/research-and-summarize
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
$ npx -y skills add DevelopersGlobal/ai-agent-skills --skill research-and-summarize --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.
- You can call itInvoke it directly when you want it.
- Slash command
/research-and-summarize
Context preview
The summary Claude sees to decide when to auto-load this skill.
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
SKILL.md
research-and-summarize.SKILL.mdname: research-and-summarize
description: Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
category: everyday
applies-to: [claude, gemini, cursor, copilot, any]
version: 1.0.0
Overview
Information overload is the default state. This skill transforms any research task into a structured summary: headline insight first, context second, detail third, action last. Designed for decision-makers who need clarity, not comprehensiveness.
When to Use
- Summarizing technical documentation or papers
- Researching a technology choice
- Briefing a team on a topic
- Distilling a long document for a specific decision
Process
Step 1: Define the Research Question
1. State the specific question being answered: *"Should we use Kafka or RabbitMQ for our event pipeline?"* 2. State who the answer is for and what decision it enables. 3. This scopes the research — don't gather information beyond what the decision needs.
**Verify:** Research question is specific enough to have a clear answer.
Step 2: Gather and Evaluate Sources
4. Identify 3–5 high-quality, authoritative sources. 5. For each source, note: recency, authority, potential bias. 6. Cross-reference key claims across sources. 7. Flag conflicting information — don't silently pick one side.
**Verify:** Key claims are supported by at least 2 independent sources.
Step 3: Write the Layered Summary
8. **Headline (1 sentence)**: The single most important insight. 9. **Key findings (3–5 bullets)**: Supporting evidence for the headline. 10. **Context and nuance (1–2 paragraphs)**: Caveats, tradeoffs, conditions under which the headline doesn't hold. 11. **What we don't know**: Gaps in the available information. 12. **Recommended action**: Given the findings, what should the reader do next?
**Deliver:** A structured summary with all 5 sections.
Step 4: Cite Sources
13. Every factual claim is linked to a source. 14. Include the date of each source (recency matters in fast-moving fields).
**Verify:** Every claim has a citation.
Common Rationalizations (and Rebuttals)
| Excuse | Rebuttal | |--------|----------| | "The topic is too complex to summarize" | The goal is to enable a decision, not to be comprehensive. Scope to the decision. | | "I'll just share the links" | Links are not summaries. Distillation is the value. |
Verification
- [ ] Research question defined before research begins
- [ ] Key claims cross-referenced across 2+ sources
- [ ] Summary has: headline, findings, context, unknowns, action
- [ ] Every factual claim has a citation with date
References
- [think-before-coding skill](../think-before-coding/SKILL.md)
- [idea-to-spec skill](../idea-to-spec/SKILL.md)
Read more
name: research-and-summarize description: Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action. category: everyday applies-to: [claude, gemini, cursor, copilot, any] version: 1.0.0
Overview
Information overload is the default state. This skill transforms any research task into a structured summary: headline insight first, context second, detail third, action last. Designed for decision-makers who need clarity, not comprehensiveness.
When to Use
- Summarizing technical documentation or papers
- Researching a technology choice
- Briefing a team on a topic
- Distilling a long document for a specific decision
Process
Step 1: Define the Research Question
1. State the specific question being answered: *"Should we use Kafka or RabbitMQ for our event pipeline?"* 2. State who the answer is for and what decision it enables. 3. This scopes the research — don't gather information beyond what the decision needs.
**Verify:** Research question is specific enough to have a clear answer.
Step 2: Gather and Evaluate Sources
4. Identify 3–5 high-quality, authoritative sources. 5. For each source, note: recency, authority, potential bias. 6. Cross-reference key claims across sources. 7. Flag conflicting information — don't silently pick one side.
**Verify:** Key claims are supported by at least 2 independent sources.
Step 3: Write the Layered Summary
8. **Headline (1 sentence)**: The single most important insight. 9. **Key findings (3–5 bullets)**: Supporting evidence for the headline. 10. **Context and nuance (1–2 paragraphs)**: Caveats, tradeoffs, conditions under which the headline doesn't hold. 11. **What we don't know**: Gaps in the available information. 12. **Recommended action**: Given the findings, what should the reader do next?
**Deliver:** A structured summary with all 5 sections.
Step 4: Cite Sources
13. Every factual claim is linked to a source. 14. Include the date of each source (recency matters in fast-moving fields).
**Verify:** Every claim has a citation.
Common Rationalizations (and Rebuttals)
| Excuse | Rebuttal | |--------|----------| | "The topic is too complex to summarize" | The goal is to enable a decision, not to be comprehensive. Scope to the decision. | | "I'll just share the links" | Links are not summaries. Distillation is the value. |
Verification
- [ ] Research question defined before research begins
- [ ] Key claims cross-referenced across 2+ sources
- [ ] Summary has: headline, findings, context, unknowns, action
- [ ] Every factual claim has a citation with date
References
- [think-before-coding skill](../think-before-coding/SKILL.md)
- [idea-to-spec skill](../idea-to-spec/SKILL.md)
AI agent skills for production grade applications
Other skills on ai-agent-skills.
- /ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
Open skill - /api-design
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
Open skill - /ci-cd-pipelines
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
Open skill - /code-explanation
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
Open skill - /code-review
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
Open skill - /context-loading
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.
Open skill

