Gendangzou-skill
A skill for analysing sectors of the Chinese A-share market: policy, media, money flows, companies and ETFs with sources and dates
- 309 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The skill calls a third-party API over HTTPS and asks for a token after an `AUTH_REQUIRED` reply.
- Conclusions concern investing, but the skill creates no orders or trades.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/gendangzou-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill calls a third-party API over HTTPS and asks for a token after an `AUTH_REQUIRED` reply.
- Conclusions concern investing, but the skill creates no orders or trades.
This is third-party code. Review the repository files before installing.
What it does
The skill turns the "跟党走" (Gendangzou) service data on the Chinese A-share market into natural-language queries. It separates the materials stream, which refreshes every five minutes, from daily snapshots that can be reproduced. Every conclusion keeps its source, date, stable ID and evidence chain. Seven standalone apps sit inside: a real-time materials radar, daily and weekly sector reports, sector dynamics and links, company mapping audit, ETF-to-sector mapping and a breakdown of CCTV news broadcasts. Conclusions are always made at sector level. Companies and ETFs serve as grounds for a mapping, and the skill gives no stock recommendations or return forecasts.
Who it is for. Analysts and private investors who study Chinese market sectors and want to see the source of every conclusion.
Good fit when
- You want to see which policy materials formed a sector signal over six hours.
- The robotics sector is compared over seven days by policy, market attention and money flows.
- Each ground for assigning a company to a sector is checked.
- A weekly review of policy and sector anomalies is assembled with one request.
Not a fit when
- You need stock picks, entry points and a return forecast, which the skill does not provide by the project rules.
- Data from other markets is needed, while only A-shares and Chinese ETFs are covered.
- HTTPS access to `api.mobiusquant.ai` is not possible.
Example request
Analyse changes in the integrated circuits sector over the last seven days by three signals: policy, market attention and money flows.Limitations
The skill works through the MobiusQuant API: anonymous by default, and after an `AUTH_REQUIRED` reply a token is needed, saved with `python3 scripts/gendangzou.py api auth set`. Python 3.10 or newer is required. Documentation and materials are in Chinese. There are no stock recommendations and the author disclaims responsibility for user losses, so investment decisions stay with you. Data comes from an external service whose availability the skill does not control.
How to disable. Ask the agent to remove the skill or delete its folder from the agent skills directory. The built-in apps can be disabled and removed one by one.
FAQ
How do I install the skill?
Ask the agent: "Install https://github.com/MobiusQuant/Gendangzou-skill". The agent installs it the native way, and you verify with `python3 scripts/gendangzou.py apps doctor` in the skill directory: the reply should contain `ok: true`.
Is a token required?
No, access is anonymous by default. A token is needed only after an `AUTH_REQUIRED` reply and is requested on the mobiusquant.ai site.
Does the skill give stock recommendations?
No. Conclusions are built per sector, cite sources and contain no entry or exit points and no return forecasts.
Which agents does the skill work with?
Claude Code, Codex, OpenClaw, Hermes and WorkBuddy: the package is shared and the agent registers it by its own rules.
Which apps are in the package?
The materials radar, daily and weekly reports, sector dynamics, company mapping audit, ETF-to-sector mapping and CCTV news breakdowns. Each app is enabled and disabled separately.
Discussion
No questions or reviews yet.
Related
SkillsA skill with Chinese A-share market data: quotes, research reports, financials, news and 11 more categories from 34 sources, no keys
Four skills for China's A-share market: quotes and indicators, trend-pullback signals, a simulated account and backtests
A skill that queries Arkvol for China, Hong Kong and US market data and retells it with the date, indicators and limits of use
A skill that writes a nine-chapter report on a US, Hong Kong or China stock: reverse DCF, EPV, earnings-quality review and scripted valuation
A skill that finds bottlenecks in an industry's supply chain and shortlists A-share, Hong Kong and US stocks with data checks
Zhengxi Views fund manager skill
基金经理·郑希观点库 Skill
An agent skill with a traceable base of fund manager Zheng Xi's public views: answers with source quotes, his method, and real fund data
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Gendangzou-skill (this card) | no | 309 | |
| a-share-skill | no | 258 | serves quotes, indicators and backtests for Chinese stocks; this skill analyses sectors through policy, media and money with a source for every conclusion |
| Tushare Skill | yes | 460 | serves Tushare Pro quotes, financials and macro data; this one centers on policy-to-sector links with an evidence chain |
README in short
The repository packages the "跟党走" service capabilities as a skill with an API SDK and an app catalog. The agent first learns the list of enabled apps, then loads the description of only the one matching the request.
README badge
Original SKILL.md
--- name: gendangzou-skill description: 查询和解读“跟党走”A股板块 API，并按需调用已安装的板块研究应用。用户询问政策或权威媒体关联板块、实时材料、历史快照、板块趋势、公司与ETF映射依据、板块日报周报或公开新闻节目对应板块时使用；不用于个股或ETF推荐和买卖建议。 --- # 跟党走 A 股板块研究 本 Skill 由平台、API SDK 和可独立安装的应用组成。需要 Python 3.10 或更高版本， 并允许 HTTPS 访问 `api.mobiusquant.ai`。 执行下列相对路径命令时，以本 `SKILL.md` 所在目录作为工作目录。 ## 核心边界 - 结论始终落在板块。公司和 ETF 仅作为映射、暴露或内部确认依据。 - 分开解释政策、权威媒体、市场关注和资金确认，不把同期信号写成确定因果。 - 区分五分钟发现的实时流与每日发布的可复现快照。 - 历史或跨接口比较固定并复用 `snapshot_id`。 - 实质判断保留日期、稳定 ID、材料标题、来源和链接。 - 不输出个股或 ETF 推荐、买卖点、收益预测。 ## 渐进式路由 先运行以下命令取得当前已启用应用，不要假设某个应用一定存在： ```bash python3 scripts/gendangzou.py apps list --format agent ``` 若一个应用的意图与请求匹配，只执行列表给出的说明加载命令，再通过统一入口运行： ```bash python3 scripts/gendangzou.py apps run APP_ID -- [APP_ARGUMENTS] ``` 不要预读其他应用。应用不存在、已禁用或不匹配时，使用通用 API 流程，不自行复刻 应用工作流。只有用户明确要求管理应用时，才读取 `platform_core/references/app-packages.md`；不得自动安装、卸载或启用应用。 ## 通用 API 没有匹配应用，或应用需要补充单项证据时，读取 [`api_sdk/references/api.md`](api_sdk/references/api.md)： 1. 定位稳定能力 ID。 2. 参数不确定时运行 `capabilities show`，以在线契约为准。 3. 比较任务复用首次响应的 `snapshot_id`。 4. 需要解释结论时再调用证据能力，不按名称或关键词补造依据。 5. 输出遵循 [`api_sdk/references/output-contracts.md`](api_sdk/references/output-contracts.md)； 业务边界不明确时再读取