Skip to content
Agentmart
Submit a tool

alphapai-research

Alpha派金融投研平台API技能,用于调用Alpha派(AlphaPai/PaiPai)的投资研究接口。覆盖五大核心能力:投研知识问答、投研数据检索、投资研究Agent(公司一页纸/业绩点评/调研大纲/主题选股/投资逻辑/可比公司/观点Challenge/行业一页纸/个股选基/主题选基/画图)、股票公告列表查询、投…

Skill by LeoYeAI

IndexedMIT★ 2,168
Write a review

Chalk Labs

Need help deploying alphapai-research?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/leoyeai-alphapai-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Alpha派金融投研平台API技能,用于调用Alpha派(AlphaPai/PaiPai)的投资研究接口。覆盖五大核心能力:投研知识问答、投研数据检索、投资研究Agent(公司一页纸/业绩点评/调研大纲/主题选股/投资逻辑/可比公司/观点Challenge/行业一页纸/个股选基/主题选基/画图)、股票公告列表查询、投研图表搜索。当用户提到AlphaPai、Alpha派、PaiPai、投研问答、召回数据、公司一页纸、行业一页纸、业绩点评、调研大纲、投资逻辑、可比公司、选基、搜图表等关键词时,务必使用本skill。

Use cases: backend, research, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/alphapai-research

What's inside

Skill name
alphapai-research
Description
Alpha派金融投研平台API技能,用于调用Alpha派(AlphaPai/PaiPai)的投资研究接口。覆盖五大核心能力:投研知识问答、投研数据检索、投资研究Agent(公司一页纸/业绩点评/调研大纲/主题选股/投资逻辑/可比公司/观点Challenge/行业一页纸/个股选基/主题选基/画图)、股票公告列表查询、投研图表搜索。当用户提到AlphaPai、Alpha派、PaiPai、投研问答、召回数据、公司一页纸、行业一页纸、业绩点评、调研大纲、投资逻辑、可比公司、选基、搜图表等关键词时,务必使用本skill。
License
MIT
Metadata
version: 1
Instructions
385 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • _meta.json
  • config.json
  • api_reference.md · references/
  • alphapai_client.py · scripts/

SKILL.md (first lines)

# AlphaPai Research Skill

基于Alpha派(AlphaPai)Open API 的投研能力技能。所有 API 调用均通过 `scripts/alphapai_client.py` 的 CLI 完成,无需手动编写请求代码。

## 输出原则

Alpha派各接口的返回内容均由专业投研模型生成,质量高、格式完整,**调用完成后应将原始输出直接呈现给用户,不做二次加工**:

- **禁止总结或压缩**:不得将原文缩写为摘要,不得用自己的语言改写
- **禁止截断**:无论内容多长,必须完整输出,不得以"以上为主要内容"等方式省略
- **保留原始格式**:Markdown 标题层级、加粗、列表、表格、引用块等结构一律原样保留
- **引用来源随正文输出**:若接口返回了参考来源(文档标题、日期、评分等),紧随正文完整呈现

> 若用户明确要求"总结"或"提炼",则在完整输出原文之后,再额外附上总结,而非替代原文。

## 数据背景

Alpha派是讯兔科技开发的金融投研 AI 应用,具有丰富的投研场景数据。不同数据源对应不同质量与特征,对专业用户的判断至关重要:

- **路演纪要**:A股上市公司业绩会、券商路演、专家交流等一线会议内容
- **券商点评**:分析师每日给机构投资者发送的点评(时效性高,质量参差不齐)
- **微信公众号**:投研相关公众号及上市公司官方公众号内容
- **券商研报**:国内外券商分析师撰写的研究报告
- **公司公告**:上市公司在交易所发布的官方公告(最权威口径)
- **图表与数据**:公告/研报图片、表格,及EDB宏观/行业/个股时序数据

## 首次使用:配置 API Key

```bash
python scripts/alphapai_client.py config --set-key YOUR_API_KEY
# 非默认服务地址时追加:--set-url https://your-host
```

查看当前配置:

```bash
python scripts/alphapai_client.py config --show
```

> 如用户未提供 api_key,向其说明:可在 Alpha 派💻电脑端获取,或联系客户经理。不要在对话中回显完整 api_key。

## 接口一:投研知识问答

向 Alpha派的投研助手 PaiPai 提问,获取答案。按照**输出原则**完整呈现回答正文与引用来源,不做二次总结。

```bash
python scripts/alphapai_client.py qa --question "问题内容" [选项]
```

| 选项                      | 说明                                                                                            |
| ------------------------- | ----------------------------------------------------------------------------------------------- |
| `--question` / `-q`       | 问题内容(必填)                                                                                |
| `--mode Flash\|Think`     | 问答模式(默认 `Flash`):`Flash`=简单搜索问答,一问一搜一答;`Think`=Wide Search,一问多搜一答 |
| `--context MSG [MSG ...]` | 多轮对话历史,按顺序传入                                                                        |
| `--web-search`            | 开启联网搜索                                                                                    |
| `--deep-reasoning`        | 开启深度推理                                                                                    |
| `--start YYYY-MM-DD`      | 数据筛选开始日期                                                                                |
| `--end YYYY-MM-DD`        | 数据筛选结束日期                                                                                |
| `--json`                  | 输出原始JSON(供程序解析)                                                                      |

**示例:**

```bash
# 基础问答(Flash 模式,默认)
python scripts/alphapai_client.py qa --question "贵州茅台2024年经营情况如何?"

# Think 模式(Wide Search,更广泛检索)
python scripts/alphapai_client.py qa --question "贵州茅台2024年经营情况如何?" --mode Think

# 多轮对话
python scripts/alphapai_client.py qa \
  --question "对行业的影响呢?" \
  --context "云南缺电对哪些公司会造成影响?" "影响主要集中在高耗能行业"

# 联网搜索 + 时间范围
python scripts/alphapai_client.py qa \
  --question "近期新能源车销量趋势" \
  --web-search --start 2025-01-01 --end 2025-03-01
```

## 接口二:投研知识检索(基于RAG技术)

获取会被送入大模型的原始底层原始数据,适合自行加工或构建自定义 RAG 流程。

```bash
python scripts/alphapai_client.py recall --query "查询问题" [选项]
```

| 选项                 | 说明                                                   |
| -------------------- | ------------------------------------------------------ |
| `--query` / `-q`     | 查询问题(必填)                                       |
| `--type TYPES`       | 数据类型,逗号分隔(不传则全类型)                     |
| `--no-cutoff`        | 返回截断前完整内容(默认截断,与送入大模型的数据一致) |
| `--start YYYY-MM-DD` | 数据筛选开始日期                                       |
| `--end YYYY-MM-DD`   | 数据筛选结束日期                                       |
| `--json`             | 输出原始JSON(供程序解析)                             |

**示例:**

```bash
# 检索和召回点评和Q&A类型数据
python scripts/alphapai_client.py recall \
  --query "贵州茅台2024年市值" \
  --type comment,qa \
  --start 2025-01-01 --end 2025-03-20

# 检索和召回全类型完整内容
python scripts/alphapai_client.py recall --query "宁德时代电池技术" --no-cutoff
```

### recallType 枚举值

选择 `--type` 参数时,根据用户意图选择合适的数据类型:

| 类型值                  | 含义                 | 特点                                     |
| ----------------------- | -------------------- | ---------------------------------------- |
| `comment`               | 券商点评             | 时效性最强,分析师每日发送,质量参差不齐 |
| `roadShow`              | 路演会议纪要         | 业绩会、券商路演、专家交流,一线投研内容 |
| `roadShow_ir`           | 上市公司官方路演纪要 | 官方披露,量少                           |

From LeoYeAI/openclaw-master-skills, MIT.

More from LeoYeAI/openclaw-master-skills

Signals

Stars
2,168
Forks
325
Open issues
13
Last commit (this folder)
Jun 8, 2026 (5 months ago)
Last release
Jul 20, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1
License
MIT
Website
myclaw.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from LeoYeAI

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get alphapai-research running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying alphapai-research?

CallGet help
Cite this page

alphapai-research skill. Agent Mart. https://agentmart.dev/skills/leoyeai-alphapai-research (last updated 2026-10-24)