HelpUDoc

Plan, review, and then assemble a stakeholder-ready dashboard package from the current analysis run, with a native interactive canvas experience.

Data analysis skill hub. Routes to the right specialist subskill depending on the request — exploration, query writing, end-to-end analysis, visualization, validation, dashboard planning plus assembly, or recurring snapshot refresh.

End-to-end data analysis — from a quick metric lookup to a formal stakeholder report. Combines schema discovery, SQL execution, optional visualization, and an evidence-based summary. Use for general "analyze / what's happening with…" requests.

Create, edit, redline, comment on, and visually verify `.docx`, Word, and Google Docs-targeted document artifacts. Use for Word documents, `.docx` files, document creation, document edits, tracked changes, comments, render QA, and Google Docs-ready local DOCX generation.

Create stunning, animation-rich browser-native HTML presentations. Use only when the user explicitly wants an HTML/web presentation or animated interactive browser deck. Do not use for `.ppt`, `.pptx`, PowerPoint, Google Slides, native deck creation, native deck editing, deck templates, or PPTX conversion/export requests; use the `pptx` skill for those.

Work with PDF documents safely, including querying existing PDFs and creating simple image-based PDFs from workspace images.

Research a company or person and get actionable sales intel. Start with internal context, then expand to current external research. Prefer tagged workspace files, Drive docs, Gmail history, and Sheets context before broader web research.

Prepare for a sales call with account context, attendee research, and a suggested agenda. Works standalone with user input and targeted web research, and becomes Google Workspace-first when Calendar, Gmail, Drive, Sheets, and tagged workspace files are available.

Process call notes or a transcript to extract action items, draft a follow-up email, and generate an internal summary. Prefer Gmail, Drive, Calendar, and tagged files first, then hand off to proposal or presentation workflows only when the user actually needs them.

Research competitors and build a seller-friendly brief or battlecard. Prefer internal docs and tagged workspace files first, then use current web research to refresh claims and market context.

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, and becomes Google Workspace-first when Calendar, Gmail, Drive, Sheets, and tagged workspace files are connected.

Research a prospect then draft personalized outreach. Prefer Gmail, Drive, Sheets, and tagged files before web search, and create a Gmail draft when possible.

Analyze a document table of contents or outline to infer structure, coverage, gaps, and recommended improvements before deeper reading or drafting.

Use this skill when a spreadsheet file is a primary input or output. This includes on-demand questions about tagged .xlsx, .xlsm, .csv, or .tsv files, as well as creating, editing, fixing, formatting, cleaning, or converting spreadsheet artifacts. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration and no local spreadsheet inspection is needed.

Create, edit, inspect, render, and verify PowerPoint `.pptx` and Google Slides-targeted decks. Use for any `.ppt`, `.pptx`, PowerPoint, Google Slides, native slide deck, pitch deck, presentation template, existing deck edit, local PPTX output, or Google Slides-ready deck generation. This skill owns PPTX-related work; do not route those requests to `frontend-slides`.

Generate tailored sales assets (landing pages, decks, one-pagers, workflow demos) from your deal context. Describe your prospect, audience, and goal — get a polished, branded asset ready to share with customers.

Produce a sourced research report in the user's language using a structured, evidence-first workflow. Supports quick, standard, deep, and exhaustive research modes. Prioritizes evidence quality, entity disambiguation, claim verification, contradiction checking, uncertainty handling, and clear synthesis before final writing.

Profile and explore a dataset — inspect source options, schema, join keys, filters, and connector choice — before writing any SQL or analysis.

Write and refine optimized, connector-specific SQL — BigQuery or DuckDB — following best practices for readability, performance, and correctness.

Refresh a stable BigQuery-backed Parquet snapshot in the workspace and regenerate recurring dashboard or report artifacts from DuckDB.

QA an analysis before sharing — check methodology, assumptions, SQL logic, calculations, visualizations, narrative, and statistical pitfalls.

Turn validated SQL query output into publication-quality Plotly charts. Select the right chart type, apply design best practices, and produce chart artifacts.

Create, revise, or polish a professional Statement of Work (SOW) / proposal for data, analytics, AI, or cloud modernization. Use when asked to draft a proposal, improve an existing proposal, produce a formal SOW, or convert rough proposal notes into a consistent workspace artifact and optional DOCX-ready format.

Work with image files safely; do not decode them as text, use image URLs for referencing, and use Gemini only for generation or editing requests.

Generate a weighted sales forecast from CSV, Sheets, or CRM data. This skill remains CRM-ready, but should succeed with Sheets or pasted pipeline context instead of assuming a connected CRM.

Analyze pipeline health from CSV, Sheets, or CRM data. This skill should stay usable for weekly reviews even when the team operates from Sheets or exports rather than a live CRM.

Use this skill for LangGraph questions by locating and summarizing official docs.