Deposition Question Development
/install deposition-question-skill
Relativity Deposition Question Builder
Overview
Analyze one or more Relativity-exported PDF productions against a legal theory and generate deposition questions organized by document ID. Each question includes a reason for asking and a document quote that can be used if the witness denies.
Required Behavior
- Ask for the legal theory first before producing analysis or questions.
- Ask for PDF path(s) if not already provided.
- Extract page-level document IDs from the bottom-right area of each page.
- If two numeric IDs appear in that area, choose the smaller number as the page document ID.
- Keep quotes verbatim and include source file plus page number for each quote.
- Group outputs by document ID and place each question under its document ID heading.
- Under every question, include:
Reason why we ask this questionQuote from the document to use in deposition in case the opponent party denies
Workflow
- Gather inputs.
- Confirm the user's legal theory.
- Confirm PDF source path(s).
- Optionally gather witness name/role and priority topics.
- Extract per-page text and document IDs.
- Run:
python scripts/extract_relativity_pages.py \ --input \x3Cpdf-folder-or-file> \ --recurse \ --output \x3Crelativity_pages.json> - Review pages where
selected_document_idis null and flag for manual check.
- Run:
- Build a relevance map for the legal theory.
- For each page, classify relation to theory:
supports,undermines,neutral. - Focus question drafting on
supportspages first, thenunderminespages for impeachment.
- For each page, classify relation to theory:
- Draft deposition questions grouped by document ID.
- Use short, concrete, single-issue questions.
- Start with authentication/foundation, then admission and contradiction questions.
- Use direct quotes from page text for denial follow-up.
- Return output in required structure.
- Follow
references/deposition_output_template.md. - Keep document IDs in ascending numeric order.
- Follow
Output Rules
- Do not merge different document IDs into one section.
- Do not omit
ReasonorQuotesections under any question. - If no reliable quote exists, mark:
Quote from the document to use in deposition in case the opponent party denies: [No direct quote located - manual verification required]
- Prefer quotes that are short, specific, and tied to one factual proposition.
Resources
- Extraction tool:
scripts/extract_relativity_pages.py - Output template:
references/deposition_output_template.md
Dependencies
Install once if missing:
python -m pip install --user pdfplumber
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install deposition-question-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/deposition-question-skill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
Deposition Question Development 是什么?
Develop deposition question sets from Relativity-exported PDF productions using a user-provided legal theory. Use when tasks involve reviewing opponent-produ... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 241 次。
如何安装 Deposition Question Development?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install deposition-question-skill」即可一键安装,无需额外配置。
Deposition Question Development 是免费的吗?
是的,Deposition Question Development 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Deposition Question Development 支持哪些平台?
Deposition Question Development 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 Deposition Question Development?
由 ChipmunkRPA(@chipmunkrpa)开发并维护,当前版本 v1.0.0。