
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 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.
--- name: review-council description: 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 "w
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.
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.
# Brand Style Skill — Template Use this skill whenever creating any visual output, document, web content, presentation, table, list, or interface element for **[Your Organization]**. This skill ensures all outputs are visually consistent with the brand. > **How to use this template:** Replace every `[placeholder]` and the example values below with your organization's actual brand values. Delete this callout when done. --- ## Brand Identity [Your Organization] is a [brief description — indus
Matches open Knowledge Gaps items to subject matter experts in the Expert Directory and assigns them. Triggers when asked to find experts, route open questions, or review unassigned gaps.
Extracts tacit knowledge from any input — typed text, transcripts, emails, documents, or Slack threads — and writes it into the Knowledge Base library as structured markdown. Triggers when someone shares knowledge directly, pastes content, or uploads a file to the Submissions library. Resolves matching open Knowledge Gaps items automatically.
Generates a comprehensive knowledge base health report covering corpus overview, knowledge decay, gap status, ingestion activity, expert coverage, and recommended next actions. Triggers when an admin asks for a knowledge base report, status update, or health check.
Logs unanswered questions to the Knowledge Gaps list and routes them to a subject matter expert. Triggers when the assistant cannot answer a question from the Knowledge Base library. Checks the Expert Directory for a matching expert and assigns the gap automatically.
Systematically edits Markdown documents — READMEs, skill files, and demo guides — using seven sequential sweeps. Each sweep focuses on one quality dimension so nothing gets missed. Use when a document needs to be clearer, tighter, or easier to act on. Triggers include "edit this", "clean this up", "review my README", "improve this skill", "tighten this up", or when a document feels long, vague, or hard to follow. Does NOT write or suggest code.
Assembles a new HTML presentation by selecting content from existing PowerPoint source decks and rendering it in a polished Copilot-themed design. Use when the user wants to build a new deck from content in other decks — triggers include "make a new deck using slides from," "combine these decks," "take the roadmap from this deck and the intro from that one," or "assemble a presentation for this customer." Produces a self-contained HTML file that opens in any browser, navigates with arrow keys, and looks like a premium dark-themed Microsoft AI briefing deck.
Review any content file (image, Word doc, Excel, PowerPoint, PDF, etc.) for compliance with UPPAbaby brand guidelines. Produces a detailed scorecard and prioritized list of actionable remediation steps. Use this skill whenever someone asks to review, audit, check, or evaluate content against UPPAbaby brand standards — including marketing materials, social posts, presentations, emails, product pages, retailer assets, or any creative deliverable. Also trigger when someone mentions "brand compliance", "brand review", "brand check", "on-brand", or "brand audit" in the context of UPPAbaby content. Even partial reviews (e.g., "does this headline sound like UPPAbaby?") should use this skill.
Builds structured FAQ pages from source material such as documents, process guides, policies, product descriptions, or topic briefs. Anticipates questions from the reader's perspective, groups them into themes, writes clear Q&A pairs, and delivers SharePoint-ready Markdown. Use when a user wants to create an FAQ from an existing document, prepare a help page for a new process or policy, or capture anticipated questions before a launch or rollout. Triggers include "create an FAQ from this", "build a FAQ page", "what questions will people ask about this", "turn this into a FAQ", or when a user wants to surface common questions from a document or topic.
Transforms raw video or audio transcripts into detailed, structured meeting summaries formatted for SharePoint. Handles messy auto-generated transcripts including unlabeled speakers, filler words, and transcript artifacts. Extracts discussion threads, decisions, action items, key quotes, and next steps. Use when a user pastes or shares a meeting transcript and wants polished, shareable notes. Triggers include "summarize this meeting transcript", "create notes from this recording", "turn this transcript into meeting notes", "write up this call", or when a user shares raw transcript text.
Sets up persistent eval suites for any AI in SharePoint skill and runs self-healing improvement loops on demand. Use this when setting up evals for a skill for the first time, or when the user says "improve [skill-name]", "fix [skill-name]", or "run evals for [skill-name]" to fix a skill that has drifted, started failing, or needs to handle new patterns.
A self-evaluating iterative agent loop that pursues a goal through structured cycles of Reason, Act, Look, Probe, and Harden until the goal is confidently achieved. Use when a task requires iterative refinement, quality assurance, or when "good enough" isn't good enough. Works for any goal — document generation, data extraction, content processing, analysis, or creative work.
Reads an Open Roles list and a Candidates list from the current SharePoint site and generates a self-contained HTML hiring dashboard for Zava Industries. The dashboard includes executive metrics, a D3 Sankey diagram of candidate flow through pipeline stages, risk callouts (stale candidates, starved roles, bottleneck stages), and a breakdown table by role. Use when asked for a hiring pipeline report, pipeline status, recruiting dashboard, or any summary of open roles and candidates.
Reads vendor, date, and spend data from the Expenses library on the current SharePoint site and generates a self-contained interactive HTML expense report for a specified fiscal quarter. Use when asked for a quarterly expense summary, Q1/Q2/Q3/Q4 financial summary, expense report, or spend analysis by period.
# Brand Style Skill — Template Use this skill whenever creating any visual output, document, web content, presentation, table, list, or interface element for **[Your Organization]**. This skill ensures all outputs are visually consistent with the brand. > **How to use this template:** Replace every `[placeholder]` and the example values below with your organization's actual brand values. Delete this callout when done. --- ## Brand Identity [Your Organization] is a [brief description — indus
Performs comprehensive analysis of a SharePoint project site by systematically reading ALL lists and ALL documents using AI in SharePoint tools, then producing a tailored, data-driven analysis. Use when asked to analyze a site holistically, create scorecards, audit project health, prepare meeting briefings, assess risks, or perform any exhaustive site-wide analysis. Works with any SharePoint team site.
Applies the forest-style brand system to any visual output, document, web content, presentation, table, list, or interface element. Enforces the color palette, typography, spacing, component styles, and voice guidelines to ensure consistent brand expression. Use this skill whenever creating or reviewing content that must conform to forest-style brand standards.
Distills long documents, reports, meeting transcripts, or briefing materials into tight one-page executive summaries formatted for SharePoint. Surfaces the core situation, key findings or decisions, recommendations, and what the reader needs to do or know. Use when a user wants to condense a long document for a leadership audience, create a TL;DR for a report, or produce a standalone summary someone can read in under two minutes. Triggers include "summarize this for leadership", "write an exec summary", "make this into a one-pager", "TL;DR this document", or when a user shares a long document and asks for a shorter version.
Create beautiful, functional SharePoint list and library formatters using JSON. Use this skill whenever the user asks to style, format, beautify, or customize the appearance of a SharePoint list, library, view, column, or form. Trigger phrases include "style my list", "format my list", "make my list pretty", "make my library beautiful", "style my library", "customize my view", "format my columns", "card layout", "tile view", "add icons to my list", "color code my list", "conditional formatting", "progress bars", or any mention of SharePoint JSON formatting. Also trigger when the user references specific formatting patterns like status indicators, data bars, people cards, Gantt charts, KPI dashboards, or hover cards in a SharePoint context. This skill produces English-language instructions only — no code generation. It teaches the agent what is possible and how to describe formatters so a downstream tool can apply them.
Crafts high-performing LinkedIn posts from any topic, story, announcement, or idea. Use this skill when a user needs to write, draft, improve, or optimize a LinkedIn post — including personal stories, product announcements, thought leadership, professional milestones, or content repurposing. Triggers include requests to "write a LinkedIn post about", "help me announce this on LinkedIn", "make this sound better for LinkedIn", or when a user provides a transcript, article, achievement, or idea they want to share professionally.
Generate engaging YouTube video descriptions from video transcripts. Use this skill whenever the user wants to create a YouTube description, write a video description, summarize a video for YouTube, or draft copy for a YouTube upload. Also trigger when the user provides a transcript and mentions YouTube, video publishing, or video SEO. Works with raw transcripts, cleaned transcripts, or transcript files in any format.
Turns a rough idea, stakeholder request, or email thread into a structured project brief with a clear problem statement, goals, success criteria, scope, stakeholders, and risks. Asks clarifying questions one at a time to fill gaps, then delivers a complete SharePoint-ready brief. Use when a user wants to scope a new project, formalize a request that came in through email or conversation, or create a brief before moving into full design or planning. Triggers include "write a project brief", "turn this email into a brief", "help me scope this project", "I need to document this request", or when a user describes a rough idea and wants a structured starting point.
Create beautiful, functional SharePoint list and library formatters using JSON. Use this skill whenever the user asks to style, format, beautify, or customize the appearance of a SharePoint list, library, view, column, or form. Trigger phrases include "style my list", "format my list", "make my list pretty", "make my library beautiful", "style my library", "customize my view", "format my columns", "card layout", "tile view", "add icons to my list", "color code my list", "conditional formatting", "progress bars", or any mention of SharePoint JSON formatting. Also trigger when the user references specific formatting patterns like status indicators, data bars, people cards, Gantt charts, KPI dashboards, or hover cards in a SharePoint context. This skill produces English-language instructions only — no code generation. It teaches the agent what is possible and how to describe formatters so a downstream tool can apply them.
Generate engaging YouTube video descriptions from video transcripts. Use this skill whenever the user wants to create a YouTube description, write a video description, summarize a video for YouTube, or draft copy for a YouTube upload. Also trigger when the user provides a transcript and mentions YouTube, video publishing, or video SEO. Works with raw transcripts, cleaned transcripts, or transcript files in any format.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Guides a raw idea through structured brainstorming into a fully fleshed-out design document formatted for SharePoint. Asks clarifying questions one at a time, proposes alternative approaches with trade-offs, builds the design incrementally with user approval, then delivers a complete SharePoint-ready document. Use when a user wants to develop an idea, proposal, project plan, or initiative into a structured doc. Triggers include "help me think through this", "turn this idea into a design doc", "I want to design a new [process/project/feature/solution]", "brainstorm this with me", or when a user describes a rough idea and wants to make it concrete.
Converts documents and knowledge gathered from Microsoft Copilot into well-structured, SharePoint-compatible markdown files. Use when a user has content from Copilot (summaries, research, meeting notes, process steps) and wants to produce a formatted page for a SharePoint site, wiki, or knowledge base. Triggers include "create a markdown file from this", "format this for SharePoint", "write this up as a knowledge base article", "turn this Copilot output into a page", or when a user pastes Copilot-generated content and asks for it to be documented.
--- name: decision-log description: Extracts and formats Decision Records from video or audio transcripts, capturing the full context of each decision: the problem being solved, options that were considered, who made the call, the rationale, concerns or dissent raised, and any conditions or follow-on actions. Produces structured, durable Decision Records rather than a meeting narrative. Use when a user wants to document the reasoning behind decisions made in a recorded meeting, create an audit t
Compares two documents or versions of content and surfaces what is missing, conflicting, changed, or new between them. Produces a structured gap analysis with categorized findings and a summary of implications. Use when a user wants to compare an old and new version of a document, check whether a spec matches an implementation, audit a policy for missing coverage, or identify what changed between two states. Triggers include "compare these two docs", "what's missing from this", "what changed between these versions", "find the gaps", "does this spec match this document", or when a user shares two documents and asks what is different or inconsistent.
Optimize any AI in SharePoint skill by iteratively running it against test inputs, scoring outputs with binary evals, mutating the prompt to fix failures, and keeping improvements. Adapts Karpathy's autoresearch methodology to AI in SharePoint's multi-turn conversation architecture.
Review any content file (image, Word doc, Excel, PowerPoint, PDF, etc.) for compliance with UPPAbaby brand guidelines. Produces a detailed scorecard and prioritized list of actionable remediation steps. Use this skill whenever someone asks to review, audit, check, or evaluate content against UPPAbaby brand standards — including marketing materials, social posts, presentations, emails, product pages, retailer assets, or any creative deliverable. Also trigger when someone mentions "brand compliance", "brand review", "brand check", "on-brand", or "brand audit" in the context of UPPAbaby content. Even partial reviews (e.g., "does this headline sound like UPPAbaby?") should use this skill.
Converts documents and knowledge gathered from Microsoft Copilot into well-structured, SharePoint-compatible markdown files. Use when a user has content from Copilot (summaries, research, meeting notes, process steps) and wants to produce a formatted page for a SharePoint site, wiki, or knowledge base. Triggers include "create a markdown file from this", "format this for SharePoint", "write this up as a knowledge base article", "turn this Copilot output into a page", or when a user pastes Copilot-generated content and asks for it to be documented.
Guides a raw idea through structured brainstorming into a fully fleshed-out design document formatted for SharePoint. Asks clarifying questions one at a time, proposes alternative approaches with trade-offs, builds the design incrementally with user approval, then delivers a complete SharePoint-ready document. Use when a user wants to develop an idea, proposal, project plan, or initiative into a structured doc. Triggers include "help me think through this", "turn this idea into a design doc", "I want to design a new [process/project/feature/solution]", "brainstorm this with me", or when a user describes a rough idea and wants to make it concrete.
Compares two documents or versions of content and surfaces what is missing, conflicting, changed, or new between them. Produces a structured gap analysis with categorized findings and a summary of implications. Use when a user wants to compare an old and new version of a document, check whether a spec matches an implementation, audit a policy for missing coverage, or identify what changed between two states. Triggers include "compare these two docs", "what's missing from this", "what changed between these versions", "find the gaps", "does this spec match this document", or when a user shares two documents and asks what is different or inconsistent.
Reads an Open Roles list and a Candidates list from the current SharePoint site and generates a self-contained HTML hiring dashboard for Zava Industries. The dashboard includes executive metrics, a D3 Sankey diagram of candidate flow through pipeline stages, risk callouts (stale candidates, starved roles, bottleneck stages), and a breakdown table by role. Use when asked for a hiring pipeline report, pipeline status, recruiting dashboard, or any summary of open roles and candidates.
Sets up persistent eval suites for any AI in SharePoint skill and runs self-healing improvement loops on demand. Use this when setting up evals for a skill for the first time, or when the user says "improve [skill-name]", "fix [skill-name]", or "run evals for [skill-name]" to fix a skill that has drifted, started failing, or needs to handle new patterns.
Generates a comprehensive knowledge base health report covering corpus overview, knowledge decay, gap status, ingestion activity, expert coverage, and recommended next actions. Triggers when an admin asks for a knowledge base report, status update, or health check.
Crafts high-performing LinkedIn posts from any topic, story, announcement, or idea. Use this skill when a user needs to write, draft, improve, or optimize a LinkedIn post — including personal stories, product announcements, thought leadership, professional milestones, or content repurposing. Triggers include requests to "write a LinkedIn post about", "help me announce this on LinkedIn", "make this sound better for LinkedIn", or when a user provides a transcript, article, achievement, or idea they want to share professionally.
Create beautiful, functional SharePoint list and library formatters using JSON. Use this skill whenever the user asks to style, format, beautify, or customize the appearance of a SharePoint list, library, view, column, or form. Trigger phrases include "style my list", "format my list", "make my list pretty", "make my library beautiful", "style my library", "customize my view", "format my columns", "card layout", "tile view", "add icons to my list", "color code my list", "conditional formatting", "progress bars", or any mention of SharePoint JSON formatting. Also trigger when the user references specific formatting patterns like status indicators, data bars, people cards, Gantt charts, KPI dashboards, or hover cards in a SharePoint context. This skill produces English-language instructions only — no code generation. It teaches the agent what is possible and how to describe formatters so a downstream tool can apply them.
Logs unanswered questions to the Knowledge Gaps list and routes them to a subject matter expert. Triggers when the assistant cannot answer a question from the Knowledge Base library. Checks the Expert Directory for a matching expert and assigns the gap automatically.
Transforms raw video or audio transcripts into detailed, structured meeting summaries formatted for SharePoint. Handles messy auto-generated transcripts including unlabeled speakers, filler words, and transcript artifacts. Extracts discussion threads, decisions, action items, key quotes, and next steps. Use when a user pastes or shares a meeting transcript and wants polished, shareable notes. Triggers include "summarize this meeting transcript", "create notes from this recording", "turn this transcript into meeting notes", "write up this call", or when a user shares raw transcript text.
A self-evaluating iterative agent loop that pursues a goal through structured cycles of Reason, Act, Look, Probe, and Harden until the goal is confidently achieved. Use when a task requires iterative refinement, quality assurance, or when "good enough" isn't good enough. Works for any goal — document generation, data extraction, content processing, analysis, or creative work.
# Brand Style Skill — Template Use this skill whenever creating any visual output, document, web content, presentation, table, list, or interface element for **[Your Organization]**. This skill ensures all outputs are visually consistent with the brand. > **How to use this template:** Replace every `[placeholder]` and the example values below with your organization's actual brand values. Delete this callout when done. --- ## Brand Identity [Your Organization] is a [brief description — indus
Generate engaging YouTube video descriptions from video transcripts. Use this skill whenever the user wants to create a YouTube description, write a video description, summarize a video for YouTube, or draft copy for a YouTube upload. Also trigger when the user provides a transcript and mentions YouTube, video publishing, or video SEO. Works with raw transcripts, cleaned transcripts, or transcript files in any format.
Turns a rough idea, stakeholder request, or email thread into a structured project brief with a clear problem statement, goals, success criteria, scope, stakeholders, and risks. Asks clarifying questions one at a time to fill gaps, then delivers a complete SharePoint-ready brief. Use when a user wants to scope a new project, formalize a request that came in through email or conversation, or create a brief before moving into full design or planning. Triggers include "write a project brief", "turn this email into a brief", "help me scope this project", "I need to document this request", or when a user describes a rough idea and wants a structured starting point.
Performs comprehensive analysis of a SharePoint project site by systematically reading ALL lists and ALL documents using AI in SharePoint tools, then producing a tailored, data-driven analysis. Use when asked to analyze a site holistically, create scorecards, audit project health, prepare meeting briefings, assess risks, or perform any exhaustive site-wide analysis. Works with any SharePoint team site.
Applies the forest-style brand system to any visual output, document, web content, presentation, table, list, or interface element. Enforces the color palette, typography, spacing, component styles, and voice guidelines to ensure consistent brand expression. Use this skill whenever creating or reviewing content that must conform to forest-style brand standards.
Matches open Knowledge Gaps items to subject matter experts in the Expert Directory and assigns them. Triggers when asked to find experts, route open questions, or review unassigned gaps.
Extracts tacit knowledge from any input — typed text, transcripts, emails, documents, or Slack threads — and writes it into the Knowledge Base library as structured markdown. Triggers when someone shares knowledge directly, pastes content, or uploads a file to the Submissions library. Resolves matching open Knowledge Gaps items automatically.
--- name: decision-log description: Extracts and formats Decision Records from video or audio transcripts, capturing the full context of each decision: the problem being solved, options that were considered, who made the call, the rationale, concerns or dissent raised, and any conditions or follow-on actions. Produces structured, durable Decision Records rather than a meeting narrative. Use when a user wants to document the reasoning behind decisions made in a recorded meeting, create an audit t
Systematically edits Markdown documents — READMEs, skill files, and demo guides — using seven sequential sweeps. Each sweep focuses on one quality dimension so nothing gets missed. Use when a document needs to be clearer, tighter, or easier to act on. Triggers include "edit this", "clean this up", "review my README", "improve this skill", "tighten this up", or when a document feels long, vague, or hard to follow. Does NOT write or suggest code.
Distills long documents, reports, meeting transcripts, or briefing materials into tight one-page executive summaries formatted for SharePoint. Surfaces the core situation, key findings or decisions, recommendations, and what the reader needs to do or know. Use when a user wants to condense a long document for a leadership audience, create a TL;DR for a report, or produce a standalone summary someone can read in under two minutes. Triggers include "summarize this for leadership", "write an exec summary", "make this into a one-pager", "TL;DR this document", or when a user shares a long document and asks for a shorter version.
Optimize any AI in SharePoint skill by iteratively running it against test inputs, scoring outputs with binary evals, mutating the prompt to fix failures, and keeping improvements. Adapts Karpathy's autoresearch methodology to AI in SharePoint's multi-turn conversation architecture.
Builds structured FAQ pages from source material such as documents, process guides, policies, product descriptions, or topic briefs. Anticipates questions from the reader's perspective, groups them into themes, writes clear Q&A pairs, and delivers SharePoint-ready Markdown. Use when a user wants to create an FAQ from an existing document, prepare a help page for a new process or policy, or capture anticipated questions before a launch or rollout. Triggers include "create an FAQ from this", "build a FAQ page", "what questions will people ask about this", "turn this into a FAQ", or when a user wants to surface common questions from a document or topic.
Reads vendor, date, and spend data from the Expenses library on the current SharePoint site and generates a self-contained interactive HTML expense report for a specified fiscal quarter. Use when asked for a quarterly expense summary, Q1/Q2/Q3/Q4 financial summary, expense report, or spend analysis by period.