Deep Research skill
Deep Research Skill for Claude Code
A deep research skill for Claude Code: multi-phase search, claim verification and cited reports in Markdown, HTML and PDF
- 1,201 ★ on the repository
- Last commit
Extended access
Why this level
- Makes many web requests and runs Python scripts
- Writes report files to the home directory
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/deep-research-skill-for-claude-codeDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Makes many web requests and runs Python scripts
- Writes report files to the home directory
This is third-party code. Review the repository files before installing.
What it does
The skill runs research through a multi-phase pipeline: scoping, planning, parallel retrieval with sub-agents, triangulation, outline refinement, synthesis, critique, refinement and packaging. Four depth modes range from a quick scan to an exhaustive report. Sources and citations are persisted to disk, so they survive context compaction, and long reports continue via new agents. Bundled Python scripts validate report structure, score source credibility and detect fabricated links and DOIs.
Who it is for. For analysts, researchers and managers who need a thorough report with verifiable sources.
Good fit when
- You need to compare technologies or options for an important decision
- You need a state of the art review with a bibliography
- You need a report where every major claim has several sources
Not a fit when
- One or two searches are enough
- The task is debugging code rather than research
Example request
deep research in deep mode: compare PostgreSQL vs Supabase for our stackLimitations
Deep modes take tens of minutes and use many tokens. For better search the author recommends search-cli with Brave, Serper, Exa, Jina or Firecrawl keys; otherwise built-in WebSearch is used. PDF output needs WeasyPrint. The README states MIT, but GitHub detects no license file.
How to disable. Delete the ~/.claude/skills/deep-research folder.
FAQ
Where are reports saved?
In ~/Documents under a folder with the topic and date: Markdown as the main file, plus HTML and PDF.
Are API keys needed?
Not for basic use. Keys are only needed for extra search through search-cli.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code skill that turns the agent into a researcher: multi-step source collection, citation verification, and a wiki report that grows session by session
Google Scholar Skills
Google Scholar Skills for Claude Code
Six skills and a gs-researcher agent: Claude Code searches Google Scholar, tracks citations, fetches full-text links and exports to Zotero
CNKI Skills
CNKI Skills for Claude Code
A Claude Code skill set that drives CNKI through Chrome DevTools MCP: search papers, browse journals, download PDFs and export to Zotero
Skill that adds /ask-perplexity to Claude Code, Codex and Cursor for source-backed web answers via the Perplexity API
A web research skill: SearXNG searches, Camofox reads pages and CloakBrowser opens sites that check their visitors
Paper search across five databases with deduplication, citation checks and RIS or BibTeX export for Claude Code and Codex
README in short
The README covers installing by cloning into the skills directory and optional search-cli setup. It describes depth modes with durations, pipeline phases, output formats and quality standards: source counts, section length and automated report and citation checks. It also shows the skill layout and version history.
README badge
Original SKILL.md
--- name: deep-research description: Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches. --- # Deep Research ## Core Purpose Deliver citation-tracked research reports through a structured pipeline with evidence persistence, source identity management, claim-level verification, and progressive context management. **Autonomy Principle:** Operate independently. Infer assumptions from context. Only stop for critical errors or incomprehensible queries. Surface high-materiality assumptions explicitly in the Introduction and Methodology rather than silently defaulting. --- ## Decision Tree ``` Request Analysis +-- Simple lookup? --> STOP: Use WebSearch +-- Debugging? --> STOP: Use standard tools +-- Complex analysis needed? --> CONTINUE Mode Selection +-- Initial exploration --> quick (3 phases, 2-5 min) +-- Standard research --> standard (6 phases, 5-10 min) [DEFAULT] +-- Critical decision --> deep (8 phases, 10-20 min) +-- Comprehensive review --> ultradeep (8+ phases, 20-45 min) ``` **Default assumptions:** Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years. --- ## Workflow Overview | Phase | Name | Quick | Std | Deep | Ultra | |-------|------|-------|-----|------|-------| | 1 | SCOPE | Y | Y | Y | Y | | 2 | PLAN | - | Y | Y | Y | | 3 | RETRIEVE | Y | Y | Y | Y | | 4 | TRIANGULATE | - | Y | Y | Y | | 4.5 | OUTLINE REFINEMENT | - | Y | Y | Y | | 5 | SYNTHESIZE | - | Y | Y | Y | | 6 | CRITIQUE | - | - | Y | Y | | 7 | REFINE | - | - | Y | Y | | 8 | PACKAGE | Y | Y | Y | Y |