OpenParable
Skip to content
← Back to skills

Sharepoint

Apps & Automation
sharepoint

Sharepoint is an Agent Skill for apps & automation published in the Arvo-AI/aurora repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

SharePoint integration for searching documents, pages, and publishing incident reports via Microsoft Graph API

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Arvo-AI/aurora/blob/HEAD/server/chat/backend/agent/skills/integrations/sharepoint/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/sharepoint, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

SharePoint Integration

Overview

SharePoint integration for searching documents and pages via Microsoft Graph API during Root Cause Analysis. Use to find runbooks, architecture docs, and past incident reports stored in SharePoint.

Instructions

Tools

  • sharepoint_search(query='error keywords', site_id='optional-site-id') -- Search across SharePoint for pages, documents, and list items matching a query. Pass a search query and optional site_id to restrict to a specific site. Returns matching items with excerpts.
  • sharepoint_fetch_page(site_id='site-id', page_id='page-id') -- Fetch a SharePoint page by site ID and page ID and return its content as markdown. Use after search to read full page details.
  • sharepoint_fetch_document(drive_id='drive-id', item_id='item-id') -- Fetch a SharePoint document by drive ID and item ID and return extracted text content. Use for Word docs, PDFs, and other documents stored in SharePoint document libraries.
  • sharepoint_create_page(site_id='site-id', title='...', content='...') -- Create a new SharePoint page with the given title and HTML/markdown content. Use to publish incident reports, postmortems, or runbooks to SharePoint.

RCA Investigation Flow

Step 1 -- Search for relevant documents

sharepoint_search(query='error keywords', site_id='optional-site-id') -- Search across SharePoint for pages, documents, and list items

Step 2 -- Read page content

sharepoint_fetch_page(site_id='site-id', page_id='page-id') -- Read full page content as markdown

Step 3 -- Extract document content

sharepoint_fetch_document(drive_id='drive-id', item_id='item-id') -- Extract text from Word docs, PDFs, etc.

Workflow

Search first to find relevant documents and pages, then fetch content for detailed review.

Post-Investigation

Use sharepoint_create_page to publish incident reports, postmortems, or runbooks back to SharePoint for the team.

Important Rules

  • Search SharePoint early in the investigation for existing runbooks and procedures.
  • Use sharepoint_fetch_page for web pages and sharepoint_fetch_document for uploaded files (Word, PDF).
  • Cross-reference findings with live infrastructure state.