mcpField
B
bias-assessor

bias-assessor

github.com/willoscarProductivity51740 installsUpdated 3w ago
Repository

About bias-assessor

bias-assessor is a lightweight skill for evidence-review that adds risk-of-bias fields to an extraction table before synthesis, using fixed ratings and brief notes.

Key features

  1. 01Adds risk-of-bias fields
  2. 02Uses low, unclear, and high ratings
  3. 03Keeps notes brief
  4. 04Updates the extraction table in place

Use cases

  1. 01Assess bias before systematic-review synthesis
  2. 02Add quality fields to a paper extraction table

Install

Copy the command and run it in a terminal.

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

After installing, type/bias-assessorin Claude Code to confirm it loaded.

Bundled filesscripts/run.py

Details

From the project README

Bias Assessor

Triggers & routing

  • Trigger: bias, risk-of-bias, RoB, evidence quality, 偏倚评估, 证据质量.
  • Use when: evidence-review 已生成 papers/extraction_table.csv，需要在 synthesis 前补齐偏倚/质量字段。
  • Skip if: 不是 evidence/systematic review，或还没有 papers/extraction_table.csv。
  • Network: none.
  • Guardrail: 使用简单可复核刻度（low/unclear/high）+ 简短 notes；保持字段一致性。

Enriches the extraction table with lightweight risk-of-bias fields for evidence-review.

Input

  • papers/extraction_table.csv

Output

  • updated papers/extraction_table.csv

Contract

The table should expose stable RoB columns:

  • rob_selection
  • rob_measurement
  • rob_confounding
  • rob_reporting
  • rob_overall
  • rob_notes

Allowed values are fixed:

  • low
  • unclear
  • high

Script boundary

scripts/run.py should:

  • add missing RoB columns
  • assign a conservative overall score
  • keep notes brief

Acceptance

  • RoB columns exist
  • all included rows have values
  • values stay within the fixed scale

Non-goals

  • deep methodological critique
  • rewriting extraction contents

Comments

Markdown supported