Skip to content
Agentmart
Submit a tool

legal-qa-extractor

从律师与客户的沟通记录中批量提取法律问答对,脱敏后输出结构化Q&A,支持增量扫描与归档。

Skill by laubeing-droid

IndexedMIT★ 16
Write a review

Chalk Labs

Need help deploying legal-qa-extractor?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/laubeing-droid-legal-qa-extractor

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

从律师与客户的沟通记录中批量提取法律问答对,脱敏后输出结构化Q&A,支持增量扫描与归档。

Use cases: testing, legal

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/legal-qa-extractor

What's inside

Skill name
legal-qa-extractor
Description
从律师与客户的沟通记录中批量提取法律问答对,脱敏后输出结构化Q&A,支持增量扫描与归档。
License
MIT
Instructions
96 lines in SKILL.md · view on GitHub

Files (20)

  • CHANGELOG.md
  • SKILL.md
  • .gitkeep · archive/
  • 01-single-issue.md · assets/benchmarks/
  • 02-multi-issue-switching.md · assets/benchmarks/
  • 03-same-issue-repeated.md · assets/benchmarks/
  • 04-follow-up-questions.md · assets/benchmarks/
  • 05-proactive-risk-reminder.md · assets/benchmarks/
  • 06-admin-heavy.md · assets/benchmarks/
  • 07-incomplete-answer.md · assets/benchmarks/
  • 08-batch-mixed-directory.md · assets/benchmarks/
  • README.md · assets/benchmarks/
  • .env.example · config/
  • batch-processing-rules.md · references/
  • benchmark-rubric.md · references/
  • extraction-rules.md · references/
  • intake-checklist.md · references/
  • output-template.md · references/
  • review-checklist.md · references/
  • scan-log-spec.md · references/

SKILL.md (first lines)

# 法律问答提取

将散落在聊天记录、邮件往来、咨询纪要中的实务问答整理为可复用的知识资产。

## 一、识别维度

从沟通文本中识别五类有价值内容:

### (一) 直接问答

客户提出具体法律问题,律师给出明确回复的对话段落。

### (二) 追问回应

在初始回答基础上,客户追加细节追问后律师的进一步阐明。

### (三) 风险提醒

律师主动提示的法律风险、合规底线或负面后果预警。

### (四) 操作指引

律师给出的具体步骤、时限、文件清单等可执行动作。

### (五) 普遍关切

不针对特定当事人、具有一般参考价值的基础法律常识阐述。

## 二、处理规则

### (一) 信息脱敏

所有输出必须去除以下可识别信息:
- 客户姓名、企业名称
- 案件编号、合同编号
- 具体金额、日期、地点

用「甲某」「某公司」「约X万元」等占位符替换。

### (二) 质量控制

- 只有形成完整问答闭环的内容才予提取
- 信息残缺导致无法独立的问答对予以舍弃
- 纯行政沟通、寒暄、日程协调等内容跳过

## 三、输出格式

每条问答对包含:

- 问题描述(脱敏后的客户原始关切)
- 律师解答(脱敏后的核心回复)
- 所属维度(对应上述五类之一)
- 价值标签:普遍性、典型性、教育性、复用性

## 四、处理模式

### (一) 单次提取

对用户直接提供的沟通文件即时处理。

### (二) 增量扫描

指定目录后,基于内容哈希判断文件变更,仅对新增或修改内容触发提取。

### (三) 项目聚合

同一子文件夹下的多次沟通记录可合并为单份 QA 输出,便于按客户或案件维度管理。

## 五、归档机制

提取结果按项目/日期归档至 `archive/extractions/`。扫描日志记录文件哈希、处理状态和所属项目。

## 六、使用方式

单文件:
```
/legal-qa-extractor @沟通记录.md
```

批量扫描:
```
/legal-qa-extractor 扫描 ./客户沟通记录/ 目录
```

## 七、参考文件

- `references/extraction-rules.md`:提取判定规则
- `references/output-template.md`:输出模板
- `references/batch-processing-rules.md`:批量处理规则
- `assets/benchmarks/`:典型场景评测用例

---

提取结果供内部知识沉淀使用,不得直接作为对外法律意见。

From laubeing-droid/unified-legal-ai-cn, MIT.

More from laubeing-droid/unified-legal-ai-cn

Signals

Stars
16
Forks
4
Open issues
1
Last commit (this folder)
Jun 5, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from laubeing-droid

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get legal-qa-extractor running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying legal-qa-extractor?

CallGet help
Cite this page

legal-qa-extractor skill. Agent Mart. https://agentmart.dev/skills/laubeing-droid-legal-qa-extractor (last updated 2026-10-24)