Agent skill

AI Tool Handoff

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

检测 AI 辅助审查工具(如 Luminance、Kira 等)是否在使用中,将大批量条款提取 交接给工具,并按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 中的 信任层级对其输出进行 QA。当用户说"交给AI工具""批量审查""AI提取"或 diligence-issue-extraction…

Apache-2.0Auto-check passedAgent Workflows

Install AI Tool Handoff

skills CLI
$ npx skills add zhou210712/claude-for-legal-ZH --skill ai-tool-handoff -a claude-code

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

GitHub CLI
$ gh skill install zhou210712/claude-for-legal-ZH ai-tool-handoff --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/corporate-legal/skills/ai-tool-handoff .claude/skills/ai-tool-handoff && 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
ai-tool-handoff
GitHub stars
225
Token cost
~833 tokens
SKILL.md length
115 words
Files
1
Skills in repo
122
Repo updated
First seen
Licence
Apache-2.0

At a glance

检测 AI 辅助审查工具(如 Luminance、Kira 等)是否在使用中,将大批量条款提取 交接给工具,并按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 中的 信任层级对其输出进行 QA。当用户说"交给AI工具""批量审查""AI提取"或 diligence-issue-extraction…

  • Tasks that involve Agent instruction files
  • SKILL.md covers 事项上下文, 目的, 加载上下文 and 何时交接, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Tool Handoff is an agent skill from zhou210712/claude-for-legal-ZH. 检测 AI 辅助审查工具(如 Luminance、Kira 等)是否在使用中,将大批量条款提取 交接给工具,并按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 中的 信任层级对其输出进行 QA。当用户说"交给AI工具""批量审查""AI提取"或 diligence-issue-extraction 遇到大批量类别时使用。

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “交给AI工具”
  • “/ai-tool-handoff”

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

AI Tool Handoff loads about 833 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 115 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~833

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). 115 words, ~833 tokens.

Download SKILL.mdSave it as .claude/skills/ai-tool-handoff/SKILL.md (or your agent's skills folder).
name
ai-tool-handoff
description
检测 AI 辅助审查工具(如 Luminance、Kira 等)是否在使用中,将大批量条款提取 交接给工具,并按 `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` 中的 信任层级对其输出进行 QA。当用户说"交给AI工具""批量审查""AI提取"或 diligence-issue-extraction 遇到大批量类别时使用。

AI 工具交接

事项上下文

事项上下文。 检查实务级 CLAUDE.md 中的 ## 事项工作区。如果 Enabled 为 ✗(企业法务用户的默认值),跳过本段其余内容——技能使用实务级上下文,事项机制不可见。如果已启用且无活跃事项,询问:"这是哪个事项?运行 /corporate-legal:matter-workspace switch <事项简称> 或说 实务级。"加载活跃事项的 matter.md 获取事项特定上下文和覆盖规则。输出写入事项文件夹 ~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/<事项简称>/。除非 跨事项上下文 为 开,否则绝不读取其他事项的文件。


目的

AI 辅助审查工具擅长一件事:读取500份合同并找到每一条控制权变更条款。它们不擅长判断——决定某条特定的控制权变更条款是否真的被本次交易结构触发。

本技能将批量提取交接给合适的工具,然后对返回的结果运行 QA 层。

交接之前: 先尝试 tabular-review(/corporate-legal:tabular-review)。对于用户环境可以处理的任何内容——几百份文档、已定义的列模式——原生表格审查设置更快、无按文档计费成本,且将工作成果保留在本地。当语料确实过于庞大、团队已有许可证和工作流,或事项要求具有已验证溯源链的工具时,再交接给 AI 工具。

加载上下文

~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md → AI辅助审查:

  • 使用的工具(Luminance / Kira / 无)
  • 用于什么(哪些条款类型)
  • 信任层级(直接使用 / 抽查 / 全面复核)
  • 交接流程(谁加载,谁QA)

如果 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 显示无AI工具 → 本技能为无操作。所有内容直接通过 diligence-issue-extraction 处理。

何时交接

以下全部满足时交接:

  • 类别有超过50份文档(少于50份时直接阅读更快)
  • 提取目标是工具擅长的条款类型(控制权变更、合同转让、独家性、最惠国待遇、终止、自动续约)
  • 文档相对统一(全部是相似文本的客户合同——而非合同、函件和董事会纪要的混搭)

不要交接:

  • 定制或经过大量谈判的文档
  • 补充函和修订协议(上下文依赖性强,工具会遗漏与主协议的互动)
  • 任何问题是"这对交易意味着什么"而非"该条款是否存在"的情况

交接

第1步:准备批次
  • 从数据室目录中识别批次文档
  • 按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 指定提取目标(哪些条款类型)
  • 注明重要性阈值以便过滤工具输出
第2步:加载(或指示加载者)

按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md ——由谁加载。如果是你,生成加载指令。如果是别人,生成请求:

markdown
## [工具] 加载请求 — [交易代码] — [类别]

**文档:** [N]份 来自数据室文件夹 [路径]
**加载至:** [工具工作区/事项]
**提取目标:**
- 控制权变更 / 合同转让
- 独家性
- [等——按 `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`]

**过滤输出:** 仅标记提取目标存在的情况——无需为每份文档报告"未发现控制权变更条款"。

**返回截止:** [日期]
第3步:QA 输出

当工具返回结果时,按信任层级应用:

"直接使用": 直接录入尽调发现。(仅在 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 如此设置时使用——这种情况很少见。)

"抽查 X%": 随机抽取 X% 的已标记文档。对每份,阅读实际条款并与工具的提取对比。如错误率低,接受该批次。如发现错误,扩大样本。

"对已标记项进行完整人工复核": 工具缩小范围(500份文档 → 80份含控制权变更条款)。人工阅读全部80份。工具节省了阅读420份干净文档的时间。

第4步:判断层

工具找到了条款。现在应用判断:

对每项已标记的控制权变更条款:是否实际被本次交易触发?

  • 股权转让 vs. 资产转让 vs. 合并——不同的触发条件
  • 合同中如何定义"控制权变更"——多数股权?董事会控制?其他?
  • 是否有针对本类交易的例外条款?

这是工具无法完成的部分。输出以内部格式进入尽调发现。

输出

以下QA摘要来源于具有特权、保密或两者兼有的数据室文件。它继承来源文件的特权和保密状态——向特权保护圈之外分发可能放弃特权。存放于事项的特权文件中。

markdown
## AI 工具交接摘要 — [类别]

**工具:** [Luminance / Kira]
**已处理文档:** [N]
**提取目标:** [条款类型]

### QA

**信任层级:** [按 `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`]
**样本量:** [N]份文档抽查
**错误率:** [X]% — [接受 / 扩大样本 / 触发全面复核]

### 结果

| 条款类型 | 工具标记文档 | 经判断层后 | 重大 |
|---|---|---|---|
| 控制权变更 | [N] | [N 实际被交易结构触发] | [N 超过阈值] |
| 合同转让 | [N] | [N] | [N] |

**→ 已将 [N] 项发现加入尽调问题清单**
**→ 已将 [N] 项同意事项加入交割检查表**

以下一步行动决策树收尾

以 CLAUDE.md ## 输出规范 中的下一步行动决策树收尾。根据本技能刚产出的内容定制选项——五个默认分支(起草X、上报、补充事实、监控等待、其他)是起点,不是锁定。决策树本身就是产出;律师选择。

本技能不做什么

  • 不运行 Luminance 或 Kira——它管理交接和 QA。由人工(或工具自身的界面)运行提取。
  • 不完全用自身判断替代工具的输出——如果 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 说抽查10%,就检查10%,不是100%。
  • 不决定信任层级——这在 CLAUDE.md 中设定,在冷启动时基于团队对工具的经验确定。

© 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 corporate-legal/skills/ai-tool-handoff of zhou210712/claude-for-legal-ZH.

Open the folder on GitHubat commit 2f01c92

Compare with similar skills

AI Tool Handoff 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.

AI Tool Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Tool Handoff this skillzhou210712/claude-for-legal-ZH225—~833Automated safety check: PassApache-2.0
Using Agent Skillsaddyosmani/agent-skills105k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.8k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k20 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    105k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.8k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 20 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-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

Categories

Questions about AI Tool Handoff

What does AI Tool Handoff do?

检测 AI 辅助审查工具(如 Luminance、Kira 等)是否在使用中,将大批量条款提取 交接给工具,并按 ~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md 中的 信任层级对其输出进行 QA。当用户说"交给AI工具""批量审查""AI提取"或 diligence-issue-extraction…. AI Tool Handoff is an agent skill from zhou210712/claude-for-legal-ZH.

When should I use AI Tool Handoff?

AI Tool Handoff fits situations like: tasks that involve Agent instruction files.

How do I install AI Tool Handoff in Claude Code?

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

How do I install AI Tool Handoff in Codex?

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

Can I use AI Tool Handoff 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 ai-tool-handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-tool-handoff, .gemini/skills/ai-tool-handoff, .github/skills/ai-tool-handoff and .opencode/skills/ai-tool-handoff in your project.

What does AI Tool Handoff need to run?

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

Does AI Tool Handoff 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 AI Tool Handoff 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 AI Tool Handoff use?

AI Tool Handoff 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 AI Tool Handoff use?

About 833 tokens (SKILL.md is roughly 3.3k 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 AI Tool Handoff?

Skills that share tags, products or a category with AI Tool Handoff: Using Agent Skills (addyosmani/agent-skills, 105k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Tool Handoff?

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.