sharepoint-skills

Audits the metadata quality of a SharePoint document library or list. Scans every item against its required columns, flags missing, blank, or placeholder values, computes a completeness score per item and per column, and saves a self-contained HTML gap-report dashboard to the site. It is strictly read-only — it never changes the list or its items. Use when the user says: - "metadata audit" - "metadata completeness" - "metadata health" - "missing metadata" - "audit metadata" - "metadata quality" - "check metadata" - "metadata gap report" - "which items are missing metadata" - "find blank columns"

Reads every document in a SharePoint project library and compiles a complete, structured record of every change event — scope assumptions, scope changes, technical decisions, client requests, risks, budget and schedule events, governance events, and early-warning signals — writing each to the Change Events SharePoint list with signal strength and governance flags. Use when the user asks to "extract change events from the project", "build the project change log", "find the signals in these project documents", "populate the Change Events list", or "start the Project Intelligence Engine on this site". First stage of the Project Intelligence Engine; its output feeds Root Cause Analysis.

Reads the Change Events list and produces a full causal analysis of a project failure — a counterfactual root-cause test, the causal chain, intervention windows, and early-warning signal analysis — ending in one actionable recommendation, persisted back to SharePoint. Use when the user asks to "find the root cause", "run root cause analysis on the project", "what went wrong and when did we know", "trace the causal chain", or "analyze the change log". Second stage of the Project Intelligence Engine; requires the Change Events list populated by Change Event Extraction.

Generates a self-contained, dependency-free HTML timeline dashboard that visualises the Project Intelligence Engine output — KPI bar, planned-vs-actual contrast panel, root cause, causal chain, signal-trail timeline, early-warnings table, governance summary, and recommendation. Use when the user asks to "build the timeline dashboard", "visualize the project intelligence output", "generate the project intelligence dashboard", or "create the root cause HTML dashboard". Final stage of the Project Intelligence Engine; requires the Change Events list and analysis from the prior two skills.

Convert an existing Copilot Cowork skill into a Copilot in SharePoint skill. Use this skill to inspect the source skill, identify Cowork-specific assumptions, produce a SharePoint-native conversion plan, get user approval, then create or update the converted skill in AgentAssets/Skills. Use when the user says: - "Convert my skill" - "Rewrite my Cowork skill" - "Make my Cowork skill work in SharePoint" - "Adapt this Cowork skill for Copilot in SharePoint" - "Port this skill from Cowork to SharePoint"

Creates single-file HTML artifacts that render reliably in SharePoint, OneDrive, Teams, File Viewer, and embedded iframe preview surfaces. Use this skill whenever the user asks for SharePoint-safe HTML, an HTML report, dashboard, deck, artifact, visual page, one-pager, or embeddable HTML file for Microsoft 365 preview surfaces. Enforces inline CSS, no external dependencies, no runtime network calls, responsive iframe-friendly layout, optional live-linked CSV/XLSX data files, accessibility, and privacy-safe escaping.

Create a read-only permission and sharing access review report as a self-contained HTML file saved to SharePoint. Use when the user says: - "who has access" - "permission report" - "sharing report" - "access review" - "review permissions" - "create a Permission Report"

Minimal KB quality-check skill for SharePoint libraries. It creates missing review columns, writes short review outputs in Markdown, sets review status, records completion time, and schedules the next review by category.

Reviews a draft proposal against the firm's configurable compliance rules — prohibited language, required disclosures, role and positioning boundaries, and procurement-submission requirements. Logs all findings to the Review Findings SharePoint list and annotates the draft document for salesperson and reviewer resolution.

Searches the firm's SharePoint document libraries — Capability Library, Content Asset Library, Past Proposals Library, and Standard Positions — to find existing content that matches each requirement or question in the RFP Tracker list. Classifies each row as administrative or substantive before searching, with smart routing per library. Writes concise summaries into Available Content and document URLs into three dedicated SharePoint Hyperlink columns (Source 1, Source 2, Source 3) for clickable navigation.

Section-by-section proposal drafting agent. Takes the approved Strategy Brief (ToC + Content Strategy Brief), the RFP Tracker list, and the firm's source documents, and produces a complete proposal draft Word document. Drafts each section individually using one of three modes — Adapt, Synthesize, or Placeholder — based on available source material. Enforces the firm's position boundary throughout. Designed to run after Phase 2 strategy approval and before Phase 4 review.

Extracts questions, mandatory requirements, submission rules, evaluation criteria, and administrative certifications from a Request for Proposal (RFP) document and populates a SharePoint List with each item categorized, flagged for mandatory status, source-traced, and ready for owner assignment and tracking. Handles addenda by letting later versions override earlier ones.

Post-generation audit agent for proposal drafts. Runs three structured checks — strategy fidelity, RFP coverage, and content sourcing — against the generated proposal draft, the approved Strategy Brief, and the RFP Tracker list. Produces a Review Report Word document flagging issues before any human reviewer opens the draft. Designed to run after Phase 3 content generation and before the human review gate.

Reviews a draft proposal for voice consistency, narrative coherence, the firm's configurable tone standards, weak or vague language, and structural quality. Runs after compliance review and salesperson corrections. Logs findings to the Review Findings SharePoint list and annotates the draft.

Reads multiple input documents — past proposals, a win strategy brief, capability statements, a win/loss debrief, and RFP evaluation criteria — and synthesizes them into a recommended proposal Table of Contents and a content strategy brief. Produces an explicit competitive-positioning recommendation and a page-budget allocation table. Designed to run after content mapping (Phase 1) and before any drafting begins (Phase 3).

Renders a polished, self-contained HTML briefing from any data source — SharePoint lists, uploaded documents, or a verbal description. Use when asked to build a competitor landscape, account brief, candidate summary, site inventory, board bio, speaker profile, partner overview, or any grid of profile cards or single-subject one-pager. Interviews the user if data is incomplete, constructs a validated JSON document, then renders it into a sandbox-safe HTML file using grid mode (2–8 subjects as responsive cards) or one-pager mode (1 subject as a rich briefing). No external dependencies — output runs inside a SharePoint sandboxed iframe.

Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description. Use when asked to build an exec report, one-pager, summary page, status dashboard, project summary, business review, or any single-page visual summary of data. Interviews the user if data is incomplete, constructs a validated JSON document block by block, then renders it into a single sandbox-safe HTML file using the component library. No external dependencies — output runs inside a SharePoint sandboxed iframe.

Generates a polished, self-contained HTML roadmap or milestone timeline from any project data — SharePoint lists, pasted tables, or a verbal description. Use when asked to build a project roadmap, product roadmap, migration timeline, release plan, onboarding sequence, run-of-show, phase plan, or any visual schedule showing items over time. Interviews the user if data is incomplete, constructs a validated JSON document, then renders it into a single sandbox-safe HTML file. Chooses between two layouts automatically: horizontal roadmap with swimlanes (for phase-range data) or vertical milestone list (for point-in-time events). No external dependencies — output runs inside a SharePoint sandboxed iframe.

Generates a polished, self-contained HTML heatmap scorecard — a weighted comparison matrix where entities (rows) are scored across dimensions (columns), with computed totals, rank badges, and a winner highlight. Use when asked to build a scorecard, comparison matrix, decision matrix, vendor evaluation, tool assessment, candidate scoring grid, competitive analysis, site-readiness matrix, or any weighted multi-criteria ranking. Interviews the user if entities or criteria are missing, constructs a validated JSON document, then renders it into a sandbox-safe HTML file using the component library. No external dependencies — output runs inside a SharePoint sandboxed iframe.

Classifies files in a SharePoint document library by reading their content and matching them to known content types (Contracts, Invoices, Purchase Orders). Creates a File classification Choice column plus 5 metadata columns per content type, extracts values from each file, and writes them back automatically. Use when the user asks to classify, categorize, tag, or auto-label files in a library, or to set up content types with metadata extraction. Trigger phrases: classify files, classify documents, classify library, categorize files, tag files, auto-classify, set up content types, extract metadata, identify contracts invoices purchase orders.

Organizes files in a document library so people and AI can find them easily. Scans all files, summarizes issues (duplicates, empty folders, bad names), recommends a clean structure with a visual before/after comparison, reads file content to propose meaningful rename suggestions, then executes with a TODO checklist the user can follow along with. Triggered when someone says "clean up file demo".

Apply a visual style theme to any SharePoint list or document library using column formatting, view formatting, row templates, and tile layouts. Use this skill whenever the user asks to style, theme, or visually transform a list or library. The goal is "I can't believe that's SharePoint" impact — not just color swaps, but fully art-directed views. This skill works with any style token file.

End-to-end orchestrator that fully organizes a SharePoint document library — classifies files by content type (via the file-classifier skill), creates and extracts metadata columns, applies brand-consistent column and view formatting, builds per-content-type views, colors folders, and creates notification rules for overdue items. Use when the user asks to organize, set up, structure, or transform a document library, or to apply branding and views across content types. Trigger phrases: organize library, organize document library, set up library, structure library, brand library, full library makeover, apply brand to library, organize and format library.

Renames all files in a SharePoint document library (including subfolders) to prefix them with their created date in yyMMdd format (e.g., 251203-Status Report.pdf). Offers a preview before committing changes. Use when the user asks to prefix filenames with dates or add date prefixes to files.

Convene a council of expert AI personas to review, stress-test, and improve any document, idea, proposal, or plan. Use this skill whenever the user asks to "review," "stress-test," "get feedback on," "critique," "poke holes in," "red team," "evaluate," "council," "panel review," or "get perspectives on" any content — whether it's an uploaded Word doc, Excel spreadsheet, PowerPoint deck, PDF, or just a raw idea typed into chat. Also trigger on phrases like "what do you think of this," "is this any good," "what am I missing," "would this work," or "convene the council." This skill works on any format: .docx, .xlsx, .pptx, .pdf, pasted text, or a verbal idea. It replaces generic "looks good" feedback with structured multi-perspective debate and a clear verdict.

Generates an interactive HTML site map showing storage breakdown and hot/cold activity heatmap across all document libraries, lists, and site pages. Includes site-wide summary stacked bars and per-library click-through drill-downs. Saves the file as {FirstName}-Site-Storage-Heatmap.html in the "storage heatmap" folder inside the site's document library, then navigates the user to it.

Bento style tokens and row template for the list-styling skill. Card layout inspired by bento boxes — distinct compartments separated by thin borders, each section labeled, warm earth tones. Layout is a horizontal row of compartments (name | status | progress | deadline) with visible dividers between each. Use when the user says "bento," "compartment," "warm style," "earth tones," "organized," or similar.

Blueprint engineering-drawing style tokens and row template for the list-styling skill. Monochromatic blue palette, double-ring rubber-stamp status badges, ultra-compact spec-sheet card with a blue left edge. The most compact card in the library — no sidebar, no banner. Overdue is the only element that turns red. Use when the user says "blueprint," "technical drawing," "engineering," "schematic," "spec sheet," or similar.

Figma Clean style tokens and row template for the list-styling skill. Polished professional cards with a colored top stripe that matches the status, clean data layout below, subtle self-colored borders. Layout features a thin status-colored bar across the top of each card. Use when the user says "figma," "clean," "polished," "professional," "design tool," or similar.

Glassmorphism (Frosted Glass) style tokens and row template for the list-styling skill. Floating cards with soft diffused shadows, no hard borders, pill badges, thin progress bars, maximum whitespace. Layout is a single-column centered card — no sidebar split. Use when the user says "glassmorphism," "frosted glass," "glass look," "soft modern," "airy," "floating," or similar.

High Contrast accessibility style tokens and row template for the list-styling skill. Maximum contrast, large text, thick borders, alternating dark/light band rows, heavy left accent bar. Layout uses wide horizontal bands with large bold text for maximum readability. Use when the user says "high contrast," "accessible," "WCAG," "large text," or similar.

Monochrome style tokens and row template for the list-styling skill. Single-hue slate design with a left-aligned large progress number as the hero element, all metadata stacked beside it. Layout uses the progress percentage as the dominant visual element. Use when the user says "monochrome," "single color," "corporate," "tonal," "minimal," or similar.

Neobrutalism style tokens and row template for the list-styling skill. Bold black borders, saturated colors, uppercase text, chunky progress bars, sharp edges, card-based row layout with sidebar metadata panel. The row template replaces the entire row with a two-panel card. Use when the user says "neobrutalism," "brutalist," "bold borders," "chunky style," or similar.

Pastel style tokens and row template for the list-styling skill. Soft candy colors, inverted badges (light bg + dark text), rounded cards with a tinted left panel that matches the status hue. Friendly and approachable. Use when the user says "pastel," "soft colors," "candy," "friendly," "approachable," or similar.

Retro Memphis style tokens and row template for the list-styling skill. Bright contrasting colors, colored shadows, playful stacked card with a status-colored top banner and large progress number. Layout is a stacked vertical card with a bold colored header strip — NOT a sidebar layout. Use when the user says "retro," "memphis," "80s," "90s," "colorful," "playful," "fun style," or similar.

Terminal / Hacker style tokens and row template for the list-styling skill. Dark cards with neon text, green/cyan accents, sharp corners, terminal prompt icon, status displayed like CLI output. Use when the user says "terminal," "hacker," "dark mode," "matrix," "developer," "CLI," or similar.

Reconciles one or more user-selected invoice files against matching purchase orders in the Purchase Order library. Compares totals, flags discrepancies, writes reconciliation status back to invoice metadata, and returns a formatted summary table. Trigger phrases: po reconciliation, invoice reconciliation, invoice to po reconciliation, reconcile invoice, reconcile po, match invoice to po, invoice po match, po match, check invoice against po.