← ClaudeAtlas

extraction-formlisted

Use when `evidence-review` has screened includes and needs a schema-aligned extraction table.
WILLOSCAR/research-units-pipeline-skills · ★ 501 · Data & Documents · score 79
Install: claude install-skill WILLOSCAR/research-units-pipeline-skills
# Extraction Form ## Triggers & routing - **Trigger**: extraction form, extraction table, data extraction, 信息提取, 提取表. - **Use when**: `evidence-review` 在 screening 后进入 extraction(C4),需要把纳入论文按字段落到 CSV 以支持后续 synthesis。 Transforms screened include rows plus protocol schema into the analysis table used by `evidence-review`. ## Inputs Required: - `papers/screening_log.csv` - `output/PROTOCOL.md` Optional: - `papers/paper_notes.jsonl` ## Output - `papers/extraction_table.csv` ## Contract The table must: - contain one row per included paper - preserve provenance columns (`paper_id`, `title`, `year`, `url`) - include protocol-defined extraction fields - keep narrative residue in `notes`, not in schema columns ## Script boundary `scripts/run.py` should: - parse the extraction schema from the protocol - filter `include` rows - materialize a normalized CSV ## Acceptance - output exists - include rows map 1:1 to extraction rows - schema matches `output/PROTOCOL.md` ## Non-goals - synthesis writing - bias scoring