Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

research-synthesize — Claude Code skill: what it does, how to install

Turns findings stored in ruflo memory into one report, with evidence grades, contradiction handling and next steps. Useful after a run of deep-research.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add ruvnet/ruflo --skill research-synthesize -a claude-code
Open on GitHub

What research-synthesize does

The skill takes what already sits in ruflo memory and pulls it into a single text. It searches the research and research-sources namespaces, collects discovered patterns, and builds context with agentdb_context-synthesize. Each finding then gets a grade. High means several independent sources agree and the claim was observed directly. Medium means one credible source and indirect support. Low means a lone unverified anecdote.

Conflicts get a fixed routine: name the claim in tension, compare the evidence behind each side, see which is newer. Anything still open is marked unresolved instead of smoothed over. neural_predict ranks findings against the original goal, and the report follows a set skeleton: summary, key findings, methodology, limitations, recommendations, sources. The finished text is written to the research-synthesis namespace via memory_store, so a later request can find it.

You call it with a topic and an optional --format report|brief|table. Every memory step runs through ruflo MCP tools, so with the server unconnected the search and store calls fail and there is nothing to synthesize.

What it helps with

  • merge findings from several deep-research runs into one text
  • separate a well-sourced claim from a single unverified one
  • work through conflicting sources and flag what stays open
  • produce a report on a fixed skeleton instead of a blank page
  • keep the synthesis in memory so later queries pick it up

Example prompts for the agent

  • Synthesize what's in memory about Postgres query caching, table format
  • Run research-synthesize on the vector database findings, grade the evidence and list contradictions
  • Pull the monorepo migration findings into a brief with next steps

How to install research-synthesize

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill research-synthesize -a claude-code

2Manually: put the files in place

~/.claude/skills/research-synthesize/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/research-synthesize/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

bailian-cli modelstudioai Skill for managing Aliyun Bailian and DashScope resources via the bl CLI. It routes app calls, quota lookups, and knowledge base queries. Claude Code CX Codex Cursor +1 18,700installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. Claude Code CX Codex Cursor +1 410,700installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. Claude Code CX Codex Cursor +1 410,300installs shadcn shadcn-ui A skill that keeps your agent on the rails with shadcn/ui: adds components, searches registries, fixes markup and builds a design system from your spec. Claude Code CX Codex Cursor +1 122,100installs

Questions about research-synthesize

How do I install research-synthesize in Claude Code?

With one command: npx skills add ruvnet/ruflo --skill research-synthesize -a claude-code. The skill file lands at ~/.claude/skills/research-synthesize/SKILL.md.

What does research-synthesize do?

It searches stored research in ruflo memory, grades each finding, resolves or flags contradictions, and saves the report to the research-synthesis namespace.

What does the skill need to work?

A connected ruflo MCP server, since it reaches memory through memory_search, memory_store, agentdb_context-synthesize and neural_predict. It also gets Bash, Read and Write.

Source text

SKILL.md · MIT 
---
name: research-synthesize
description: Synthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations
argument-hint: "<topic> [--format report|brief|table]"
allowed-tools: mcp__plugin_ruflo-core_ruflo__memory_search mcp__plugin_ruflo-core_ruflo__memory_search_unified mcp__plugin_ruflo-core_ruflo__memory_list mcp__plugin_ruflo-core_ruflo__memory_retrieve mcp__plugin_ruflo-core_ruflo__memory_store mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesize mcp__plugin_ruflo-core_ruflo__agentdb_pattern-search mcp__plugin_ruflo-core_ruflo__neural_predict Bash Read Write
---

# Research Synthesize

Synthesize accumulated research findings into actionable reports.

## When to use

After running deep-research (one or multiple times), when you need to pull together findings from memory into a coherent synthesis with recommendations.

## Steps

1. **Gather findings** — search across research namespaces:
   - `mcp__plugin_ruflo-core_ruflo__memory_search` namespace `research` for raw findings
   - `mcp__plugin_ruflo-core_ruflo__memory_search` namespace `research-sources` for references
   - `mcp__plugin_ruflo-core_ruflo__agentdb_pattern-search` for discovered patterns
   - `mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesize` for AI-assisted context building
2. **Grade evidence** — for each finding, assess:
   - **High**: Multiple independent sources agree, directly observed, reproducible
   - **Medium**: Single credible source, indirectly supported, plausible
   - **Low**: Anecdotal, single unverified source, speculative
3. **Resolve contradictions** — when findings conflict:
   - Identify the specific claim in tension
   - Compare evidence quality
   - Check recency (newer data may supersede)
   - Note unresolved contradictions explicitly
4. **Predict relevance** — call `mcp__plugin_ruflo-core_ruflo__neural_predict` to score which findings are most relevant to the original goal
5. **Structure report**:
   - Executive summary (2-3 sentences answering the original question)
   - Key findings (ranked by evidence quality)
   - Methodology (what sources were checked)
   - Limitations (what wasn't checked, what remains uncertain)
   - Recommendations (concrete next actions)
   - References (source links and memory keys)
6. **Store synthesis** — call `mcp__plugin_ruflo-core_ruflo__memory_store` namespace `research-synthesis` with the full report

## Output format

```
# [Research Topic] — Synthesis Report

## Summary
[2-3 sentence answer]

## Key Findings
1. [Finding] — Evidence: High/Medium/Low
2. [Finding] — Evidence: High/Medium/Low

## Contradictions
- [Claim A] vs [Claim B]: [resolution or "unresolved"]

## Recommendations
1. [Action] — because [reasoning]

## Sources
- [key]: [description]
```

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor