Skills/documents/faq-building/SKILL.md
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.
npx skillsauth add zrosenfield/sharepoint-ai-skills faq-buildingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill reads source material and produces structured FAQ pages from the reader's perspective — anticipating what people will actually ask, not just restating what the document says.
Scope: Produces prose and Markdown only. Does not write code, scripts, or formulas.
Who is asking these questions? The audience determines which questions appear and how answers are phrased. Ask if not specified:
What is the source material? Confirm what the FAQ should be built from. Common inputs:
Is there anything out of scope? If the source covers more than the FAQ should, confirm what to exclude. For example: "Build a FAQ for the new onboarding process only — not the broader HR policy."
If all three are clear from context, proceed without asking.
Work through the source with the reader's eye, not the author's. For each section or topic, generate candidate questions by asking:
Confusion questions — What in this section would a first-time reader misunderstand? Where is the wording ambiguous?
"What about me?" questions — What will readers wonder about their own situation? ("Does this apply to part-time employees?" "What if I already have an account?")
Process questions — How do I do this? What happens after? Who do I contact? What if something goes wrong?
Exception questions — What are the edge cases? What happens if the normal path doesn't apply?
Policy and authority questions — Who decides this? Can this be waived? Is this required or optional?
Motivation questions — Why are we doing this? Why does it work this way?
Collect all candidate questions before filtering. It is easier to cut good questions than to invent missing ones.
Group questions into themes before writing answers. Good themes are:
Typical theme patterns:
For process/procedure FAQs: Overview → Getting Started → Day-to-Day Use → Troubleshooting → Contacts and Escalation
For policy FAQs: What Is This → Who Is Affected → What Changes → Exceptions and Edge Cases → What to Do Next
For product/feature FAQs: What Is It → How It Works → How to Get Access → Common Issues → Getting Help
Use the pattern that fits the content. Do not force content into a pattern that does not fit.
Aim for 5–15 questions total. Fewer than five suggests the source material is too thin; more than fifteen suggests the FAQ needs to be split into multiple pages or the questions need pruning.
Write questions in the voice of the reader, not the author. Use plain, natural language:
Use first or second person in questions: "I", "my", "you", "your". Questions starting with "What", "How", "Can", "Do", "When", and "Who" are almost always clearer than questions starting with "Is it possible to" or "In the event that".
Lead with the direct answer. The first sentence should answer the question. Context and explanation follow.
Be complete but not exhaustive. An FAQ answer should resolve the question, not reproduce the source document. If the full answer requires the user to read a linked document, say so — but give them enough to orient first.
Use the second person. Write "You will need to..." not "Users are required to..."
Acknowledge genuine complexity. If an answer depends on the reader's situation, say so: "If you are a full-time employee, [X]. If you are a contractor, [Y]."
End with a pointer when relevant. If the user may need more than the answer provides, end with: "For more detail, see [link/document]" or "Contact [person/team] if your situation is not covered here."
# Frequently Asked Questions: [Topic]
*Last updated: [Date if known]*
---
## [Theme 1 Name]
**[Question]**
[Answer]
**[Question]**
[Answer]
---
## [Theme 2 Name]
**[Question]**
[Answer]
---
## Still have questions?
[Contact information, escalation path, or link to additional resources — if available from source material]
Use bold for questions rather than heading levels. This renders cleanly in SharePoint and keeps the page scannable.
Before delivering, verify:
Deliver:
testing
--- 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
tools
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.
development
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.
development
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.