Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LawMotion-AI/Vibe-Lawyering --skill contract-reviewgit clone --depth 1 https://github.com/LawMotion-AI/Vibe-LawyeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lawmotion-ai/vibe-lawyering/contract-review)<a href="https://agentmods.dev/skills/lawmotion-ai/vibe-lawyering/contract-review"><img src="https://agentmods.dev/badge/skills/lawmotion-ai/vibe-lawyering/contract-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lawmotion-ai/vibe-lawyering/contract-review"><img src="https://agentmods.dev/badge/skills/lawmotion-ai/vibe-lawyering/contract-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.05097 |
| Opus 5 | $0.00064 | $0.02549 |
| Sonnet 5 | $0.00026 | $0.01019 |
| Haiku 4.5 | $0.00013 | $0.00510 |
Grade C, and why
contract-review scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ~/.claude/.mcp.json << 'EOF' Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat > ~/.claude/.mcp.json << 'EOF' How it starts
The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
合同审核技能
概述
本技能通过仅添加批注的方式审查合同(不修改原文)。采用四层审核模型(主体核验、基础审核、商务条款、法律条款),生成:
- 带批注的合同(.docx)
- 合同概要(.docx)
- 综合审核意见(.docx)
- 业务流程图(Mermaid + 渲染图片)
语言规则: 检测合同主要语言,所有生成内容(批注、概要、意见、流程图文字)使用该语言输出。参考 references/language.md。
企查查企业核验:CLI + MCP 双模式
🎯 架构原则:CLI 与 MCP 互补使用,发挥各自优势
| 功能模块 | 推荐工具 | 优势 | 数据来源标注 |
|---|---|---|---|
| 主体信息核验 | QCC CLI(终端直连) | 低延迟、高可靠、无需MCP配置 | 基于企查查 CLI 终端直连获取 |
| 风险穿透预警 | QCC MCP(深度分析) | 18类风险全面扫描、AI深度分析 | 基于企查查 MCP 深度分析 |
为什么采用双模式?
- CLI(终端直连):适合主体核验这类标准化查询,响应快、稳定性高
- MCP(深度分析):适合风险穿透这类需要复杂推理的分析,AI增强理解
CLI 配置(推荐用于主体信息核验)
⚠️ 重要:启用企查查 CLI 企业核验前,确保 CLI 已安装
安装检查:
# 验证 QCC CLI 是否已安装
qcc --version
# 测试企业信息核验
qcc company get_company_registration_info --searchKey "企查查科技股份有限公司"
预期输出:
正在调用 company/get_company_registration_info...
* 企业名称: 企查查科技股份有限公司
* 统一社会信用代码: 91320594088140947F
* 法定代表人: 陈德强
* 登记状态: 在业
...
CLI 安装(如未安装):
# 查看 QCC CLI 安装指南
pip install qcc-cli
# 或从以下地址下载:https://github.com/duhu2000/qcc-cli
MCP 配置(用于深度风险分析)
⚠️ 可选:启用企查查 MCP 进行增强型风险穿透分析
检查清单:
- ✅
~/.claude/.mcp.json存在且配置正确 - ✅
QCC_MCP_API_KEY环境变量已设置 - ✅ Claude Code 已重启以加载 MCP 配置
配置步骤:
# 1. 创建 MCP 配置文件
cat > ~/.claude/.mcp.json << 'EOF'
{
"mcpServers": {
"qcc-company": {
"url": "https://agent.qcc.com/mcp/company/stream",
"headers": { "Authorization": "Bearer ${QCC_MCP_API_KEY}" }
},
"qcc-risk": {
"url": "https://agent.qcc.com/mcp/risk/stream",
"headers": { "Authorization": "Bearer ${QCC_MCP_API_KEY}" }
}
}
}
EOF
# 2. 设置 API 密钥
export QCC_MCP_API_KEY="your_api_key_here"
# 3. 重启 Claude Code
详见:https://github.com/duhu2000/legal-assistant-skills/blob/main/docs/MCP_CONFIGURATION.md
工作流程
执行步骤(必须遵循)
当用户请求合同审核时(如"请审核这份合同"):
- 定位合同文件 - 如用户仅提供文件名,在常用目录(
/Downloads、/.claude/downloads、当前目录)中搜索完整路径 - 读取合同 使用可用工具(优先 pandoc,备选直接 XML)- 必须使用第1步中找到的正确完整路径
- 提取合同主体 并通过 QCC CLI(首选)、QCC MCP(备选)或 Web Search(最后备选)进行核验
- 中国企业核验工具优先级:
- QCC CLI(首选):使用
qcc company get_company_registration_info --searchKey "企业名称"进行快速企业核验- 如 CLI 返回数据 → 作为权威来源使用
- 如 CLI 未安装或失败 → 降级到 MCP
- QCC MCP(备选):如 CLI 不可用但 MCP 已配置,使用 MCP 工具:
qcc-company/get_company_registration_info用于企业核验qcc-company/get_company_profile用于补充信息- 如 MCP 返回数据 → 作为权威来源使用
- Web Search(最后备选):仅当 CLI 和 MCP 都不可用时使用
- QCC CLI(首选):使用
- 数据来源标注:始终在批注中标注核验来源:
- CLI 核验 → 标注"基于企查查 CLI 终端直连获取"
- MCP 核验 → 标注"基于企查查 MCP 服务获取"
- 风险分析 → 标注"基于企查查 MCP 深度分析"
- Web Search → 标注"基于公开网络信息查询"
- 中国企业核验工具优先级:
- 生成所有必需内容(必须创建以下全部内容):
- 合同概要文字 → 作为
summary_text参数传入 - 综合审核意见文字 → 作为
opinion_text参数传入 - Mermaid 流程图代码 → 作为
flowchart_mermaid参数传入(可选,如有问题可跳过)
- 合同概要文字 → 作为
- 执行工作流程 通过
review_contract()或ContractReviewWorkflow.run_full_workflow()并传入所有生成内容:
重要:不要直接写入文件。让工作流程生成 DOCX 文件。workflow.run_full_workflow( comments=comments, output_docx_filename="合同_审核版.docx", summary_text=summary_text, # 合同概要内容 opinion_text=opinion_text, # 综合审核意见内容 flowchart_mermaid=flowchart_mermaid, # 可选 ) - 向用户报告结果 包含所有输出文件位置
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README_QCC_MCP.md 9.3 KB
- references/checklist.md 6.6 KB
- references/examples.md 5.5 KB
- references/flowchart.md 1.8 KB
- references/language.md 2.2 KB
- references/opinion.md 1.3 KB
- references/summary.md 2.8 KB
- references/technical.md 2.7 KB
- scripts/__init__.py 50 B runs code
- scripts/api_list_checker.py 251 B runs code
- scripts/contract_analyzer.py 9.2 KB runs code
- scripts/contract_review.py 2.7 KB runs code
- scripts/document.py 11 KB runs code
- scripts/error_handling.py 16 KB runs code
- scripts/mermaid_renderer.py 6.9 KB runs code
- scripts/ooxml/__init__.py 189 B runs code
- scripts/ooxml/pack.py 3.5 KB runs code
- scripts/ooxml/unpack.py 1.1 KB runs code
- scripts/ooxml/validate.py 1.7 KB runs code
- scripts/ooxml/validation/__init__.py 433 B runs code
- scripts/ooxml/validation/base.py 1.5 KB runs code
- scripts/ooxml/validation/docx.py 311 B runs code
- scripts/ooxml/validation/pptx.py 274 B runs code
- scripts/ooxml/validation/redlining.py 217 B runs code
- scripts/opinion_renderer.py 4.2 KB runs code
- scripts/qcc_mcp_client.py 29 KB runs code
- scripts/summary_renderer.py 9.1 KB runs code
- scripts/utilities.py 3.1 KB runs code
- scripts/workflow.py 75 KB runs code
- SKILL_EN.md 19 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 472 lines · 129 tokens per session scan C 56bc29f33955
contract-review is a skill published in the GitHub repository LawMotion-AI/Vibe-Lawyering (20 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 5,097 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…