Agent skill

Legal Risk Visualization

by zh-xx in zh-xx/legal-assistant-skills

法律风险结构化分析与可视化。基于法律分析文本，执行五步风险抽取模型，生成四层可视化输出（雷达图数据、风险矩阵、影响路径图、决策树）。

Apache-2.0Auto-check passedLegal & Compliance

Install Legal Risk Visualization

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a claude-code

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

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization --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/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legal-risk-visualization .claude/skills/legal-risk-visualization && 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/

Paste into Claude Code

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .claude/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/legal-risk-visualization .agents/skills/legal-risk-visualization && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .agents/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/legal-risk-visualization .cursor/skills/legal-risk-visualization && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .cursor/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/zh-xx/legal-assistant-skills.git --path legal-risk-visualization

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/legal-risk-visualization .gemini/skills/legal-risk-visualization && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .gemini/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/legal-risk-visualization .github/skills/legal-risk-visualization && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .github/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install zh-xx/legal-assistant-skills legal-risk-visualization --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/zh-xx/legal-assistant-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/legal-risk-visualization .opencode/skills/legal-risk-visualization && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "legal-risk-visualization" agent skill from https://github.com/zh-xx/legal-assistant-skills/tree/main/legal-risk-visualization into .opencode/skills/legal-risk-visualization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "legal-risk-visualization", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: legal-risk-visualization
GitHub stars: 174
Token cost: ~2.4k tokens
SKILL.md length: 568 words
Files: 9 (incl. scripts, references, assets)
Skills in repo: 8
Repo updated: Apr 18, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

法律风险结构化分析与可视化。基于法律分析文本，执行五步风险抽取模型，生成四层可视化输出（雷达图数据、风险矩阵、影响路径图、决策树）。

Works in 7 steps: ：读取并理解法律分析文本 → ：抽取风险节点 → ：分类节点并建立因果 → …
Tasks that involve Legal risk assessment
SKILL.md covers Overview, 术语规范, Workflow（7 步顺序执行） and Output Format, plus 4 more sections
Runs Python scripts from its folder; calls python3, pip3 and npm

What it does

Legal Risk Visualization is an agent skill from zh-xx/legal-assistant-skills. 法律风险结构化分析与可视化。基于法律分析文本，执行五步风险抽取模型，生成四层可视化输出（雷达图数据、风险矩阵、影响路径图、决策树）。适用于：(1) 用户提供法律分析报告要求风险可视化， (2) 要求风险结构分析或风险传导分析， (3) 要求生成风险决策建议或风险评估报告， (4) 提到"风险雷达图""风险矩阵""影响路径图""决策树"等关键词。

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts, reference files and assets (for example `assets/report-template.md`, `references/anchoring-tables.md` and `references/case-example.md`).

It sits in Legal & Compliance, covering Legal risk assessment. The repository describes itself as: AI assistant skills for legal work. Compatible with Claude Code, Codex, and other platforms. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Legal risk assessment

Example prompts

“/legal-risk-visualization”

Requirements

Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

：读取并理解法律分析文本
：抽取风险节点
：分类节点并建立因果
：计算风险属性
：识别关键节点与路径
：生成四层输出
：输出报告与图形渲染

What it can do on your machine

Read from SKILL.md and the folder at commit 3094afd. 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
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
- pip3
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip3 and npm, which can reach the network depending on how they are called.
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

Legal Risk Visualization loads about 2.4k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 568 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~50
When it runs · the whole SKILL.md, loaded when a task matches: ~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~10k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from zh-xx/legal-assistant-skills at commit 3094afd, republished under its Apache-2.0 licence (© zh-xx). 568 words, ~2,422 tokens.

Download SKILL.mdSave it as .claude/skills/legal-risk-visualization/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: legal-risk-visualization
description: 法律风险结构化分析与可视化。基于法律分析文本，执行五步风险抽取模型，生成四层可视化输出（雷达图数据、风险矩阵、影响路径图、决策树）。适用于：(1) 用户提供法律分析报告要求风险可视化， (2) 要求风险结构分析或风险传导分析， (3) 要求生成风险决策建议或风险评估报告， (4) 提到"风险雷达图""风险矩阵""影响路径图""决策树"等关键词。

Legal Risk Visualization

Overview

输入： 法律分析文本（简要或详尽均可）
输出： 结构化风险分析报告（Markdown 格式 + 4 张 PNG 图片）
报告语言： 始终中文
核心理念： 第三层（影响路径图）为唯一数据源头，其他三层从中派生
渲染工具： matplotlib（雷达图、风险矩阵）+ mmdc（Mermaid 影响路径图、决策树）
读者定位： 法律人 + 业务决策者，报告主体不使用工程化缩写

本 skill 将线性法律分析文本转化为网络化风险结构，支持内部决策与系统化风险管理。

不是简单风险评分工具，而是法律推理结构的可视化表达系统。

术语规范

全技能范围内使用以下中文术语，主报告中不使用英文缩写：

术语	含义	仅附录中可出现的缩写
风险指数	单节点综合风险评分	NRS
传导风险值	沿路径累积的风险	PCR
发生可能性	该风险发生的概率	P
影响严重性	该风险造成的损害程度	I
可干预程度	当事人可主动干预的程度	C
可补救程度	风险后果可修复的程度	R

节点类型在图表中使用颜色 + 图例区分，不在节点文本中显示类型标签：

内部分类	图表显示标签	颜色
事实节点	风险源头	🔴 红色 `#E74C3C`
法律判断节点	中间环节	🔵 蓝色 `#3498DB`
风险结果节点	风险后果	🟠 橙色 `#F39C12`
商业影响节点	业务影响	🟣 紫色 `#9B59B6`

边标签简化规则（数值权重仅保留在附录）：

传导强度	图中表现	附录中完整标注
强传导	粗箭头 `==>`	强因果 0.9
中传导	普通箭头 `-->`	中因果 0.6
弱传导/待确认	虚线 `-.->` + `"待确认"`	弱因果 0.3

统一配色方案（全部图表一致）：

颜色	色号	含义
🟢 绿色	`#27AE60`	安全/较低（1-2级）
🟡 黄色	`#F39C12`	关注/中等（3级）
🔴 红色	`#E74C3C`	警戒/较高（4-5级）
🔵 蓝色	`#3498DB`	可干预节点
⚫ 灰色	`#95A5A6`	待确认关系

Workflow（7 步顺序执行）

Step 1：读取并理解法律分析文本

通读全文，识别法律领域（合同纠纷、知识产权、劳动争议、公司治理等）
确定具体场景和涉及方
选择适用的风险维度（从以下维度中选择 4-6 个）：
- 合规风险、诉讼风险、财务风险、声誉风险、政策风险、执行风险、运营风险
- 可根据行业特征增加特定维度
维度选择依据：文本涉及的风险类别覆盖情况

Step 2：抽取风险节点

从文本中识别以下类型的表述，每个表述对应一个风险节点：

表述类型	识别特征
风险描述	"存在…风险""可能面临…"
不确定性判断	"尚不明确""有待确认""存在争议"
可能后果	"可能导致""将面临""后果为"
条件触发语句	"若…则…""一旦…就…""在…情况下"

输出节点列表，每个节点包含：

编号（N1, N2, ...）
名称（简短描述）
来源文本依据（原文引用）

Step 3：分类节点并建立因果

3a. 节点分类

将每个节点归类为以下四种类型之一：

类型	定义	典型特征	图表标签	颜色
事实节点	客观存在的状态或条件	合同条款、已发生事件	风险源头	🔴 红色
法律判断节点	需要法律推理才能确定的判断	责任认定、合规性判断	中间环节	🔵 蓝色
风险结果节点	最终的法律后果	赔偿、处罚、判决结果	风险后果	🟠 橙色
商业影响节点	对业务运营的实际影响	资金流、声誉、运营	业务影响	🟣 紫色

3b. 识别显式因果

通过逻辑连接词识别直接因果关系：

因此、所以、导致、造成、引发、使得
若…则…、如果…将…、一旦…就…
进而、从而、继而、以致
由于、鉴于、基于

显式因果 → 高置信度 ●●●

3c. 识别隐含因果

参考 references/causal-patterns.md 识别三种隐含模式：

并列暗示型 → 默认低置信度 ●○○
背景预设型 → 默认中置信度 ●●○
专业常识型 → 根据通用性判断（通用法律常识→高，行业特定→中，推测性→低）

3d. 设定边权重

传导类型	系数	适用场景
强传导	0.9	前因几乎必然导致后果
中传导	0.6	前因大概率导致后果
弱传导	0.3	前因可能导致后果
条件传导	0.1-0.9	取决于特定条件

Step 4：计算风险属性

4a. 节点属性评估

为每个节点评估四个属性（0-1 范围）：

属性	含义
发生可能性	该风险发生的可能性
影响严重性	该风险造成的损害程度
可干预程度	当事人可干预的程度
可补救程度	风险后果可修复的程度

4b. 计算风险指数

风险指数 = 发生可能性 × 影响严重性 × (1 - 可干预程度) × (1 - 可补救程度)

必须在附录中展示每个节点的完整计算过程。

4c. 计算传导风险值

传导风险值 = 起点风险指数 × ∏(边权重_i)

处理规则详见 references/formulas.md：

分叉： 各分支独立传导
汇聚（OR，默认）： 取各入边传导风险值最大值
汇聚（AND）： 取各入边传导风险值乘积（仅当法律逻辑要求"同时满足"时）
反馈环路： 拓扑排序识别，最大迭代 3 轮，收敛条件 < 5%

Step 5：识别关键节点与路径

识别以下四类关键节点：

节点类型	识别标准	意义
根源节点	入度 = 0	风险源头
放大节点	高出度的分叉点	风险扩散器
可控节点	可干预程度 > 0.3	优先干预目标
关键路径节点	位于最大传导风险值路径上	核心传导链

关键路径 = 从根节点到叶节点的所有路径中传导风险值最大的路径。

Step 6：生成四层输出

所有数据均从第三层（影响路径图）派生。

第一层：雷达图维度评分

将所有叶节点按风险维度分组
每个维度评分 = 该维度下叶节点传导风险值最大值
映射为 1-5 等级：

等级 = ceil(传导风险值 × 4) + 1，上限 5

使用 references/anchoring-tables.md 中的锚定表校准等级标签

第二层：风险矩阵（matplotlib 散点图）

取所有叶节点（终端风险），生成 matplotlib 四象限散点图：

横轴 = 发生可能性（0→1）
纵轴 = 影响严重性（0→1）
气泡大小 = 风险指数
颜色 = 象限对应色（统一配色方案）
四象限中文标签：高优先级 / 重点关注 / 常规监控 / 持续观察

数据格式（传给 render_risk_matrix.py）：

json

[
  {"name": "节点名称", "p": 0.9, "i": 0.6, "score": 0.34},
  ...
]

第三层：影响路径图（Mermaid）

生成 Mermaid 流程图，遵循以下规则：

mermaid

graph TD
    %% 节点格式：去掉类型标签，仅保留简短描述
    %% N1["新规扩展假期天数"]（不再写"事实节点"）

    %% 边标签简化：
    %% 强传导：==>（粗箭头，无文字）
    %% 中传导：-->（普通箭头，无文字）
    %% 弱传导/待确认：-.->|"待确认"|

    %% 使用 subgraph 分组：
    subgraph 风险源头
        N1["新规扩展假期天数"]
    end
    subgraph 中间环节
        N2["..."]
    end
    subgraph 风险后果
        N5["..."]
    end
    subgraph 业务影响
        N6["..."]
    end

    %% 节点着色（按类型）：
    %% 风险源头：fill:#E74C3C,stroke:#333,stroke-width:2px,color:white
    %% 中间环节：fill:#3498DB,stroke:#333,stroke-width:2px,color:white
    %% 风险后果：fill:#F39C12,stroke:#333,stroke-width:2px,color:white
    %% 业务影响：fill:#9B59B6,stroke:#333,stroke-width:2px,color:white
    %% 关键路径边：stroke:#E74C3C,stroke-width:3px
    %% 待确认边：stroke:#95A5A6,stroke-dasharray:5

图下方添加中文图例：

图例说明： 🔴 红色 = 风险源头 | 🔵 蓝色 = 中间环节 | 🟠 橙色 = 风险后果 | 🟣 紫色 = 业务影响 | 粗线 = 强传导关系 | 虚线 = 待确认关系

第四层：决策树（Mermaid graph TD）

基于可干预节点（可干预程度 > 0.3）生成 Mermaid 决策树。

菱形判断节点使用是非问答形式（非阈值数值）：

mermaid

graph TD
    D1{"公司假期制度是否<br/>已按新规更新？"}
    D1 -->|"是"| A1["无需行动"]
    D1 -->|"否"| A2["建议尽快更新制度"]

    %% 行动节点交通灯色：
    %% 绿=无需行动：fill:#27AE60,color:white
    %% 黄=建议行动：fill:#F39C12,color:white
    %% 红=紧急行动：fill:#E74C3C,color:white
    %% 菱形节点：fill:#3498DB,color:white

每个判断节点：

将风险节点名称转化为是非问题（"是否…？""有没有…？"）
分支标签只用 "是" / "否"
动作节点根据紧急程度着色

Step 7：输出报告与图形渲染

使用 assets/report-template.md 模板生成完整 Markdown 报告。

报告结构（面向两类读者的分层设计）：

一、风险概览        ← 决策者看这里（1页，交通灯摘要表 + 雷达图 + 核心建议）
二、核心发现与建议   ← 决策者+法律人（叙事式风险发现，非节点表格）
三、风险全景图      ← 两类读者（4张图 + 每张图前一句中文引导语）
四、风险情景分析    ← 法律人用来讲故事的场景推演
五、行动方案        ← 两类读者（含负责部门、建议时限、预期效果）
附录：分析方法与计算详情 ← 仅法律专业人员参考（公式、完整计算过程）

关键输出原则：

主报告中不出现英文缩写（NRS/PCR/P/I/C/R 仅在附录）
主报告中不出现节点内部类型名（事实节点/法律判断节点等），用颜色+图例区分
叙事优先：核心发现用完整段落描述，不用表格堆砌
情景化：每条关键路径写一个具体场景推演（事实→法律问题→可能后果→应对窗口）

Show full SKILL.md (263 more words)Show less

7a. 图形渲染步骤

画布尺寸动态计算规则：

Mermaid 图表渲染时需要根据节点数量动态调整画布尺寸，避免字体重叠：

节点数量	建议画布尺寸	适用场景
≤ 8 个节点	1200 x 900	简单流程
9-12 个节点	1600 x 1200	中等复杂度
13-16 个节点	2000 x 1500	较复杂
> 16 个节点	2400 x 1800	高复杂度

注意： 中文文字比英文更宽，建议在上述基础上增加 20% 宽度。

在输出目录中生成 4 张 PNG 图片：

第一层雷达图 → risk_radar.png

bash

python3 ~/.claude/skills/legal-risk-visualization/scripts/render_radar.py \
  --data '{"维度1":分数, "维度2":分数, ...}' \
  --output <输出目录>/risk_radar.png

第二层风险矩阵 → risk_matrix.png（使用 matplotlib，非 Mermaid）

bash

python3 ~/.claude/skills/legal-risk-visualization/scripts/render_risk_matrix.py \
  --data '[{"name":"节点名称","p":0.9,"i":0.6,"score":0.34}, ...]' \
  --output <输出目录>/risk_matrix.png

第三层影响路径图 → impact_pathway.png

将 graph TD Mermaid 代码写入 impact_pathway.mmd
调用渲染脚本（根据节点数量动态设置尺寸）：

bash

# 影响路径图节点数量通常在 8-14 之间，建议使用 1600x1200
python3 ~/.claude/skills/legal-risk-visualization/scripts/render_mermaid.py \
  --input <输出目录>/impact_pathway.mmd \
  --output <输出目录>/impact_pathway.png \
  --width 1600 --height 1200

第四层决策树 → decision_tree.png

将 graph TD Mermaid 代码写入 decision_tree.mmd
调用渲染脚本（根据节点数量动态设置尺寸）：

bash

# 决策树节点数量通常在 6-12 之间，建议使用 1400x1000
python3 ~/.claude/skills/legal-risk-visualization/scripts/render_mermaid.py \
  --input <输出目录>/decision_tree.mmd \
  --output <输出目录>/decision_tree.png \
  --width 1400 --height 1000

在 Markdown 报告中嵌入图片引用：![图名](文件名.png)

Output Format

输出目录包含：

1 份 Markdown 报告，包含：
- 风险概览（交通灯摘要表）
- 核心发现与建议（叙事式）
- 风险全景图（4 张图 + 引导语）
- 风险情景分析（场景推演）
- 行动方案（含负责部门、建议时限）
- 附录（公式、完整计算过程）
- 图片引用（![图名](文件名.png)）
4 张 PNG 图片：
- risk_radar.png — 风险雷达图（matplotlib 生成，含色带背景和等级标签）
- risk_matrix.png — 风险矩阵四象限图（matplotlib 生成，全中文标签）
- impact_pathway.png — 影响路径有向图（Mermaid graph TD，简化节点和边标签）
- decision_tree.png — 决策树（Mermaid graph TD，是非问答形式）

Dependencies

工具	用途	安装方式
matplotlib	雷达图和风险矩阵渲染	`pip3 install matplotlib`
numpy	雷达图色带渲染	`pip3 install numpy`（通常随 matplotlib 安装）
mmdc (mermaid-cli)	Mermaid 图渲染（影响路径图、决策树）	`npm install -g @mermaid-js/mermaid-cli`
Chrome/Chromium	mmdc 的浏览器后端	macOS 自带或手动安装

Key Rules

客户导向规则

面向读者： 报告主体面向法律人和业务决策者，术语使用中文全称，不使用工程化缩写
叙事优先： 核心发现用完整段落描述，避免大量表格堆砌
可讲述性： 报告第一节+第三节应能支持 5 分钟内向业务部门口头汇报核心风险
情景驱动： 每条关键路径需转化为具体场景推演，帮助非法律人理解风险传导逻辑

数据完整性规则

单一数据源： 第三层（影响路径图）是唯一数据源头，其他三层的数据必须从第三层派生
计算透明： 风险指数和传导风险值计算必须完整展示过程（放在附录中）
雷达图校准： 雷达图评分必须使用锚定表校准，不可凭感觉打分

因果关系规则

置信度标注： 低置信度因果关系必须用虚线标注并注明"待确认"
隐含因果标记： 所有隐含因果关系必须在附录中标注模式类型和置信度
显式优先： 优先采用显式因果，隐含因果作为补充

可视化规则

全中文： 所有图表标签、轴标签、图例必须为中文，不得出现英文
统一配色： 全部图表使用统一交通灯色系（绿/黄/红/蓝/灰）
关键路径高亮： 影响路径图中关键路径必须加粗/变色显示
节点着色： 按节点类型使用对应颜色区分（红/蓝/橙/紫）
图例说明： 每张图下方需附中文图例说明

决策规则

是非问答： 决策树使用是非问题形式，不使用数值阈值
行动建议： 必须按紧急程度排序，包含负责部门和建议时限
可控节点优先： 行动建议优先针对可干预节点，尤其是关键路径上的可干预节点

References

references/formulas.md — 完整计算模型（风险指数、传导风险值、映射公式、分叉/汇聚/环路规则）
references/causal-patterns.md — 因果关系识别（显式+隐含模式+置信度）
references/anchoring-tables.md — 各维度 1-5 等级锚定表
references/case-example.md — 技术服务合同纠纷端到端案例

Example

完整端到端案例见 references/case-example.md。

该案例演示了从"技术服务合同纠纷"原始法律分析文本，经过 7 步工作流，生成包含 7 个节点、2 条路径、完整四层输出的风险可视化报告的全过程。

Files

SKILL.md and 8 other files (scripts, references, assets) in legal-risk-visualization of zh-xx/legal-assistant-skills.

SKILL.md
assets/report-template.md
references/anchoring-tables.md
references/case-example.md
references/causal-patterns.md
references/formulas.md
scripts/render_mermaid.py
scripts/render_radar.py
scripts/render_risk_matrix.py

Open the folder on GitHubat commit 3094afd

Compare with similar skills

Legal Risk Visualization 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.

Legal Risk Visualization compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Legal Risk Visualization this skillzh-xx/legal-assistant-skills	174	—	~2.4k	Automated safety check: Pass	Apache-2.0	5 mo ago
Product Launch Legal Reviewanthropics/claude-for-legal	9.6k	2 repos	~5k	Automated safety check: Pass	Apache-2.0	11 days ago
Contract Renewal Trackeranthropics/claude-for-legal	9.6k	2 repos	~3.1k	Automated safety check: Pass	Apache-2.0	11 days ago
Deep Risk Analysiszubair-trabzada/ai-legal-claude	1.8k	—	~1.9k	Automated safety check: Pass	None	6 mo ago
Canghe Tianyanchafreestylefly/canghe-skills	461	—	~2.4k	Automated safety check: Pass	None	4 mo ago
EU AI Act System Inventoryanthropics/claude-for-legal	9.6k	3 repos	~2.8k	Automated safety check: Pass	Apache-2.0	11 days ago

Similar skills

Product Launch Legal Review
anthropics/claude-for-legal
Official
Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.
9.6k GitHub starsUsed in 2 repos~5k tokens
Legal & ComplianceAuto-check passed
Contract Renewal Tracker
anthropics/claude-for-legal
Official
Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.
9.6k GitHub starsUsed in 2 repos~3.1k tokens
Legal & ComplianceAuto-check passed
Deep Risk Analysis
zubair-trabzada/ai-legal-claude
Clause-by-clause contract risk analysis with severity scoring, financial exposure estimates, and prioritized remediation guidance
1.8k GitHub stars~1.9k tokensUpdated 6 mo ago
Legal & ComplianceAuto-check passed
Canghe Tianyancha
freestylefly/canghe-skills
Generates Tianyancha-style company and industry insight dashboards from researched enterprise data.
461 GitHub stars~2.4k tokensUpdated 4 mo ago
Legal & ComplianceAuto-check passed
EU AI Act System Inventory
anthropics/claude-for-legal
Official
Maintains a register of AI systems under the EU AI Act, recording each system's role and risk tier separately, because both can differ from one system to the next.
9.6k GitHub starsUsed in 3 repos~2.8k tokens
Legal & ComplianceAuto-check passed
Eu AI Act Readiness
seb1n/awesome-ai-agent-skills
Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…
206 GitHub stars~3.3k tokensUpdated 2 mo ago
Legal & ComplianceAuto-check passed

More from zh-xx/legal-assistant-skills

All 8 skills in this repo

Ad Compliance Review
zh-xx/legal-assistant-skills
广告合规审核技能，用于审核广告素材是否符合中国广告法及相关法规。适用场景：(1) 用户提交广告文案、广告素材要求合规审核时；(2) 用户提到"广告审核""广告合规""广告法审查"等关键词时；(3) 用户要求检查广告内容是否存在违法违规风险时；(4) 用户提交房地产、食品、医疗、药品、互联网等行业广告要求专项审核时。审核依据涵盖《广告法》《反不正当竞争法》及行业专项法规。
174 GitHub stars~1.2k tokensUpdated 5 mo ago
Auto-check passed
Contract Gen
zh-xx/legal-assistant-skills
合同生成技能，以资深法律专家身份生成完整合同。适用场景：(1) 用户要求'起草合同''生成合同''拟定协议''写合同''草拟合同'时；(2) 用户提供合同类型和交易信息，要求生成完整合同文本时；(3) 用户要求根据特定立场（甲方/乙方/买方/卖方/出租方/承租方）起草倾斜性合同时；(4) 用户要求将已有合同要点或业务条件生成为正式合同文本时。输出 Markdown 格式，可选导出 .docx。
174 GitHub stars~897 tokensUpdated 5 mo ago
Auto-check passed
Contract Review
zh-xx/legal-assistant-skills
Contract review skill that adds comment-based issue annotations without changing original text.
174 GitHub stars~1.6k tokensUpdated 5 mo ago
Auto-check passed
Food Label Review
zh-xx/legal-assistant-skills
预包装食品标签合规审核技能，用于审核食品标签是否符合 GB 7718（预包装食品标签通则）和 GB 28050（预包装食品营养标签通则）。适用场景：(1) 用户提交食品标签图片、文字或文档要求合规审核时；(2) 用户提到"食品标签审核""标签合规""营养标签审查""GB 7718""GB 28050"等关键词时；(3) 用户要求检查食品标签是否存在缺项、错误或违规风险时。支持 2011 版和…
174 GitHub stars~1.7k tokensUpdated 5 mo ago
Auto-check passed
Legal Job Search
zh-xx/legal-assistant-skills
法律AI求职助手 - 帮助法律人（法务/律师）使用AI辅助求职。支持公司/律所调研、法律风险分析、网页简历生成、针对性材料准备、面试备忘录生成。具备MCP工具级降级能力，无MCP时自动使用Web Search。
174 GitHub stars~1.7k tokensUpdated 5 mo ago
Auto-check passed
Law To Markdown
zh-xx/legal-assistant-skills
将法条/规范文件（.txt/.docx/.pdf）转为 Markdown。适用于用户要求“法条转 markdown”“pdf/docx 转 markdown”。处理 .pdf/.docx 时先检查是否已安装 mineru-ocr skill；未安装先引导安装，安装后优先用 mineru-ocr；仅在用户明确同意时再用本地回退方案。
174 GitHub starsUsed in 1 repo~669 tokens
Auto-check passed

Questions about Legal Risk Visualization

What does Legal Risk Visualization do?

法律风险结构化分析与可视化。基于法律分析文本，执行五步风险抽取模型，生成四层可视化输出（雷达图数据、风险矩阵、影响路径图、决策树）。. Legal Risk Visualization is an agent skill from zh-xx/legal-assistant-skills.

When should I use Legal Risk Visualization?

Legal Risk Visualization fits situations like: tasks that involve Legal risk assessment.

How do I install Legal Risk Visualization in Claude Code?

Run `npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a claude-code`. Or copy the skill folder (legal-risk-visualization in zh-xx/legal-assistant-skills) into .claude/skills/legal-risk-visualization in your project. Claude Code loads it when a task matches its description.

How do I install Legal Risk Visualization in Codex?

Run `npx skills add zh-xx/legal-assistant-skills --skill legal-risk-visualization -a codex`. Or copy the skill folder (legal-risk-visualization in zh-xx/legal-assistant-skills) into .agents/skills/legal-risk-visualization in your project. Codex loads it when a task matches its description.

Can I use Legal Risk Visualization 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 zh-xx/legal-assistant-skills --skill legal-risk-visualization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/legal-risk-visualization, .gemini/skills/legal-risk-visualization, .github/skills/legal-risk-visualization and .opencode/skills/legal-risk-visualization in your project.

What does Legal Risk Visualization need to run?

Going by SKILL.md and its folder, Legal Risk Visualization needs Python for the scripts in its folder and the command-line tools its instructions call (python3, pip3 and npm). Our summary lists: Python 3.

Does Legal Risk Visualization access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Legal Risk Visualization 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Legal Risk Visualization use?

Legal Risk Visualization 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 Legal Risk Visualization use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.8k tokens, read only when the agent opens those files.

What are the alternatives to Legal Risk Visualization?

Skills that share tags, products or a category with Legal Risk Visualization: Product Launch Legal Review (anthropics/claude-for-legal, 9.6k stars), Contract Renewal Tracker (anthropics/claude-for-legal, 9.6k stars), Deep Risk Analysis (zubair-trabzada/ai-legal-claude, 1.8k stars) and Canghe Tianyancha (freestylefly/canghe-skills, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Legal Risk Visualization?

zh-xx (a GitHub user) maintains it in zh-xx/legal-assistant-skills, which has 174 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 18, 2026.

Source: zh-xx/legal-assistant-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Legal Risk Visualization

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Legal Risk Visualization

Overview

术语规范

Workflow（7 步顺序执行）

Step 1：读取并理解法律分析文本

Step 2：抽取风险节点

Step 3：分类节点并建立因果

3a. 节点分类

3b. 识别显式因果

3c. 识别隐含因果

3d. 设定边权重

Step 4：计算风险属性

4a. 节点属性评估

4b. 计算风险指数

4c. 计算传导风险值

Step 5：识别关键节点与路径

Step 6：生成四层输出

第一层：雷达图维度评分

第二层：风险矩阵（matplotlib 散点图）

第三层：影响路径图（Mermaid）

第四层：决策树（Mermaid graph TD）

Step 7：输出报告与图形渲染

7a. 图形渲染步骤

Output Format

Dependencies

Key Rules

客户导向规则

数据完整性规则

因果关系规则

可视化规则

决策规则

References

Example

Files

Compare with similar skills

Similar skills

More from zh-xx/legal-assistant-skills

Related

Questions about Legal Risk Visualization