extraction-formlisted
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