sharepoint-shared-doc-maintenance
$
npx mdskill add openai/plugins/sharepoint-shared-doc-maintenanceMaintains shared SharePoint documents by propagating changes from updated source documents.
- Helps keep strategy, roadmap, or status documents aligned with evolving source materials.
- Integrates with SharePoint to fetch and update documents based on timestamps.
- Decides actions by comparing document changes and applying minimal targeted edits.
- Presents results by verifying updates and reflecting new details in the maintained document.
SKILL.md
.github/skills/sharepoint-shared-doc-maintenanceView on GitHub ↗
--- name: sharepoint-shared-doc-maintenance description: Maintain shared SharePoint strategy, roadmap, planning, or status documents from changing source documents. Use when the user wants cross-document synthesis, source-of-truth propagation, or targeted updates to a maintained shared document. --- # SharePoint Shared Doc Maintenance ## Overview Use this skill when the job is not just editing one document, but keeping a maintained shared document aligned with newer source documents. Optimize for finding the real delta and applying the smallest necessary patch. ## Core Workflow 1. Identify the maintained document. 2. Identify the likely source documents that feed it. 3. Compare timestamps so you know which sources changed after the maintained document's last update. 4. Fetch only the maintained document plus the changed source docs. 5. Extract the concrete delta: - timeline shifts - milestone changes - new risks - updated owners - revised launch dates - removed commitments 6. Decide whether the maintained document needs: - no change - a targeted insertion - a broader section rewrite 7. Apply the smallest edit that fully propagates the source change. 8. Re-fetch and verify that the maintained document now reflects the new source-of-truth details in the right section. ## Synthesis Rules - Treat maintenance as a distinct workflow, not as generic document summarization. - For roadmap and milestone maintenance, prefer concrete propagation over broad re-summarization. - Use modification timestamps as a triage tool, not as proof of substantive change. - For multi-document synthesis requests, verify the source set before writing. If the user asks for a consolidated strategy or a summary of all related materials, enumerate the source documents explicitly and verify that likely variants were not skipped. - Even if you expect only one source to have changed, enumerate the source set so you do not miss a second updated input. ## Verification - Verification should confirm both the new fact and its placement in the document. - Do not stop at proving a changed year, date, or milestone appears somewhere. Confirm it appears in the roadmap, recommendations, timing discussion, or risk framing where readers would expect it. - If the maintained document is already on a low-fidelity fallback format because of connector limits, favor precise content patches over broad structural rewrites. ## Recovery Notes - Optimize for quick triage: - list likely source docs once - use modification times to narrow the fetch set - fetch only the maintained doc plus changed sources - extract the exact delta before editing - avoid rewriting unaffected sections - If a changed source contains a strong explicit marker such as `UPDATE`, `TIMELINE CHANGED`, revised year ranges, or renamed milestones, treat that as a high-confidence propagation target.
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|