Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Deep Research

A P0–P7 research pipeline with parallel subagents, a locked citation registry, source-type governance and mandatory counter-review for traceable reports.

Content & WritingAdvanced★ 1,323⑂ 212AI score 10/10Last updated: Aug 8, 2026

What it does

  • Breaks a research question into 4–6 tasks (3–4 in Lightweight mode) and dispatches them to expert-persona subagents in parallel groups of three.
  • Keeps raw search results inside subagent contexts; the lead agent drafts only from distilled notes (~60–70% context savings).
  • Classifies every source by type (official, academic, secondary-industry, journalism, community) and by accessibility, then enforces quality gates (min approved sources, ≥5 unique domains, ≥30% official, ≤25% single-source share) before it enters the citation registry.
  • Sets an explicit AS_OF date, downgrades stale evidence, requires a counter-review pass that must surface ≥3 issues, and verifies every [n] against the approved registry.
  • Enterprise mode adds six-dimension data collection plus SWOT, weighted competitive-barrier scoring, an 8-category risk matrix, a scorecard and a 7-chapter report template.

Who it's for

  • Analysts, consultants and strategists producing market, industry or competitive reports.
  • Policy, investment and due-diligence writers who need every claim traceable to a source.
  • Researchers and grad students who want structural guardrails against fabricated URLs and numbers.

Examples

  1. "Write a report on the B2B SaaS payments market" → 5 parallel tasks, registry meeting the official-source quota, 3,000–8,000 word report with confidence markers.
  2. "Competitive analysis of Company X" → Enterprise mode: six data dimensions, SWOT, risk matrix, 7-chapter report with source index.
  3. "Quick survey of RAG vendors for tech selection" → Lightweight mode with 3 tasks, 2,000–4,000 words plus a Key Controversies section.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/deep-research/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the deep-research folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/deep-research/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/deep-research ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal.
  2. Clone the repository: git clone https://github.com/daymade/claude-code-skills.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r claude-code-skills/deep-research ~/.claude/skills/
  5. Confirm the references/ subfolder came along — it holds the report templates and quality checklists the skill loads.
  6. Restart Claude Code and prompt with something like "write a research report on …" to trigger it.
  7. Make sure web search (and ideally web fetch plus subagent dispatch) is enabled; without search the skill stops at phase P0.
View source on GitHub ↗License: MIT