What makes Boheng Investment Workflow notable?

2K downloads. Trust evidence available

How should Boheng Investment Workflow be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Boheng Investment Workflow

投资研究多智能体决策系统 - 8位专业分析师并行研究，加权投票给出投资建议。支持A股股票/基金/ETF/可转债。支持真实财报数据（baostock）或基础行情数据。⚠️ 风险提示：分析结果仅供学习参考，不构成投资建议。 Skill: Boheng Investment Workflow Owner: zhangboheng Summary: 投资研究多智能体决策系统 - 8位专业分析师并行研究，加权投票给出投资建议。支持A股股票/基金/ETF/可转债。支持真实财报数据（baostock）或基础行情数据。⚠️ 风险提示：分析结果仅供学习参考，不构成投资建议。 Tags: AI:1.2.4, fund:1.2.4, investment:1.2.4, latest:1.5.5, stock:1.2.4 Version history: v1.5.5 | 2026-05-19T11:23:09.055Z | user 新增动态ROE评估系统，根据行业基准和财报季度动态调整评估标准，新增季度对比表 v1.5.4 | 2026-05-11T11:20:15.599Z | user 修复显示名称为Boheng Investment Workflow v1.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.0k

Updated

Oct 9, 2026

Version

1.5.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2K downloadsadoption · observed Oct 9, 2026
Latest release: 1.5.5release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s17aecn58hk3xdbx0aekn3xq3d85k4d7:boheng-investment-workflow

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhangboheng-boheng-investment-workflow/snapshot"

Documentation

CLAWHUB

156,472 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: boheng-investment-workflow
version: 1.5.5
author: 张权 (Zhang Quan)
author_website: https://www.luckydesigner.space
author_brand: Luckydesigner（行运设计师）
author_pen_name: 伯衡君
license: MIT
description: "投资研究多智能体决策系统 - 8位专业分析师并行研究，加权投票给出投资建议。支持A股股票/基金/ETF/可转债。支持真实财报数据（baostock）或基础行情数据。⚠️ 风险提示：分析结果仅供学习参考，不构成投资建议。"
---

⚠️ **安全提示**
- 分析报告保存在 `~/.openclaw/workspace/investment/reports/`，已加入 .gitignore
- 如有敏感信息，请从 USER.md 中移除或设置 `ENABLE_BROWSER_NEWS=0` 禁用浏览器功能
- Agent Browser 新闻功能默认关闭，需设置 `ENABLE_BROWSER_NEWS=1` 启用

📖 **USER.md 数据使用**
本系统会读取 `USER.md` 获取投资偏好用于个性化建议：
- 投资风格、风险偏好、持仓周期（用于调整建议）
- 不会保存或上传用户数据，仅本地使用

⚠️ **风险警告**：本系统提供的分析结果仅供参考，不构成任何形式的投资建议。用户应自行承担投资风险，决策前请务必查阅官方财报或咨询专业投资顾问。

keywords:
  - 股票分析
  - 投资决策
  - 多智能体
  - 多数据源
  - A股
  - 财务分析
  - 估值分析
  - 基金分析
  - ETF分析
  - 可转债分析
  - baostock
  - 真实财报
trigger_keywords:
  - 分析
  - 投资
  - 股票
  - 基金
  - ETF
  - 可转债
  - 值得投资吗
  - 能买吗
  - 可以买吗
  - 这支股票怎么样
  - 这只股票怎么样
  - 股票好不好
  - 股票怎么样
  - 买入建议
  - 卖出建议
  - 投资建议
  - 财务分析
  - 估值分析
  - 推荐股票
  - 推荐基金
min_openclaw_version: "1.0.0"
security:
  network_access: true
  allowed_domains:
    - qt.gtimg.cn
    - web.ifzq.gtimg.cn
    - push2.eastmoney.com
    - stock.xueqiu.com
    - finance.sina.com.cn
    - api.baostock.com
    - so.eastmoney.com
  file_writes:
    - ~/.openclaw/workspace/investment/
  system_commands: false
  https_only: true
  background_tasks: false
  # 安全修复 v1.5.2:
  # - 移除所有 subprocess pkill 系统命令调用
  # - Agent Browser CLI 调用保留（OpenClaw 沙箱内置工具）
  # - 新增新闻内容输入净化层（防止提示注入）
  # - 严格限制外部内容长度与字符集
  browser_automation: optional_disabled_by_default
  akshare_optional: "True - 推荐安装baostock获取真实财报：pip install baostock"
  # 安全说明:
  # 本技能不使用系统命令(subprocess)，agent-browser 调用属于 OpenClaw 内置 CLI
  # 新闻模块已添加输入净化(sanitize_news_field)防止提示注入攻击
  input_sanitization: true
---

# 投资研究多智能体决策系统

## 🎯 核心特性

| 特性 | 说明 |
|------|------|
| ✅ **多智能体分析** | 8位专业分析师并行研究 |
| ✅ **加权投票机制** | 按权重计算最终投资建议 |
| ✅ **多标的支持** | 支持A股股票、基金、ETF、可转债 |
| ✅ **实时行情** | 通过腾讯财经API获取实时行情 |
| ✅ **财务数据分析** | 双模式：基础估算 或 baostock真实财报 |
| ✅ **多年财务趋势** | 近5年财务数据对比，识别风险信号 |
| ✅ **行业对比分析** | 与同行业公司对比，判断竞争地位 |
| ✅ **baostock支持** | 获取真实财报数据，替代估算值（需安装baostock） |
| ✅ **快速分析入口** | quick_analysis.py - 自动调用8位分析师 |
| ✅ **完整报告** | 输出结构化投资决策报告（含数据来源标注） |
| ✅ **风险提示** | 识别并提示潜在风险 |
| ✅ **质检功能** | 自动检查报告生成、数据完整性 |

> ⚠️ **重要风险提示**：
> - 本技能分析结果**仅供学习参考**，不构成任何投资建议
> - 投资有风险，决策需谨慎，务必以官方财报为准

### 📊 数据获取优先级

本技能采用**多级降级策略**获取数据，确保在任何情况下都能提供分析结果：

```
┌─────────────────────────────────────────────────────────────┐
│                    数据获取优先级                              │
├─────────────────────────────────────────────────────────────┤
│  1️⃣ AKShare    → 真实财报数据（推荐首选）                   │
│     ↓ 失败                                                      │
│  2️⃣ baostock   → 真实财报数据（备用）                        │
│     ↓ 失败                                                      │
│  3️⃣ 模型预训练数据 → 基于AI模型的知识推断                    │
│     ↓ 无数据                                                    │
│  4️⃣ 默认估算值   → 行业平均值（保底）

_meta.json

{
  "ownerId": "kn7bj8mtcw6j7s73kyz9zhck6985kv85",
  "slug": "boheng-investment-workflow",
  "version": "1.5.5",
  "publishedAt": 1779189789055
}

CHANGELOG.md

# 更新日志

## v1.5.5 (2026-05-19)

### ✨ 新增功能
- **动态ROE评估系统** (`roe_evaluator.py`)
  - 根据行业基准动态调整ROE评估标准（不再固定15%）
  - 考虑财报季度因素：Q1=25%, Q2=50%, Q3=75%, Q4=100%
  - 支持历史趋势对比
  - **新增季度对比表**：显示每个季度的行业基准、动态阈值、公司ROE、差距

### 🔧 优化
- `analysts.py` 集成动态ROE评估
- `financial_data_baostock.py` 财报期间改为结构化数据
- `quick_analysis.py` 传递财报季度信息给分析师

### 📚 文档更新
- SKILL.md 新增"动态ROE评估说明"章节（含季度对比表示例）
- 文件结构新增 `roe_evaluator.py`

---

## v1.5.2 (2026-05-11)

### 🔧 优化
- 根据查询日期自动匹配对应财报期间
- 支持 -d 参数指定日期

---

## v1.5.1 (2026-05-xx)

### 早期版本
- 基础8位分析师系统
- baostock/AKShare双数据源
- 财务趋势分析
- 行业对比分析

skill-card.md

## Description:

Investment research multi-agent decision system that runs eight analyst roles in parallel, applies weighted voting, and produces informational analysis for A-share stocks, funds, ETFs, and convertible bonds.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zhangboheng](https://clawhub.ai/user/zhangboheng)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to research Chinese A-share stocks, funds, ETFs, and convertible bonds through multi-agent financial analysis, data-source labeling, and generated research reports. Outputs are informational and should not be treated as financial advice.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill automatically reads USER.md investment preferences and can persist derived profile details in local reports.

Mitigation: Remove sensitive details from USER.md before use, run the skill in an isolated workspace, and review or delete generated reports before sharing the workspace.

Risk: The skill performs external financial and news data requests, and optional browser news collection can launch browser subprocesses.

Mitigation: Keep browser news disabled unless needed, use a virtual environment with pinned dependencies, and review allowed network domains before deployment.

Risk: Generated investment recommendations may be incomplete, stale, or misleading.

Mitigation: Treat outputs as informational research only, verify data against official filings or trusted market sources, and consult a qualified professional before making investment decisions.

Risk: Security disclosures in the artifact may not fully match saved-data, HTTP-traffic, and browser-subprocess behavior reported by server scanning.

Mitigation: Use evidence.security as the authoritative risk source during review and update public disclosures before broad release.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/zhangboheng/skills/boheng-investment-workflow)
- [Author Website](https://www.luckydesigner.space)
- [AKShare Official Documentation](https://akshare.akfamily.xyz/)
- [AKShare GitHub](https://github.com/akfamily/akshare)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown and plain-text reports with shell command examples and structured analysis summaries]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Analysis scripts can write reports under ~/.openclaw/workspace/investment/reports/.]

## Skill Version(s):

1.5.5 (source: server release evidence, frontmatter, and changelog released 2026-05-19)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

requirements.txt

requests>=2.28.0
beautifulsoup4>=4.11.0
lxml>=4.9.0
duckduckgo-search>=7.0

Github ReposUpdated 12h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.