Agent skill
knowledge-synthesis
[Research] Synthesize research findings into structured report using template. Final step of research workflow.
Install this agent skill to your Project
npx add-skill https://github.com/duc01226/EasyPlatform/tree/main/.claude/skills/knowledge-synthesis
SKILL.md
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting.
Prerequisites: MUST READ before executing:
.claude/skills/shared/web-research-protocol.md
Quick Summary
Goal: Synthesize evidence base into final structured report using enforced template.
Workflow:
- Load evidence — Read evidence base from deep-research
- Load template — Read enforced template from docs/templates/
- Synthesize — Write report following template structure
- Citation check — Verify every claim has citation
- Confidence summary — Aggregate scores, flag gaps
Key Rules:
- MUST use enforced template structure — all sections required
- Every factual claim inline-cited:
[N]referencing source table - Knowledge gaps section mandatory
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Knowledge Synthesis
Step 1: Load Evidence
Read .claude/tmp/_evidence-{slug}.md and .claude/tmp/_sources-{slug}.md.
Inventory:
- Total findings with confidence scores
- Unresolved discrepancies
- Remaining gaps
Step 2: Load Template
Read the enforced template: docs/templates/research-report-template.md
Every section in the template MUST appear in the final report.
Step 3: Synthesize Report
Write to docs/knowledge/research/{slug}.md:
For each template section:
- Map relevant findings from evidence base
- Write content with inline citations
[N] - Declare confidence per finding
- Note cross-cutting patterns and contradictions in Analysis section
Step 4: Citation Audit
Verify:
- Every factual claim has at least one
[N]citation - Every source in the Sources table is referenced at least once
- No orphan citations (referencing non-existent source)
Step 5: Confidence Summary
Calculate overall report confidence:
- Average of all finding confidence scores
- Weight by finding importance
- Flag any <60% findings prominently
Output
Final report: docs/knowledge/research/{descriptive-slug}.md
Clean up working files from .claude/tmp/ after successful synthesis.
Closing Reminders
- MUST break work into small todo tasks using
TaskCreateBEFORE starting - MUST search codebase for 3+ similar patterns before creating new code
- MUST cite
file:lineevidence for every claim (confidence >80% to act) - MUST add a final review todo task to verify work quality
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
fix-parallel
[Implementation] Analyze & fix issues with parallel fullstack-developer agents
ask
[Utilities] Answer technical and architectural questions.
claude-code
[Utilities] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.
workflow-deployment
[Workflow] Trigger Deployment & Infrastructure workflow — CI/CD pipelines, Docker, Kubernetes setup and deployment.
workflow-idea-to-pbi
[Workflow] Trigger Idea to PBI workflow — po/ba workflow: capture idea, refine to pbi, create stories, prioritize.
easy-claude-help
[Utilities] Configuration guide for the easy-claude framework — explain settings, guide users through configuring .ck.json.
Didn't find tool you were looking for?