deep-research

name	deep-research
description	Multi-step autonomous research methodology for deep investigation tasks with structured synthesis
version	1.0.0
model	sonnet
invoked_by	both
user_invocable	true
tools	["Read","Write","WebSearch","WebFetch","Bash","Grep","Glob"]
agents	["researcher","planner","architect"]
category	Research & Investigation
tags	["research","deep-research","investigation","synthesis","multi-step","autonomous"]
best_practices	["Define explicit scope and success criteria before starting","Use multiple independent sources to cross-validate findings","Synthesize into actionable insights, not just summaries","Validate findings with primary sources"]
error_handling	graceful
streaming	supported
source	builtin
trust_score	100
provenance_sha	aa4a7a8cd5041d32

Deep Research

Deep Research Skill — Multi-step autonomous research methodology for structured, evidence-based investigation and synthesis. - 5-phase autonomous research workflow (Scope → Search → Synthesis → Validation → Report) - Multi-source evidence gathering with cross-validation - Structured output with citations and confidence ratings - Gap detection and iterative depth expansion - Actionable recommendation generation

When to Use

• Task requires investigation across multiple sources before drawing a conclusion
• Evidence-based answers needed, not pattern-matched guesses
• Question spans multiple domains and needs synthesis
• Accuracy of findings is critical to downstream decisions

Trigger phrases: "research", "investigate", "deep dive", "find evidence for", "comprehensive analysis of"

Iron Law

Never synthesize without reading sources. Every claim in the final report must trace to a source retrieved during Phase 2.

5-Phase Process

Phase 1: Scope — Restate as one research question. Define 3–5 sub-questions, success criteria, constraints, and non-goals. Cannot proceed without a written scope block.

Phase 2: Multi-Source Search — Run 3+ WebSearch queries. WebFetch each source URL. pnpm search:code for prior-art. Maintain evidence log: URL, claim, confidence (HIGH/MEDIUM/LOW), sub-question. Each sub-question needs ≥2 independent sources.

Phase 3: Synthesis — Group evidence by sub-question. CONSENSUS (2+ sources) → HIGH; CONFLICT → LOW, flag for user. Build synthesis matrix. Label unsupported claims [UNVERIFIED].

Phase 4: Validation

• Source freshness — appropriate time period?
• Contradiction check — resolve or flag CONFLICT items.
• Assumption audit — 3 assumptions stated explicitly?
• Scope alignment — each finding maps to a Phase 1 sub-question?
• Confidence calibration — downgrade single-source HIGH ratings.

Phase 5: Report — Save to .claude/context/reports/backend/<topic>-research-<YYYY-MM-DD>.md with sections: Executive Summary, Findings (finding + confidence + evidence per sub-question), Conflicts, Recommended Actions, Knowledge Gaps, Sources.