process-retriever

用于信托领域合规与运营中的流程检索助手场景，支持结构化处理与报告输出。

105 stars

byaifinlab

View on GitHub Installation ↓

Best use case

process-retriever is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

用于信托领域合规与运营中的流程检索助手场景，支持结构化处理与报告输出。

Teams using process-retriever should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/process-retriever/SKILL.md --create-dirs "https://raw.githubusercontent.com/aifinlab/FinClaw/main/skills/process-retriever/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/process-retriever/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How process-retriever Compares

Feature / Agent	process-retriever	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

用于信托领域合规与运营中的流程检索助手场景，支持结构化处理与报告输出。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# process-retriever

## 概述

本技能用于信托业务场景的结构化处理，支持数据解析、规则识别与报告输出。

## 输入要求

- 支持 JSON 数组或 JSONL
- 建议字段：`id`, `name`, `text`, `status`, `timestamp`，以及场景相关业务字段

## 工作流程

1. 明确业务口径与目标
2. 读取并清洗输入数据
3. 执行规则分析与风险识别
4. 输出结构化结果并标注复核事项
5. 人工复核后进入正式流程

## 执行方式

```bash
python scripts/analyze.py --input input.json --output report.md
```

## 输出结构

1. 样本概览（数量、等级分布）
2. 重点条目（分值、命中原因）
3. 风险提示与复核建议
4. 免责声明

## 质量要求

- 事实与判断分离
- 规则命中可追溯
- 保留自动生成需人工复核声明
- 不输出投资建议、授信决策或法律最终意见

## 使用示例

### 示例 1: 基本使用

```python
# 调用 skill
result = run_skill({
    "param1": "value1",
    "param2": "value2"
})
```

### 示例 2: 命令行使用

```bash
python scripts/run_skill.py --input data.json
```