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
npx skills add genspark-ai/genoffice --skill deep-research -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/deep-research/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/deep-research/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill deep-research -a codex2Manually: put the files in place
.agents/skills/deep-research/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill deep-research -a cursor2Manually: put the files in place
.cursor/skills/deep-research/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install genspark-ai/genoffice skills/recommended/deep-research2Manually: put the files in place
.github/skills/deep-research/SKILL.md1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill deep-research -a gemini-cli2Platform CLI
gemini skills install https://github.com/genspark-ai/genoffice --path skills/recommended/deep-researchManually: put the files in place
.devin/skills/deep-research/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.