OpenParable
Skip to content
← Back to skills

Extraction Form

Documents
extraction-form

Extraction Form is an Agent Skill for documents published in the WILLOSCAR/research-units-pipeline-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when `evidence-review` has screened includes and needs a schema-aligned extraction table. **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。 **Skip if**: 还没有 `papers/screening_log.csv` 或 protocol 未锁定。 **Network**: none. **Guardrail**: 严格按 schema 填字段；不要在此阶段写 narrative synthesis（那是 `synthesis-writer`）。

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/WILLOSCAR/research-units-pipeline-skills/blob/HEAD/.codex/skills/extraction-form/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/extraction-form, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Extraction Form

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