deep-research
Deep Research breaks down complex queries into atomic sub-questions, then systematically crawls multiple sources, extracts verifiable claims, and resolves contradictions. The skill delivers structured reports with confidence scoring, source attribution, and explicit gap flagging—ensuring every finding is traceable and conflicts are surfaced rather than hidden.
Deep Research conducts multi-phase autonomous research with claim verification and inline citations across 8+ sources.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-19
Deep Research conducts multi-phase autonomous research with claim verification and inline citations across 8+ sources. Deep Research breaks down complex queries into atomic sub-questions, then systematically crawls multiple sources, extracts verifiable claims, and resolves contradictions. The skill delivers structured reports with confidence scoring, source attribution, and explicit gap flagging—ensuring every finding is traceable and conflicts are surfaced rather than hidden.
Use it when
- Yes.
- Deep Research generates structured reports organized by sourcing tiers and quality gates.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Similar skills
Install
shobcoder/shob/research-knowledge · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does deep-research conduct thorough, multi-source research with verified claims and inline citations?
Deep Research breaks down your query into atomic sub-questions, then systematically crawls multiple sources to extract verifiable claims. Each finding includes inline citations and source attribution, so you can trace every assertion back to its origin. The skill prioritizes verified information and surfaces contradictions rather than hiding them.
Can deep-research verify claims across multiple sources?
Yes. Deep Research detects and resolves conflicting information across sources by applying confidence scoring to each claim. When sources disagree, the skill flags the conflict explicitly, shows you which sources support which positions, and helps you understand the strength of evidence behind competing claims.
What does a deep-research structured intelligence report include?
Deep Research generates structured reports organized by sourcing tiers and quality gates. Reports include verified findings with citations, confidence scores for each claim, explicit gap flagging for unverified or disputed information, and source ranking so you know which authorities contributed to each conclusion.
How does deep-research decompose complex questions into sub-questions?
Deep Research breaks down complex queries into smaller, atomic sub-questions that are easier to research systematically. Each sub-question is answered individually with its own sources and citations, then the answers are synthesized into a coherent whole—ensuring no angle is overlooked.
Does deep-research identify research gaps and flag unverified claims?
Yes. Deep Research explicitly identifies gaps in available evidence and flags claims that lack sufficient verification or remain disputed across sources. This transparency helps you understand the limits of current knowledge on your topic and spot areas where further investigation is needed.
What license does deep-research use?
Deep Research is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Deep Research — GOD MODE
Trigger
/deep-research <query> or when user says "research this deeply", "go deep on",
"full research report on", "investigate this thoroughly".
Core Philosophy
> Raw search results are noise. Verified synthesis is signal. > Every claim needs a source. Every conflict needs a resolution. > A great deep research report is a structured intelligence brief, not a search summary.
Architecture
Query
└── Phase 1: Decompose → Sub-questions
└── Phase 2: Parallel Search → Raw Sources
└── Phase 3: Crawl & Extract → Claims
└── Phase 4: Cross-Reference → Verify / Conflict
└── Phase 5: Synthesize → Report
└── Phase 6: Quality Gates → Deliver
Phase 1 — Query Decomposition
Break the user's
(truncated - see the full file via the links below)
File tree — 1 file
skills/research-knowledge/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Conduct thorough, multi-source research with verified claims and inline citations”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Deep Research pulls together information from multiple web sources to build comprehensive, cited reports. It breaks topics into focused sub-questions, searches across available tools, reads key sources in depth, and synthesizes findings into structured reports with full attribution. Ideal for competitive analysis, due diligence, market sizing, or any investigation requiring evidence-backed conclusions.
Youmind Deep Research automates in-depth topic investigation, producing detailed reports with citations, key findings, and actionable insights saved to your YouMind board. Specify your research question for best results—the skill handles source gathering, analysis, and cross-referencing across the web.
Web Research provides access to neural search and web scraping through x402-protected endpoints, combining Exa's semantic capabilities with Firecrawl's extraction power. Use it for deep investigations, finding similar content, extracting clean text from blocked sites, and crawling multiple pages—each with transparent per-task pricing starting at $0.002.
Research Wiki maintains a structured, project-level knowledge base that grows smarter as you add papers, test ideas, run experiments, and capture findings. Every entry connects through typed relationships—papers extend or contradict each other, ideas get tested by experiments, claims gain proof status—so your research compounds rather than scatters. Initialize once, keep it current, query it to avoid re-deriving insights.
Lesson Study Cycle Designer structures the Japanese jugyō kenkyū process for teacher teams investigating student learning challenges. It generates a research theme, detailed cycle plan with meeting agendas, a research lesson designed for collaborative observation, and protocols focused on case students. The skill grounds itself in evidence from Stigler & Hiebert, Lewis, Perry & Murata, Dudley, and Takahashi & McDougal on how teachers develop shared professional knowledge through structured cycles of planning, teaching, observing, and analysing.
This skill builds ordered question progressions designed to develop concepts through dialogue rather than direct instruction. It distinguishes genuine Socratic inquiry—which surfaces assumptions and builds understanding through student reasoning—from leading questions that funnel toward predetermined answers. The skill generates branching follow-up paths based on likely student responses, anticipating dialogue contingencies that teachers typically cannot construct in real time.