Deep Research
- 791 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
deep-research is a Claude Code skill that orchestrates multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findings before technical commitments.
About
deep-research is an agent research skill for developers who need thorough, multi-source investigation before choosing a feature, architecture, or product direction. The skill coordinates claude-flow MCP capabilities including memory_store, memory_search, agentdb hierarchical store/recall, pattern search/store, neural_predict, hooks intelligence pattern tools, and task_create/list orchestration. Developers invoke deep-research with a topic argument when they want evidence gathered across sources, prior session memory, and stored patterns, then synthesized into structured findings rather than a single web snippet. The workflow is designed for decision gates where shallow answers would create rework downstream.
- Orchestrates parallel web searches, academic papers, and code repositories in one agent run
- Synthesizes findings into structured, citation-backed reports with confidence scoring
- Reduces shallow AI hallucinations by grounding every claim in real sources
- Works across any builder context from market validation to architecture choices
Deep Research by the numbers
- 791 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #1,330 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill deep-researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 791 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you run multi-source technical research with an agent?
Conduct thorough, multi-source investigation before committing to an idea, feature, or technical decision.
Who is it for?
Developers evaluating features, libraries, or architectures who need persisted, multi-source agent research before implementation.
Skip if: Quick factual lookups, code-only refactors, or teams without claude-flow MCP memory and task tools available.
When should I use this skill?
A user needs thorough investigation across web and agent memory before committing to an idea, feature, or technical decision.
What you get
Structured research findings with stored memory entries, matched patterns, and synthesized conclusions for a stated topic.
- Structured research findings
- Stored memory and pattern artifacts
Files
Deep Research
Orchestrate multi-phase deep research campaigns that gather, cross-reference, and synthesize information from multiple sources.
When to use
When you need to investigate a complex topic thoroughly — spanning web sources, codebase patterns, stored memory, and external documentation — and produce a structured synthesis.
Steps
1. Define research scope — break the question into 3-7 sub-questions that together answer the main question 2. Search existing knowledge — call mcp__claude-flow__memory_search_unified and mcp__claude-flow__agentdb_pattern-search to check what's already known 3. Web research — use WebSearch and WebFetch to gather external information for each sub-question 4. Codebase analysis — use Bash (grep/find), Read to examine relevant source files 5. Cross-reference — compare findings across sources, identify agreements and contradictions 6. Store findings — call mcp__claude-flow__memory_store with namespace research for each key finding 7. Store patterns — call mcp__claude-flow__agentdb_pattern-store for reusable patterns discovered 8. Synthesize — produce a structured research report with:
- Executive summary (2-3 sentences)
- Key findings (bulleted)
- Evidence quality assessment (high/medium/low per finding)
- Open questions remaining
- Recommended next steps
Research depth levels
- Quick — memory search + 1-2 web queries, 2-3 minutes
- Standard — memory + web + codebase scan, 5-10 minutes
- Deep — all sources + cross-referencing + pattern storage, 15-30 minutes
- Exhaustive — deep + spawn sub-agents for parallel research threads, 30+ minutes
Memory namespaces
research— raw findings keyed by topicresearch-synthesis— completed synthesis reportsresearch-sources— source URLs and references
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick deep-research over a single web search when you need memory-backed pattern recall and structured synthesis across multiple agent phases.
FAQ
What MCP tools does deep-research use?
deep-research orchestrates claude-flow MCP tools for memory_store, memory_search, agentdb hierarchical store/recall, pattern search/store, hooks intelligence patterns, neural_predict, and task_create/list to gather and synthesize findings.
When should a developer invoke deep-research?
deep-research fits pre-commitment investigation: choosing a feature direction, comparing technical approaches, or validating an idea with multi-source evidence. Pass a topic via the argument-hint to scope the run.