Agent skill

Demand Received

by zhou210712 in zhou210712/claude-for-legal-ZH

来函分流处理——提取关键字段、交叉检索案件组合、评估实质理由、 提出响应方案并附建议,必要时转交案件登记或律师函起草. An agent skill from zhou210712/claude-for-legal-ZH.

Apache-2.0Auto-check passed

Install Demand Received

skills CLI
$ npx skills add zhou210712/claude-for-legal-ZH --skill demand-received -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zhou210712/claude-for-legal-ZH demand-received --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZH.git skills-src && mkdir -p .claude/skills && cp -r skills-src/litigation-legal/skills/demand-received .claude/skills/demand-received && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
demand-received
GitHub stars
225
Token cost
~1.4k tokens
SKILL.md length
184 words
Files
1
Skills in repo
122
Repo updated
First seen
Licence
Apache-2.0

At a glance

来函分流处理——提取关键字段、交叉检索案件组合、评估实质理由、 提出响应方案并附建议,必要时转交案件登记或律师函起草. An agent skill from zhou210712/claude-for-legal-ZH.

  • Works in 7 steps: 读取提供的来函文件。 → 加载… → 加载… → …
  • Tasks that involve Legal research
  • SKILL.md covers 目的, 加载上下文, 工作流 and 以下一步决策树收尾, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Demand Received is an agent skill from zhou210712/claude-for-legal-ZH. 来函分流处理——提取关键字段、交叉检索案件组合、评估实质理由、 提出响应方案并附建议,必要时转交案件登记或律师函起草。 当用户说"收到一封律师函"、"审查这个来函"或附上来函要求评估时使用。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Legal research

Example prompts

  • “收到一封律师函”
  • “审查这个来函”
  • “/demand-received”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 读取提供的来函文件。
  2. 加载 ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml 用于案件组合交叉检索。
  3. 加载 ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → 风险校准、执业背景、律师函实务惯例。
  4. 按以下工作流操作。
  5. 提取关键字段;交叉检索案件组合;评估实质理由;提出方案并附建议。
  6. 写入 ~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/triage.md。将来函复制或链接至…
  7. 按用户选择转交

What it can do on your machine

Read from SKILL.md and the folder at commit 2f01c92. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Demand Received loads about 1.4k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 184 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zhou210712/claude-for-legal-ZH at commit 2f01c92, republished under its Apache-2.0 licence (© zhou210712). 184 words, ~1,360 tokens.

Download SKILL.mdSave it as .claude/skills/demand-received/SKILL.md (or your agent's skills folder).
name
demand-received
description
来函分流处理——提取关键字段、交叉检索案件组合、评估实质理由、 提出响应方案并附建议,必要时转交案件登记或律师函起草。 当用户说"收到一封律师函"、"审查这个来函"或附上来函要求评估时使用。
argument-hint
[来函文件路径] [--slug=自定义代号]

/demand-received

  1. 读取提供的来函文件。
  2. 加载 ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml 用于案件组合交叉检索。
  3. 加载 ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → 风险校准、执业背景、律师函实务惯例。
  4. 按以下工作流操作。
  5. 提取关键字段;交叉检索案件组合;评估实质理由;提出方案并附建议。
  6. 写入 ~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/triage.md。将来函复制或链接至 ~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/incoming.[ext]。
  7. 按用户选择转交:
    • 创建案件 → 预填充的 /matter-intake
    • 回复律师函 → 预填充的 /demand-intake
    • 关联既有案件 → 更新日志中的 related_matters
    • 独立归档 → 无需进一步操作

收函处理

目的

来函是法务诉讼实务中的常规工作。极少数需要升级;大多数可以通过结构化回复或暂时搁置信函处理。本技能进行分流、交叉检索案件组合,并提供选项。

加载上下文

  • 来函文件(用户提供路径或在会话中发送)
  • ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml —— 扫描关联案件(相同对方、通过实体关系关联的对方、或同类案件类型+近期日期)
  • ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → 风险校准(用于实质理由评估)、执业背景(发函方是否为经常性对手?)、律师函实务惯例(事务所语调和回复默认策略)

工作流

步骤1:审读来函

从来函中提取:

  • 发函方 —— 主体、签署人、代理律师(如由外部律所签署)
  • 收函方 —— 我方哪个主体/人员
  • 送达方式 —— 快递、电子邮件、当面送达(影响期限计算)
  • 签收日期 vs. 签署日期
  • 来函类型 —— 付款催告、违约整改、停止侵权通知、证据保全要求、和解要约、其他
  • 具体要求 —— 对方要求什么、要求何时完成
  • 主张事实 —— 对方关于事实的版本
  • 法律依据 —— 援引的法律法规、合同条款、理论
  • 威胁内容 —— 如不按要求履行的后果
步骤2:案件组合交叉检索

在 _log.yaml 中检索:

  • 直接匹配 —— 相同对方的案件(对方简称匹配发函方)
  • 类型匹配 —— 与该对方此前同类案件(已结案件仍需关注——形成对方行为模式)
  • 事项重叠 —— 争议主题可能相同的案件(同一合同、同一产品、同一项目)

呈现检索结果:

  • 如直接匹配 + 进行中: 几乎可以确认是同一案件;建议将来函归入既有案件,不开新案。如系边缘关联,更新 related_matters。
  • 如直接匹配 + 已结: 注意——对方回头了。可能是新争议(开新案)或旧事重提(重新立案或修改原案)。用户决定。
  • 如类型匹配: 注明为先例/背景参考;大概率是独立案件,但可为回复策略提供信息。
  • 如无匹配: 新事项。按新案处理。
步骤3:实质理由评估

并非法律意见——是结构化的初步判断:

  • 事实 —— 对方主张的事实与我方掌握的是否一致?偏差在哪里?
  • 法律基础 —— 援引的法条/合同条款是否真正适用?(标注引用供用户核实——不自行验证法律。)
  • 对方胜算 —— 如果对方明天起诉,ta的诉讼逻辑是什么?
  • 我方抗辩 —— 我们可能的抗辩事由是什么?
  • 索赔金额 vs. 合理判赔 —— 对方的请求与其胜诉后法院可能支持的金额是否成比例?
  • 筹码与压力 —— 对方是否真的准备起诉?是否有诉讼能力?是否属于 ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md 中记录的常发性对手?

输出分流评级:有实质根据 / 有争议空间 / 较弱 / 无依据。直说——用户在做分流,不是在写代理词。

步骤4:回复方案

提出3-4个方案并附利弊分析:

方案A —— 实质性回复

  • 适用:来函有实质根据或至少存在争议空间;理性的回复能保护我方书面记录
  • 权衡:在书面中固定了我方立场
  • 下一步:/demand-intake,预填充回函起草字段

方案B —— 暂搁置信函

  • 适用:需要时间调查;不希望承认任何事项或触发对方期限计算
  • 权衡:不解决任何问题;争取2-4周时间
  • 下一步:起草简短确认函

方案C —— 和解回复

  • 适用:早期和解成本低于诉讼;愿意在不承认的前提下讨论
  • 权衡:需要和解谈判姿态——注意诉讼时效中断风险(《民法典》第195条)。[法条原文]
  • 下一步:/demand-intake,类型为 type: settlement-response

方案D —— 不回复 + 保留证据

  • 适用:来函无实质根据,或对方设定的期限不产生法律上的不利后果
  • 权衡:沉默在某些情况下可能对我不利(如账目确认);仍需考虑证据保全
  • 下一步:如尚未发出,通过 /legal-hold --issue 发出证据保全通知;记录来函并搁置

推荐一个方案,具体说明理由。

步骤5:期限分流
  • 对方宣告的期限 —— 注意,但对我方无约束力
  • 我方内部决策期限 —— 必须做出决定的日期(通常:对方期限减去5个工作日用于起草+审批)
  • 法定期限 —— 诉讼时效、合同约定的补正期、程序性要求

标注任何紧迫的法定期限,列入日程。

不沉默补充。 如来函引用的法规、案例或法条需核实,且向配置的法律研究工具的查询返回零条或极少结果,报告已找到的内容并停止。不要不询问就从联网搜索或模型知识填补空白。说:"搜索从[工具]返回了[N]条结果。[引用/法律问题]的覆盖范围似乎很薄。选项:(1)扩大搜索查询,(2)尝试其他研究工具,(3)搜索网络——结果将标注[联网检索——需复核],依赖前应核实,(4)标注[需审查]并在此停止。您希望选哪个?"由律师决定是否接受较低可信度的来源。

来源标注。 为分流意见中的每个引用——包括发函方援引的法律依据、我方回复方案的理由、以及实质理由评估中调取的研究——标注来源:[yuandian检索]用于通过检索连接器获取的引用;[联网检索——需复核]用于联网搜索引用;[模型知识——需验证]用于模型知识回忆的引用;[用户提供]用于来函中援引的法规。标注需验证的引用具有较高的编造风险,应首先核验。不得删除或压缩标签。

步骤6:撰写分流意见

输出:~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/triage.md。

markdown
[工作成果标头——根据插件配置 ## 输出——因角色不同;见 `## 使用者`]

# 来函分流——[对方名称]

> **用于分流判断,并非法律意见。** 本文件是登记审查和方案分析——不是法律实质意见。以下分流评级是支持律师决定如何路由来函的结构化判断,不是对实质问题的推荐意见,不替代特定案件的法律分析。每条援引的法规、规则或案例均标注供核实;每个实质判断属于律师,不属于本技能。

**代号:** [slug]
**收函日期:** [YYYY-MM-DD]
**收函主体:** [实体/人员]
**来函文件:** [路径]

---

## 来函概要

**发函方:** [主体、签署人、代理律师]
**来函类型:** [类型]
**具体要求:** [列表]
**对方设定的期限:** [日期]

## 主张事实

[对方版本,一段]

## 援引的法律依据

[引用——每条内联标注 `[需审查:法律适用性/时效性/管辖地]` —— 未经独立核对,不得依赖此处的任何引用]

## 威胁/声明的后续措施

[列表]

---

## 案件组合交叉检索

**直接匹配:** [如有,注明代号;否则"无"]
**类型匹配/先例:** [列表或"无"]
**事项重叠:** [列表或"无"]
**建议:** [新案 / 归入既有案件 / 通过 related_matters 关联 / 独立归档]

---

## 实质理由评估

**事实:** [与我方版本的一致性;分歧点]
**法律基础:** [适用性,附标注]
**对方诉讼前景:** [一段]
**我方抗辩:** [一段]
**索赔合理性:** [评估]
**威胁可信度:** [对方是否会起诉?是否有诉讼能力?是否为常发性对手?]

**分流评级:** [有实质根据 / 有争议空间 / 较弱 / 无依据] —— *用于路由的结构化判断,并非实质意见;`[需审查:律师确认后信赖]`*

---

## 回复方案

### A. 实质性回复
[理由、权衡、下一步]

### B. 暂搁置信函
[理由、权衡、下一步]

### C. 和解回复
[理由、权衡、下一步]

### D. 不回复 + 保留证据
[理由、权衡、下一步]

**推荐:** [A/B/C/D] —— [两句话说明理由] —— `[需审查:律师确认后执行]`

---

## 期限

- **对方设定的期限:** [日期]
- **我方内部决策期限:** [日期]
- **法定期限:** [诉讼时效、补正期、程序性要求——附日期]

---

## 即时行动

- [ ] 证据保全通知是否已发出——[是/否]——如否,运行 `/legal-hold [slug] --issue`
- [ ] 案件是否已在日志中创建——[是/否/待定]
- [ ] 承办律师是否已指定——[谁]
- [ ] 是否已通知保险——[是/否/不适用]
- [ ] 内部上报(法务负责人/CFO/业务负责人)——[谁/何时]
步骤7:转交

基于推荐意见和用户确认:

  • 创建案件 → 转交 /matter-intake:预填充对方、类型、source: demand-letter(收函),初始理论以防御姿态构建。
  • 回复律师函 → 转交 /demand-intake:预填充对方、分流上下文、期望回复结果。
  • 关联既有案件 → 更新该案件在 _log.yaml 中的 related_matters;追加事件至其 history.md。
  • 独立归档 → 保留在 ~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/;不更新案件组合。

以下一步决策树收尾

以 CLAUDE.md ## 输出 中的下一步决策树收尾。根据本技能刚产生的内容自定义选项——五个默认分支(起草X、上报、获取更多事实、观察等待、其他选择)是起点而非锁定项。决策树本身就是输出;由律师选择。

本技能不做什么

  • 验证被引用的法律。 标注引用供用户核对(确认是否为有效法律)或与外聘律师核实。对来函自行发明法律分析是执业风险敞口。
  • 发送回复。 回复函在 demand-draft 中起草;本技能停留在分流决定。
  • 对实质问题做出最终判断。 分流评级是用于路由的判断;正式的实质法律意见应由外聘律师或更深入的分析完成。
  • 替用户决定是否创建案件。 呈现推荐意见;用户决定。

© zhou210712, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in litigation-legal/skills/demand-received of zhou210712/claude-for-legal-ZH.

Open the folder on GitHubat commit 2f01c92

Compare with similar skills

Demand Received next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Demand Received compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Demand Received this skillzhou210712/claude-for-legal-ZH225—~1.4kAutomated safety check: PassApache-2.0
Tw Legal RAGaa0101181514/tw-legal-rag328—~580Automated safety check: PassCustom licence
Design Award SearchSeanJ1ang/design-judge-skills712—~3kAutomated safety check: PassApache-2.0
China Lawyer AnalystCSlawyer1985/china-lawyer-analyst196—~3.3kAutomated safety check: PassNone
Free Willsyahiidkamil/Software-Engineer-AI-Agent-Atlas401—~3.4kAutomated safety check: PassNone
Billing And Litigation BudgetTHUYRan/Legal-Skills-Chinese874—~5kAutomated safety check: PassNone

Similar skills

  • Tw Legal RAG

    aa0101181514/tw-legal-rag

    Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.

    328 GitHub stars~580 tokensUpdated 2 days ago
    Legal & ComplianceAuto-check passed
  • Design Award Search

    SeanJ1ang/design-judge-skills

    Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention…

    712 GitHub stars~3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • China Lawyer Analyst

    CSlawyer1985/china-lawyer-analyst

    通过中国法律视角分析事件,运用成文法解释、指导案例参照、请求权基础分析等方法, 理解权利义务、评估责任风险、识别法律依据并推荐合规策略。

    196 GitHub stars~3.3k tokensUpdated 8 mo ago
    Legal & ComplianceAuto-check passed
  • Free Will

    syahiidkamil/Software-Engineer-AI-Agent-Atlas

    Deliberate-choice procedure for a medium-to-high-stakes engineering fork — when the first plausible solution (the instinct, the default next-token pull) would be costly to get wrong.

    401 GitHub stars~3.4k tokensUpdated 3 mo ago
    DatabasesAuto-check passed
  • Billing And Litigation Budget

    THUYRan/Legal-Skills-Chinese

    A skill your agent uses when the user needs to track or manage attorney hours, expert fees, and investigation costs; control litigation spend; or prepare timesheets or expense statements for clients.

    874 GitHub stars~5k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Case Lifecycle Planning

    THUYRan/Legal-Skills-Chinese

    Case full-lifecycle planning skill. An agent skill from THUYRan/Legal-Skills-Chinese.

    874 GitHub stars~1k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

More from zhou210712/claude-for-legal-ZH

All 122 skills in this repo
  • Claim Chart

    zhou210712/claude-for-legal-ZH

    构建或审查要件分析表——专利权利要求对照表(侵权、无效或审查)或 民事构成要件分析表(任何诉讼请求或抗辩),每个单元格附精确引用, 缺口检测为优先输出。当用户要求要件分析表、权利要求对照表、 证据对照表、侵权或无效主张、逐要件映射,或问"我们证明[主张]还缺什么"时使用。

    225 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Client Intake

    zhou210712/claude-for-legal-ZH

    结构化接待——实践领域模板、跨领域考点识别、利益冲突标记、分流分类. An agent skill from zhou210712/claude-for-legal-ZH.

    225 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Gap Surfacer

    zhou210712/claude-for-legal-ZH

    参考资料:支持 /regulatory-legal:gaps 和 /regulatory-legal:comments 的共享差距和意见征集跟踪框架。跟踪未关闭的政策差距及其整改状态, 从 policy-diff 中获取差距,呈现开放和即将到期的事项,路由给负责人, 并通过企业通讯工具通知差距负责人,每次发送前需确认。

    225 GitHub stars~757 tokensUpdated 4 mo ago
    Auto-check passed
  • Launch Review

    zhou210712/claude-for-legal-ZH

    对照您的框架和风险校准进行全面产品上线审查。当用户说"审查这个上线" "[功能]法务审查""我们能上线吗""[产品]有什么法律问题"或引用了需要 逐类审查备忘录的产品需求文档或上线追踪工单时使用。

    225 GitHub stars~2k tokensUpdated 4 mo ago
    Auto-check passed
  • Reg Feed Watcher

    zhou210712/claude-for-legal-ZH

    检查法规动态源,报告自上次检查以来的新事项,按重要度阈值过滤。适用于用户说"检查法规动态"、"有什么新规定"、"法规更新"、从定时任务触发执行,或手动粘贴法规动态进行分类和差异分析时。

    225 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Renewal Tracker

    zhou210712/claude-for-legal-ZH

    展示具有即将到来的取消截止日期的合同,在通知窗口关闭前发出预警, 基于维护的续约登记册运行。当用户询问"什么即将续约""哪些续约即将到期" "我们是否错过了取消窗口""将此添加到续约追踪器"时使用,或按计划运行。

    225 GitHub stars~681 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Demand Received

What does Demand Received do?

来函分流处理——提取关键字段、交叉检索案件组合、评估实质理由、 提出响应方案并附建议,必要时转交案件登记或律师函起草. An agent skill from zhou210712/claude-for-legal-ZH. Demand Received is an agent skill from zhou210712/claude-for-legal-ZH.

When should I use Demand Received?

Demand Received fits situations like: tasks that involve Legal research.

How do I install Demand Received in Claude Code?

Run `npx skills add zhou210712/claude-for-legal-ZH --skill demand-received -a claude-code`. Or copy the skill folder (litigation-legal/skills/demand-received in zhou210712/claude-for-legal-ZH) into .claude/skills/demand-received in your project. Claude Code loads it when a task matches its description.

How do I install Demand Received in Codex?

Run `npx skills add zhou210712/claude-for-legal-ZH --skill demand-received -a codex`. Or copy the skill folder (litigation-legal/skills/demand-received in zhou210712/claude-for-legal-ZH) into .agents/skills/demand-received in your project. Codex loads it when a task matches its description.

Can I use Demand Received in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zhou210712/claude-for-legal-ZH --skill demand-received -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/demand-received, .gemini/skills/demand-received, .github/skills/demand-received and .opencode/skills/demand-received in your project.

What does Demand Received need to run?

SKILL.md names no scripts, command-line tools or credentials: Demand Received is instructions for the agent only.

Does Demand Received access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Demand Received safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Demand Received use?

Demand Received is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Demand Received use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Demand Received?

Skills that share tags, products or a category with Demand Received: Tw Legal RAG (aa0101181514/tw-legal-rag, 328 stars), Design Award Search (SeanJ1ang/design-judge-skills, 712 stars), China Lawyer Analyst (CSlawyer1985/china-lawyer-analyst, 196 stars) and Free Will (syahiidkamil/Software-Engineer-AI-Agent-Atlas, 401 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Demand Received?

zhou210712 (a GitHub user) maintains it in zhou210712/claude-for-legal-ZH, which has 225 GitHub stars. The repository holds 122 skills in this directory. The repository was last updated on May 15, 2026.

Source: zhou210712/claude-for-legal-ZH on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.