sharepoint-site-discovery
$
npx mdskill add openai/plugins/sharepoint-site-discoveryLocate the correct SharePoint site, library, and folder before file operations.
- Helps users find the right context before editing or fetching documents.
- Integrates with search, site validation, and drive listing APIs.
- Decides actions by validating hostnames and inspecting library contents.
- Delivers resolved URLs and folder paths for downstream file tasks.
SKILL.md
.github/skills/sharepoint-site-discoveryView on GitHub ↗
--- name: sharepoint-site-discovery description: Resolve the right SharePoint site, library, and folder before file work. Use when the user needs to find the right site context, browse a known site, inspect document libraries, or narrow the correct folder before fetching or editing a file. --- # SharePoint Site Discovery Use this skill when the main job is locating the right SharePoint site, drive, or folder before file analysis or editing. ## Start Here - Treat SharePoint discovery as site-scoped, not user-recency-scoped. - Use `search(query="...")` for keyword search. - Use `search(query=None, hostname=..., site_path=..., folder_path=...)` for browse mode. - Use `get_site(...)` and `list_site_drives(...)` when the user knows the site but not the right library. ## Workflow 1. If the user names a SharePoint hostname and site path, validate them with `get_site(...)`. 2. If the site is known but the right library is not, use `list_site_drives(...)` to inspect the site-scoped document libraries. 3. If the user wants to browse a known folder or library, use `search(query=None, hostname=..., site_path=..., folder_path=...)` and inspect the immediate children. 4. If the user wants to find a file by keyword, use `search(query="...")`, then narrow with `hostname`, `site_path`, or `folder_path` when the scope is known. 5. Preserve the exact returned `url`, site, drive, and folder context so later `fetch`, `update_file`, or `upload_file` calls use the resolved destination instead of a guessed path. 6. When multiple plausible sites or libraries exist, present the candidates and explain the distinguishing context instead of picking silently. ## Output Conventions - Name the exact site, library, and folder you resolved. - Distinguish clearly between browse results and keyword-search results. - When handing off to another SharePoint workflow, include the resolved `url` or the exact site and folder context that should be reused. ## Example Requests - "Find the right SharePoint site for the launch checklist and show me the available document libraries." - "Browse the ops site and narrow me to the folder that contains the Q2 roadmap files." - "Search SharePoint for the pricing workbook, but keep the search inside the finance site."
More from openai/plugins
- accessibility-and-inclusive-visualizationMake data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.
- agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
- agent-browser-verifyAutomated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
- agents-sdkBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
- ai-elementsAI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.
- ai-gatewayVercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.
- ai-generation-persistenceAI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
- ai-sdkVercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
- aiq-deploy|
- aiq-research|