deep-research
Comprehensive research reports generated through iterative searching and analysis.
Install
mkdir -p .claude/skills/deep-research-satorykono && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18584" && unzip -o skill.zip -d .claude/skills/deep-research-satorykono && rm skill.zipInstalls to .claude/skills/deep-research-satorykono
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when asked for \"deep research\", \"thorough analysis\", \"comprehensive report\", \"investigate\", \"due diligence\", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.Key capabilities
- →Clarify research scope
- →Write research briefs
- →Draft from existing knowledge and mark uncertainty
- →Red-team drafts using a critique framework
- →Run targeted research with reflection
- →Score sources and cite claims
How it works
This skill conducts complex research by iteratively clarifying scope, drafting, critiquing, and refining findings with targeted searches and source evaluation. It produces a structured report.
Inputs & outputs
When to use deep-research
- →Perform technical due diligence
- →Compare technology stacks
- →Conduct state-of-art survey
- →Research architecture decisions
About this skill
Conducting Deep Research
Source Of Truth
- Root runtime contract:
../../../AGENTS.md - Project rules:
../../../docs/00-project/RULES.md - Requirements:
../../../docs/01-requirements/REQUIREMENTS.md - Accepted ADRs:
../../../docs/02-architecture/decisions - Normative index:
../../../docs/00-project/NORMATIVE_SOURCES.md
Workflow
Use this skill for complex research, comparisons, due diligence, state-of-art surveys, or questions requiring multiple sources. Do not use it for simple lookups.
- Clarify scope only when the topic, timeframe, geography, or success criteria are ambiguous.
- Write a research brief with topic, scope, key questions, constraints, and response language.
- Draft from existing knowledge and mark uncertainty.
- Red-team the draft using references/critique-framework.md.
- Run targeted research with reflection after each search; use references/search-patterns.md for query selection.
- Score sources, track contradictions, and cite claims using references/source-evaluation.md.
- Refine the draft until claims are sourced, unsupported claims are removed, and contradictions are explicit.
- Evaluate quality; repeat critique/research/refinement up to three cycles when the answer is still below decision quality.
- Finalize using references/report-templates.md.
Output Requirements
- Executive summary.
- Findings organized by research question.
- Methodology and source confidence.
- Limitations, gaps, and unresolved contradictions.
- Source list with confidence indicators.
User Interaction
Ask for user input only when the scope is genuinely ambiguous, sources conflict in a way that requires user judgment, or the user must choose between additional research and finalizing with known limitations.
When not to use it
- →Simple lookups
- →When the answer is below decision quality after three cycles
Limitations
- →Not for simple lookups
- →Requires iterative refinement up to three cycles
- →User input is needed for ambiguous scope or conflicting sources
How it compares
This skill employs a structured, iterative research methodology with explicit critique and source scoring steps, which differs from a single search query or basic information retrieval.
Compared to similar skills
deep-research side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| deep-research (this skill) | 0 | 17d | No flags | Advanced |
| exa-search | 9 | 7mo | Review | Beginner |
| search-specialist | 3 | 3mo | No flags | Advanced |
| ddgs | 0 | 3mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by SatoryKono
View all by SatoryKono →You might also like
exa-search
benjaminjackson
Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.
search-specialist
sickn33
Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.
ddgs
itsmeadarsh2008
Use when an agent needs to search the web, find images/news/videos/books, or extract content from a URL. Covers the ddgs Python library, CLI, and MCP server integration.
deep-research
inuishan
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
market-research-reports
davila7
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.
competitive-intelligence
anthropics
Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".