graphlit

Use when a user wants an AI agent to install Vault Sync, mirror an existing Vault Git repository to local files, keep it refreshed, or consume an already-synced Vault with normal filesystem tools.

Use when the user wants to install Vault Sync, connect an existing Vault Git repository to a local folder, refresh it, configure a recurring pull schedule, or make a local Vault available to an AI agent through filesystem files.

Use when the user wants an AI agent to answer questions or perform research from an already-synced Vault folder using local Markdown files and normal filesystem tools.

Use this skill when the user wants to install, authenticate, connect source accounts, manage data sources, script, or operate Durable Agents from the terminal with the Durable CLI, including automated agents, runs, library content, VFS commands, channels, and MCP connectors.

Use this skill when a developer wants to give an agent Graphlit retrieval, resource reading, content mutation, enrichment, or media generation tools with the @graphlit/agent-tools NPM package in any tool-calling framework without hand-writing common schemas and handlers.

Use this skill when the user wants to add Graphlit to a project, integrate Graphlit, build grounded chat or streaming chat with retrieval, ingest files, websites, or text, sync Slack, Google Drive, email, RSS, S3, or web content, search a knowledge base, scope content by collection, configure Graphlit model specifications, extract entities, or build a knowledge graph. Provides external developer guidance for Graphlit setup, ingestion, feeds, readiness polling, retrieval, collections, specifications, knowledge graph workflows, and `streamAgent()` chat patterns.