["--api-key", "YOUR_KEY"]
}
}
}
Note: CSV export only includes notes older than 30 days and doesn't include full transcripts.
Import and search meeting notes:
"Search my Granola notes for anything about the product roadmap"
"What did we discuss in last month's board meeting?"
"Find action items from my 1:1s"
When MCP is available:
"What meetings did I have this week?"
"Summarize my meeting with John yesterday"
"What are my action items from today?"