Skip to main content
skill CX Codex

deep-research · genspark-ai — Claude Code skill: what it does, how to install

deep-research splits research topics into targeted sub-questions, verifies figures across independent sources, and exports a cited Word document.

Apache-2.0 ★ 12,746 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add genspark-ai/genoffice --skill deep-research -a claude-code
Open on GitHub

What deep-research does

This skill turns Claude Code into an analytical researcher for industry analysis, competitor audits, and fact checking. Instead of dropping a brief chat summary, the agent decomposes your objective into 3 to 6 sub-questions covering current players, market metrics, trends, and uncertainties.

Verification follows a strict cross-checking routine. The agent executes at least two search rounds per sub-question with different keywords. Dates, figures, and names are marked confirmed only when two distinct sources agree. If sources clash, the skill highlights the discrepancy directly. Missing facts are labelled "could not be verified" without inventing citations.

The final output is saved as a Word document. It includes an executive summary with at most 5 conclusions, dedicated evidence sections, risk assessments, and a numbered reference list with URLs. The skill expects search and document creation tools configured in your agent environment.

What it helps with

  • produce a competitor comparison report formatted as a Word document
  • verify key figures and dates against two independent online sources
  • structure industry research into sub-questions with citations
  • document discrepancies when public data points disagree

Example prompts for the agent

  • Research the leading products in this space and produce a comparison report.
  • Verify the key figures in this material and note any discrepancies.
  • Run an industry analysis on AI code assistants and generate a Word report.

How to install deep-research

1Skills CLI (Vercel)

npx skills add genspark-ai/genoffice --skill deep-research -a claude-code

2Manually: put the files in place

~/.claude/skills/deep-research/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/deep-research/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about deep-research

How do I install deep-research in Claude Code?

Run npx skills add genspark-ai/genoffice --skill deep-research -a claude-code in your terminal. Alternatively, place the specification file at ~/.claude/skills/deep-research/SKILL.md.

What document structure does deep-research generate?

It compiles a Word file with an executive summary capped at 5 conclusions, followed by sub-question analyses with evidence, a risks section, and a numbered URL reference list.

How does deep-research handle conflicting facts?

Every claim requires confirmation from at least two independent sources. If sources disagree, the report records the contradiction, while unverified claims are labelled "could not be verified".

Source text

SKILL.md · Apache-2.0
---
name: deep-research
description: Run multi-round searches with cross-checking and produce a research report with cited sources, delivered as a Word document
category: business
scenarios: Competitor research | Industry analysis | Fact checking
quickPrompts: Research the leading products in this space and produce a comparison report | Verify the key figures in this material
metadata:
  version: 1.0.0
---

You are a deep-research specialist. Unlike a quick research answer, you deliver a complete report document, not a paragraph of reply.

## Workflow

1. Break the question down: split the research goal into 3-6 sub-questions (current state / players / data / trends / controversies) and list them for the user.
2. For each sub-question, search the web with the search tool available here in several rounds: at least two different sets of keywords per sub-question, cross-checking different sources. A number, date or entity name counts as reliable only when at least two independent sources agree; where they conflict, report the disagreement as it is.
3. Build the document as a Word document with the document tools available here:
   - Structure: executive summary (at most 5 hard conclusions), one section per sub-question (conclusion first, then evidence and data), risks and uncertainties, references (every URL listed).
   - Every key factual sentence carries a source number that maps to the reference list at the end.
4. If something cannot be found, write "could not be verified"; never fabricate a source. Cite every source.

© genspark-ai · Apache-2.0 · genspark-ai/genoffice

Similar skills

All skills for Office documents →

deep-research by other authors comes first.

deep-research Imbad0202 deep-research runs a team of 13 agents through academic research on any topic, from framing the question to an APA 7.0 report. CX Codex +1 8,200installs deep-research affaan-m deep-research — a skill for Claude Code, Codex, Cursor and other agents that builds cited research reports from 15–30 sources using firecrawl and exa MCP tools. Triggers on phrases like "research", "deep dive", or "competitive analysis". CX Codex +1 7,000installs deep-research bytedance deep-research — a skill for Claude Code runs source-based research with current evidence and cross-checks. It fits questions that need more than one search. CX Codex +1 2,800installs deep-research 199-biotechnologies deep-research — a skill for Claude Code, Codex, Cursor and other agents that runs a multi-phase research pipeline and produces a fully cited report with per-claim verification. CX Codex +1 10,500installs deep-research ruvnet deep-research orchestrates multi-phase research using web search, codebase analysis, and memory storage. It generates structured findings with evidence ratings for complex topics. CX Codex +1 894installs content-research-and-sourcing social-media-skills content-research-and-sourcing is a Claude Code skill that checks stats and citations in drafts before publication, tracing numbers to primary sources and flagging fabricated AI references and stale figures. CX Codex +1 1,300installs research-claim-map lyndonkl research-claim-map — a skill for Claude Code and Codex that systematically investigates claims and triangulates sources. Runs during fact-checking, due diligence workflows, and conflicting evidence reviews. CX Codex +1 101installs nature-paper2word Yuan1z0825 nature-paper2word is a Claude Code skill that compiles academic Markdown into compliant Word files. It triggers when preparing submission-ready DOCX papers with OMML formulas and citations. CX Codex +1 1,400installs academic-deep-research kesslerio academic-deep-research — a skill that runs multi-step research: two search cycles per theme, an evidence hierarchy and APA 7 citations. Useful for literature reviews and competitive intelligence. CX Codex +1 562installs research Alireza Rezvani research is a Claude Code skill that routes research requests to specialist skills or runs a general search workflow. It shows the routing choice and lets the user override it. CX Codex +1 348installs parallel-deep-research parallel parallel-deep-research runs multi-step deep research jobs using parallel-cli. Use it when you need an exhaustive markdown report with citations rather than a quick web search. CX Codex +1 16,400installs

From the same set65

The whole set →
resume-polisher resume-polisher rewrites a resume against a job description, turns experience into lines with numbers, and returns a Word file. CX Codex +1 ★ 12,746repo stars data-analyst data-analyst transforms raw tables into structured Excel workbooks featuring dynamic formulas, charts, and plain-language takeaways. CX Codex +1 ★ 12,746repo stars slide-planner The slide-planner skill drafts a slide-by-slide narrative outline, then builds a PowerPoint deck after you approve it. Use it for progress updates, pitch decks, or training sessions. CX Codex +1 ★ 12,746repo stars weekly-report weekly-report turns rough progress notes into a structured weekly or monthly report and returns a Word document you can hand in. CX Codex +1 ★ 12,746repo stars qc-geometry The qc-geometry prompt fixes slide geometry defects backed by audit findings. Use it to check a slide when the model cannot inspect its rendered image. GP ChatGPT ★ 12,746repo stars contract-drafter contract-drafter turns a rough brief into a Word contract draft, then lists the clauses that could bite you before signing. CX Codex +1 ★ 12,746repo stars qc-visual qc-visual inspects slide layouts to fix overlaps, bad contrast, and alignment issues from screenshots. Keeps original copy, palettes, and fonts intact. GP ChatGPT ★ 12,746repo stars shape-image The shape-image prompt guides Claude Code in adding shapes, labels, and in-cell trend charts to spreadsheets. Use it to annotate key figures or show a data pattern without adding chart objects. GP ChatGPT ★ 12,746repo stars

Project sponsors

Companies that keep this analytics open