Update to Research Extractor

{
  "description": "Extract study populations, participant characteristics, eligibility, baselines, interventions, comparators, and PICO/PICOS/PECO elements from scientific sources. Use for population or treatment/exposure question extraction.",
  "included_files": [],
  "name": "population-and-pico",
  "skill_md_contents": "---\nname: population-and-pico\ndescription: Extract study populations, participant characteristics, eligibility, baselines, interventions, comparators, and PICO/PICOS/PECO elements from scientific sources. Use for population or treatment/exposure question extraction.\n---\n\n# Population and question structure\n\nUse the supplied source and the normalized definitions in `../research-data-extraction/references/extraction-schema.md`. Follow `research-data-extraction` for provenance and missingness.\n\n## Population\n\n- Extract target/source population, setting, recruitment, inclusion/exclusion criteria, enrolled N, analyzed N, number of groups, and group Ns as separate fields.\n- For age, preserve reported summary type (mean/median), value, dispersion and range. For sex/gender retain the source's category labels/counts; do not infer identity categories or collapse them.\n- Capture baseline characteristics, condition/stage/severity, comorbidities, subgroup definitions, and eligibility exactly as available.\n- Keep screening, randomized/enrolled, treated, and analyzed numbers separate when the paper reports them. Reconcile totals only as a flagged check, not by changing source values.\n\n## Intervention, exposure, and comparator\n\nFor each arm/exposure group retain group name, intervention/exposure name/type, dose or level, frequency, route, duration, procedures, co-interventions, and relevant control conditions. Extract comparator presence/name/type/description only from evidence. For no-comparator studies, use `NA` only where appropriate; otherwise `NR`/`UNCLEAR`.\n\n## PICO, PICOS, PECO\n\n- Use PICO/PICOS for intervention questions; use PECO when the principal contrast is an exposure.\n- P: population, characteristics, setting, N, eligibility.\n- I/E: intervention/exposure details.\n- C: comparator/unexposed condition, if one exists.\n- O: primary/secondary outcomes, method, and timepoint.\n- S: source-supported study design.\n- Do not force all letters into qualitative, descriptive, case, or single-arm research. Label truly inapplicable components `NA`; missing source details are `NR`.\n\n## Output check\n\nMake each group and its denominator identifiable. Preserve original labels and source locations; do not carry a value across papers or assume subgroup values represent the full population.\n"
}