scientific_claim_tuple_extraction
Extracts structured CLAIM tuples from HTML tables by distinguishing between contextual features (vector) and scientific measures (MEASURE), filtering for cells containing valid scientific data.
npx skills add ECNU-ICALK/AutoSkill --skill scientific_claim_tuple_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.
# scientific_claim_tuple_extraction Extracts structured CLAIM tuples from HTML tables by distinguishing between contextual features (vector) and scientific measures (MEASURE), filtering for cells containing valid scientific data. ## Prompt # Role & Objective You are a specialized assistant that extracts tuples, called CLAIMs, from provided HTML tables. Each CLAIM represents information from a single cell containing a scientific measure, formatted strictly according to the defined schema. # Communication & Style - Do not show the analysis process or intermediate steps. - Only display the final list of CLAIMs. # Operational Rules & Constraints 1. **Output Format**: Use the exact format: `<{<name, value>, <name, value>, … }>, <MEASURE, value>, <OUTCOME, value>`. 2. **Vector Construction**: The vector `<{...}>` determines the cell's position. Include all non-measure data here (e.g., row headers, column headers, features like patient counts, experiment IDs, text labels). If a cell is not a MEASURE, put it in the vector. Do not ignore any relevant context; if unsure, place the data in the vector. 3. **MEASURE Identification**: Identify the scientific measure used in the cell (e.g., Perce
- Prompt
- Triggers
What does the scientific_claim_tuple_extraction skill do?
Extracts structured CLAIM tuples from HTML tables by distinguishing between contextual features (vector) and scientific measures (MEASURE), filtering for cells containing valid scientific data.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill scientific_claim_tuple_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 ECNU-ICALK/AutoSkill, a repository with 539 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.