← 返回 Skills 市场
138
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install bias-assessor
功能描述
Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently. **Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估,...
使用说明 (SKILL.md)
Bias Assessor (risk-of-bias, lightweight)
Goal: make evidence quality explicit in a way that is quick, consistent, and auditable.
Inputs
papers/extraction_table.csv
Outputs
- Updated
papers/extraction_table.csv
Recommended fields
Use a simple 3-level scale (all lowercase): low | unclear | high.
Suggested columns to add (if missing):
rob_selectionrob_measurementrob_confoundingrob_reportingrob_overallrob_notes
Workflow
- Read
papers/extraction_table.csvand identify the set of included studies. - If RoB columns are missing, add them (keep names stable once introduced).
- For each study, fill each RoB domain:
low: design/reporting plausibly controls the biasunclear: not enough information to judgehigh: clear risk (e.g., missing controls, ambiguous measurement, selective reporting)
- Set
rob_overallconservatively:highif any domain ishighunclearif nohighbut at least oneunclearlowonly if all domains arelow
- Add 1–3 short notes in
rob_notesthat justify the rating.
Definition of Done
- Every included paper row has all RoB columns filled.
- Values are strictly from
low|unclear|high(no free-form scale drift). - Notes are short and specific (what was missing / what was strong).
Troubleshooting
Issue: the table has mixed or inconsistent RoB column names
Fix:
- Normalize to the recommended column names and keep a single set across all rows.
Issue: the paper lacks enough methodological detail
Fix:
- Prefer
unclearwith a concrete note (“no details on X”) rather than guessing.
安全使用建议
This skill appears to do what it claims: it reads papers/extraction_table.csv and populates conservative RoB fields (low|unclear|high) with short notes. Things to consider before installing: 1) Back up your papers/extraction_table.csv before running the skill (the tooling contains atomic write/backup helpers but always keep a copy). 2) The package includes many pipeline manifests and helper modules (larger code bundle than a tiny single-script helper); if you want minimal surface area, review or run only the specific script that edits extraction_table.csv. 3) Confirm you will run this in a workspace that does not contain sensitive files you don't want touched (the skill writes local files but declares no network access or credentials). 4) If you need stronger assurance, inspect tooling/quality_gate.py and the scripts that will be executed (scripts/run.py is referenced by the executor) to verify they only perform local CSV/file updates. 5) Human oversight is appropriate: review the produced rob_* fields and notes for errors or systematic drift.
功能分析
Type: OpenClaw Skill
Name: bias-assessor
Version: 1.0.0
The bias-assessor skill bundle is a legitimate component of a research pipeline framework designed for academic tasks like systematic reviews and literature engineering. The SKILL.md instructions are strictly limited to the stated purpose of assessing risk-of-bias in CSV tables. The extensive supporting code in the tooling/ directory (such as quality_gate.py and executor.py) provides infrastructure for validating artifacts and running pipeline units; while these scripts possess broad file-system access and execution capabilities (via subprocess.run), they are functionally aligned with the framework's role as a task runner and lack any indicators of malicious intent, data exfiltration, or unauthorized network activity.
能力评估
Purpose & Capability
The skill's name/description (add RoB fields to papers/extraction_table.csv) matches the runtime instructions and the declared requirement of python. The bundle also includes a large set of pipeline manifests and helper modules (tooling/*.py and many pipelines), which increases the attack surface compared with a minimal single-file helper but is coherent in the context of a research-pipeline collection.
Instruction Scope
SKILL.md explicitly limits inputs to papers/extraction_table.csv and outputs to an updated extraction_table.csv, prescribes a simple 3-level scale and short notes, and states 'Network: none'. The instructions do not ask the agent to read unrelated files, environment variables, or to transmit data externally.
Install Mechanism
No install spec is provided (instruction+bundled python modules). That is low-risk: nothing is downloaded at install time. The declared runtime requirement (python/python3) is appropriate for the included Python code.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportionate to a local CSV-editing utility.
Persistence & Privilege
The skill is not marked always:true and does not request elevated persistence or to modify other skills. The default ability for the agent to invoke the skill autonomously is unchanged and not by itself suspicious here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install bias-assessor - 安装完成后，直接呼叫该 Skill 的名称或使用
/bias-assessor触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of bias-assessor: add bias/risk-of-bias assessment fields and ensure consistent evidence quality evaluation in systematic reviews.
- Adds recommended RoB columns (selection, measurement, confounding, reporting, overall, notes) to extraction tables.
- Populates RoB fields for each included paper using a 3-level scale: low, unclear, high.
- Ensures columns and scale are consistent and auditable across all rows.
- Provides concise, concrete notes for each rating.
- Normalizes column names and skips non-systematic reviews or missing tables.
元数据
常见问题
Bias Assessor 是什么？
Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently. **Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 138 次。
如何安装 Bias Assessor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install bias-assessor」即可一键安装，无需额外配置。
Bias Assessor 是免费的吗？
是的，Bias Assessor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Bias Assessor 支持哪些平台？
Bias Assessor 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Bias Assessor？
由 WILLOSCAR（@willoscar）开发并维护，当前版本 v1.0.0。
推荐 Skills