Skill
Security
Skill
/research-synthesis-analyst
Synthesize multi-source evidence into decision-ready research outputs with conflict tracking and citation hygiene.
Install
$ npx -y skills add frumu-ai/tandem --skill research-synthesis-analyst --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/research-synthesis-analyst
Context preview
The summary Claude sees to decide when to auto-load this skill.
Synthesize multi-source evidence into decision-ready research outputs with conflict tracking and citation hygiene.
SKILL.md
research-synthesis-analyst.SKILL.mdname: research-synthesis-analyst description: "Synthesize multi-source evidence into decision-ready research outputs with conflict tracking and citation hygiene." version: "0.1.0" author: tandem compatibility: tandem tags: - research - analysis - evidence requires: - markdown triggers: - synthesis - research brief - evidence table
Research Synthesis Skill
Mission
Produce a clear, defensible synthesis from many sources while preserving uncertainty and conflicts.
Inputs To Use First
- inputs/questions.md
- inputs/methodology.md
- inputs/references.md
- inputs/papers/
Workflow
1. Build a source map: summarize each paper in 2-4 bullets. 2. Group claims by theme and identify direct conflicts. 3. Score evidence strength (high/medium/low) with rationale. 4. Write synthesis focused on decisions, not just summaries. 5. Convert findings into executive-ready artifacts.
Required Outputs
- outputs/workspace_scan_summary.md
- outputs/synthesis_analysis.md
- outputs/claims_evidence_table.md
- outputs/executive_brief.md
- outputs/research_brief_dashboard.html
Quality Bar
- Claims have explicit support and source linkage.
- Conflicting evidence is surfaced, not hidden.
- Recommendations include risk and confidence.
- Executive brief is concise and action-oriented.
Ships withtandem
Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
Get the whole plugin
Stats
125
Stars
13
Forks
Active
Maintenance
Rust
Language
23d ago
Last commit
9mo ago
Created
2h ago
Added