opencontracts-guide
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "opencontracts-guide":https://skillpi.com/zh/skills/deepskill-ee356b80a3752291a582b6ea8386eb32c9c83ab8f09472ec0f8d86780560d4bf。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/domains/law/opencontracts-guide/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/domains/law/opencontracts-guide --skill opencontracts-guide来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目面向法律事务场景,提供“opencontracts-guide”技能的目录入口。公开标签:learning、合同、法律文档、NLP。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
---
name: opencontracts-guide
description: "Legal document annotation, versioning, and analysis platform"
metadata:
openclaw:
emoji: "📋"
category: "domains"
subcategory: "law"
keywords: ["legal documents", "contract annotation", "document versioning", "legal AI", "NLP legal", "MCP"]
source: "https://github.com/Open-Source-Legal/OpenContracts"
---
# OpenContracts Guide
## Overview
OpenContracts is an open-source platform for legal document annotation, versioning, and analysis. It provides collaborative annotation tools for legal text, version tracking across document drafts, NLP-powered clause extraction, and integration with AI agents via MCP. Designed for legal researchers, law firms, and teams managing large document collections that need structured annotation and analysis.
## Installation
```bash
# Docker deployment
git clone https://github.com/Open-Source-Legal/OpenContracts.git
cd OpenContracts
docker-compose up -d
# Access at http://localhost:3000
```
## Core Features
### Document Management
```python
from opencontracts import Client
client = Client("http://localhost:3000")
# Upload documents
doc = client.upload(
file="contract.pdf",
metadata={
"type": "NDA",
"parties": ["Company A", "Company B"],
"date": "2025-01-15",
"jurisdiction": "Delaware",
},
)
# Version tracking
versions = client.get_versions(doc.id)
for v in versions:
print(f"v{v.number}: {v.date} — {v.changes_summary}")
# Compare versions
diff = client.compare_versions(doc.id, v1=1, v2=3)
for change in diff.changes:
print(f"[{change.type}] Section {change.section}: "
f"{change.description}")
```
### Annotation
```python
# Create annotation project
project = client.create_project(
name="NDA Clause Analysis",
documents=[doc.id],
label_set=[
"confidentiality_scope",
"term_duration",
"exclusions",
"remedies",
"governing_law",
"dispute_resolution",
],
)
# Add annotations
client.annotate(
document_id=doc.id,
annotations=[
{
"start": 1250, "end": 1480,
"label": "confidentiality_scope",
"note": "Broad definition including derivatives",
},
{
"start": 2100, "end": 2250,
"label": "term_duration",
"note": "5-year term with auto-renewal",
},
],
)
```
### NLP Analysis
```python
# Automated clause extraction
clauses = client.extract_clauses(
doc.id,
clause_types=[
"indemnification",
"limitation_of_liability",
"termination",
"force_majeure",
"assignment",
],
)
for clause in clauses:
print(f"\n[{clause.type}] (confidence: {clause.confidence:.2f})")
print(f" Location: p.{clause.page}, para {clause.paragraph}")
print(f" Text: {clause.text[:100]}...")
# Risk assessment
risks = client.assess_risks(doc.id)
for risk in risks:
print(f"[{risk.severity}] {risk.clause}: {risk.description}")
```
### MCP Integration
```json
{
"mcpServers": {
"opencontracts": {
"command": "npx",
"args": ["@opencontracts/mcp-server"],
"env": {
"OPENCONTRACTS_URL": "http://localhost:3000"
}
}
}
}
```
## Search and Analytics
```python
# Full-text search across documents
results = client.search(
query="indemnification unlimited liability",
document_types=["NDA", "MSA"],
date_range=("2024-01-01", "2025-12-31"),
)
# Analytics
stats = client.analytics(project_id=project.id)
print(f"Documents annotated: {stats.docs_complete}")
print(f"Total annotations: {stats.total_annotations}")
print(f"Inter-annotator agreement: {stats.agreement:.2f}")
print(f"Most common clause: {stats.top_clauses[0]}")
```
## Use Cases
1. **Contract review**: Systematic clause analysis and risk assessment
2. **Legal research**: Annotate case law and legislation
3. **Compliance**: Track regulatory document requirements
4. **Training data**: Build labeled datasets for legal NLP
5. **Due diligence**: Structured review of deal documents
## References
- [OpenContracts GitHub](https://github.com/Open-Source-Legal/OpenContracts)
- [Legal NLP Resources](https://github.com/thunlp/LegalPapers)
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
0.0.1
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
面向法律专业人士的实用工具,解决合同审查、法律研究、合规等实际需求
评分依据
触发词覆盖全面且精准,包含法律文档、合同标注、版本控制等关键词
评分依据
文档结构清晰,包含完整的安装、功能演示、用例和参考链接
评分依据
工具来源明确,GitHub 地址清晰可查
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
-
安装或获取外部依赖
使用官方来源并锁定版本,在隔离环境检查安装脚本。当前文档检查不覆盖后续下载的代码。
主文档提及 · 第 129 行
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- github.com
- localhost
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。