claim-extraction
Extract structured claims, predictions, hints, and opinions from AI research content. Use when processing tweets, blog posts, substacks, or other content from AI researchers to identify substantive assertions about AI capabilities, limitations, and progress.
npx skills add majiayu000/claude-skill-registry --skill claim-extraction --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Claim Extraction Skill Extract all substantive claims from AI research content. A claim is any assertion that: - States something as true about AI capabilities, limitations, or progress - Predicts future developments - Hints at unreleased work - Expresses a positioned opinion on the field's direction - Critiques others' claims or work ## Extraction Schema For each claim, extract: ### 1. claimText The claim in clear, standalone form. Paraphrase if needed for clarity. ### 2. claimType - `fact`: Assertion about current state ("GPT-4 can do X") - `prediction`: Forward-looking ("By 2026, we'll have...") - `hint`: Implies unreleased work ("We've been seeing interesting results with...") - `opinion`: Positioned take ("I think scaling is/isn't sufficient") - `critique`: Challenges others ("Marcus is wrong because...") - `question`: Genuine uncertainty expressed ("I'm not sure if...") ### 3. topic Primary topic category: - `scaling`: Scaling laws, compute, training efficiency - `reasoning`: LLM reasoning, chain-of-thought, planning - `agents`: AI agents, tool use, autonomy - `safety`: AI safety, alignment, control - `interpretability`: Mechanistic interpretability - `multimodal`: Vision,
- Extraction Schema
- 1. claimText
- 2. claimType
- 3. topic
- 4. stance
- 5. bullishness
- 6. confidence
- 7. timeframe (for predictions)
- 8. evidenceProvided
- 9. quoteworthiness
- Output Format
- Guidelines
- Author Context Matters
What does the claim-extraction skill do?
Extract structured claims, predictions, hints, and opinions from AI research content. Use when processing tweets, blog posts, substacks, or other content from AI researchers to identify substantive assertions about AI capabilities, limitations, and progress.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill claim-extraction --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.