研究综合

将记忆中的研究发现综合成结构化报告，包含证据分级、矛盾解决和可行建议

文件预览

1 个文件

SKILL.md

2.7 KB · 可预览

---
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__claude-flow__memory_search mcp__claude-flow__memory_search_unified mcp__claude-flow__memory_list mcp__claude-flow__memory_retrieve mcp__claude-flow__memory_store mcp__claude-flow__agentdb_context-synthesize mcp__claude-flow__agentdb_pattern-search mcp__claude-flow__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__claude-flow__memory_search` namespace `research` for raw findings
   - `mcp__claude-flow__memory_search` namespace `research-sources` for references
   - `mcp__claude-flow__agentdb_pattern-search` for discovered patterns
   - `mcp__claude-flow__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__claude-flow__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__claude-flow__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]
```

SKILL.md

raw

元数据

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__claude-flow__memory_search mcp__claude-flow__memory_search_unified mcp__claude-flow__memory_list mcp__claude-flow__memory_retrieve mcp__claude-flow__memory_store mcp__claude-flow__agentdb_context-synthesize mcp__claude-flow__agentdb_pattern-search mcp__claude-flow__neural_predict Bash Read Write

研究综合 将积累的研究发现综合成可执行的报告。 何时使用 在运行深度研究（一次或多次）之后，需要将记忆中的发现整合为连贯的综合报告并提供建议时。 步骤 收集发现 — 搜索研究命名空间： mcp__claude-flow__memory_search 命名空间 research 获取原始发现 mcp__claude-flow__memory_search 命名空间 research-sources 获取参考文献 mcp__claude-flow__agentdb_pattern-search 获取已发现的模式 mcp__claude-flow__agentdb_context-synthesize 用于 AI 辅助的上下文构建 证据分级 — 对每条发现，评估： 高 ：多个独立来源一致同意，可直接观察，可重现 中 ：单一可信来源，间接支持，合理 低 ：轶事，单一未验证来源，推测性 解决矛盾 — 当发现冲突时： 识别存在张力的具体主张 比较证据质量 检查时效性（较新的数据可能取代旧数据） 明确标注未解决的矛盾 预测相关性 — 调用 mcp__claude-flow__neural_predict 评分哪些发现与原始目标最相关 构建报告 ： 执行摘要（2-3 句回答原始问题） 关键发现（按证据质量排序） 方法（检查了哪些来源） 局限性（未检查的内容，仍不确定的部分） 建议（具体的下一步行动） 参考文献（来源链接和记忆键） 存储综合报告 — 调用 mcp__claude-flow__memory_store 命名空间 research-synthesis ，存储完整报告 输出格式 text Copy code # [研究主题] — 综合报告 ## 摘要 [2-3 句回答] ## 关键发现 1. [发现] — 证据：高/中/低 2. [发现] — 证据：高/中/低 ## 矛盾 - [主张 A] vs [主张 B]：[解决方案或“未解决”] ## 建议 1. [行动] — 因为 [推理] ## 来源 - [键]：[描述]