Agent skill

topic-synthesis

Synthesize claims across multiple sources to identify consensus, disagreements, and emerging narratives on AI research topics. Use when you have claims from both lab researchers and critics on the same topic and need to understand where they agree, disagree, and what the overall hype level is.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill topic-synthesis --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/analysis/topic-synthesis/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Topic Synthesis Skill Synthesize claims from multiple sources to produce a coherent picture of discourse on an AI topic. ## Input Structure You'll receive claims grouped by source type: - **Lab researcher claims**: From people at Anthropic, OpenAI, DeepMind, Meta AI, etc. - **Critic claims**: From credentialed skeptics like Marcus, Chollet, Mitchell, Bender - **Independent claims**: From independent researchers and practitioners ## Synthesis Components ### 1. Lab Consensus What do lab researchers generally agree on? Write 2-3 sentences capturing the central themes. Look for: - Repeated claims across multiple lab researchers - Consistent stance on capabilities/limitations - Shared predictions or timelines ### 2. Critic Consensus What do critics generally agree on? Write 2-3 sentences capturing the central themes. Look for: - Common critiques raised by multiple critics - Shared concerns about hype or methodology - Consistent alternative explanations ### 3. Agreements What do BOTH sides agree on? These are often the most reliable signal. Examples: - "Current models struggle with certain forms of reasoning" - "More compute does improve capabilities" - "Benchmarks have limitations" ##

What's inside
Steps it walks through
  1. Input Structure
  2. Synthesis Components
  3. 1. Lab Consensus
  4. 2. Critic Consensus
  5. 3. Agreements
  6. 4. Disagreements
  7. 5. Emerging Narratives
  8. 6. Notable Predictions
  9. 7. Evidence Quality
  10. Hype Delta Calculation
  11. Output Format
  12. Synthesis Narrative Guidelines
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the topic-synthesis skill do?

Synthesize claims across multiple sources to identify consensus, disagreements, and emerging narratives on AI research topics. Use when you have claims from both lab researchers and critics on the same topic and need to understand where they agree, disagree, and what the overall hype level is.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill topic-synthesis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going