mcpField
E
extraction-form

extraction-form

github.com/willoscarData & databases51745 installsUpdated 3w ago
Repository

About extraction-form

extraction-form is a skill for the evidence-review extraction stage, turning included papers and protocol fields into a normalized CSV for later synthesis.

Key features

  1. 01Parse protocol extraction fields
  2. 02Filter included papers
  3. 03Generate a normalized CSV
  4. 04Preserve paper provenance
  5. 05Keep narrative notes separate

Use cases

  1. 01Turn screening results into an extraction table
  2. 02Record included papers by protocol field
  3. 03Prepare data for later synthesis

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill extraction-form

After installing, type/extraction-formin Claude Code to confirm it loaded.

Bundled filesscripts/run.py

Details

From the project README

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

Comments

Markdown supported