← Back to Skills Marketplace
shawn92

Skills of A-share announcement data released by ft.tech.

by Shawn92 · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
475
Downloads
48
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install ftshare-announcement-data
Description
A 股公告与研报数据技能集。覆盖指定日期全市场公告/研报、单只股票公告/研报历史、通过 url_hash 下载公告/研报 PDF(market.ft.tech)。用户询问某天公告列表、某只股票公告或研报、下载公告/研报时使用。
README (SKILL.md)

FT A-share 公告与研报数据 Skills

本 skill 是 FTShare-ashare-announcement-data统一路由入口

根据用户问题,从下方「能力总览」匹配对应子 skill,然后通过 run.py 执行并解析响应。

所有接口均以 https://market.ft.tech 为基础域名,使用 HTTP GET。


调用方式(唯一规则)

run.py 与本文件(SKILL.md)位于同一目录。执行时:

  1. 取本文件的绝对路径,将末尾 /SKILL.md 替换为 /run.py,得到 \x3CRUN_PY>
  2. 调用:python \x3CRUN_PY> \x3C子skill名> [参数...]
# 示例(\x3CRUN_PY> 为实际绝对路径)
python \x3CRUN_PY> stock-announcements-all-stocks-specific-date --start-date 20241231 --page 1 --page-size 20
python \x3CRUN_PY> stock-announcements-single-stock-all-periods --stock-code 000001.SZ --page 1 --page-size 20
python \x3CRUN_PY> stock-announcements-specific-url-hash --url-hash \x3Chash> --output announcement.pdf
python \x3CRUN_PY> stock-reports-all-stocks-specific-date --start-date 20241231 --page 1 --page-size 20
python \x3CRUN_PY> stock-reports-single-stock-all-periods --stock-code 000001.SZ --page 1 --page-size 20
python \x3CRUN_PY> stock-reports-specific-url-hash --url-hash \x3Chash> --output report.pdf

run.py 内部通过 __file__ 自定位,无论安装在何处都能正确找到各子 skill 的脚本。


能力总览

1. 公告

  • stock-announcements-all-stocks-specific-date:指定日期全市场股票公告列表(分页)。必填参数:--start-date(YYYYMMDD);可选 --page--page-size

  • stock-announcements-single-stock-all-periods:单只股票公告历史(分页)。必填参数:--stock-code(带市场后缀,如 000001.SZ);可选 --page--page-size

  • stock-announcements-specific-url-hash:通过 url_hash 查询/下载单条公告 PDF。必填参数:--url-hash;可选 --output(保存文件名)。

2. 研报

  • stock-reports-all-stocks-specific-date:指定日期全市场股票研报列表(分页)。必填参数:--start-date(YYYYMMDD);可选 --page--page-size

  • stock-reports-single-stock-all-periods:单只股票研报历史(分页)。必填参数:--stock-code(带市场后缀);可选 --page--page-size

  • stock-reports-specific-url-hash:通过 url_hash 查询/下载单条研报 PDF。必填参数:--url-hash;可选 --output(保存文件名)。


使用流程

  1. 记录本文件绝对路径,将 /SKILL.md 替换为 /run.py 得到 \x3CRUN_PY>
  2. 理解用户意图,从「能力总览」匹配对应子 skill 名称。
  3. (可选)读取 \x3CRUN_PY> 同级目录 sub-skills/\x3C子skill名>/SKILL.md 了解接口详情与参数。
  4. 执行python \x3CRUN_PY> \x3C子skill名> [参数...],获取 JSON 输出。
  5. 解析并输出:以表格或要点形式展示给用户。

子 skill 与用户问法示例

用户问法示例 子 skill 名
「今天/某天的公告列表」 stock-announcements-all-stocks-specific-date
「指定日期全市场公告」 stock-announcements-all-stocks-specific-date
「某只股票的历史公告」 stock-announcements-single-stock-all-periods
「下载某条公告 PDF」 stock-announcements-specific-url-hash
「今天/某天的研报列表」 stock-reports-all-stocks-specific-date
「指定日期全市场研报」 stock-reports-all-stocks-specific-date
「某只股票的历史研报」 stock-reports-single-stock-all-periods
「下载某条研报 PDF」 stock-reports-specific-url-hash
Usage Guidance
This skill appears to do exactly what it claims: query market.ft.tech endpoints and optionally save PDFs. Before installing, confirm you trust the source (market.ft.tech) and are comfortable the agent may write downloaded PDFs into the skill directory (handlers enforce a same-directory restriction). If you want extra safety, run the skill in an isolated environment or container and review the included scripts; there are no hidden network endpoints, required credentials, or remote install steps.
Capability Analysis
Type: OpenClaw Skill Name: ftshare-announcement-data Version: 1.0.1 The skill bundle provides a structured interface for retrieving A-share stock market announcements and research reports from the domain market.ft.tech. The implementation uses standard Python libraries (urllib, subprocess) and includes proactive security measures, such as the _safe_output_path function in handler.py scripts, which effectively prevents directory traversal attacks when downloading PDF files. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the code and runtime behavior: every handler issues HTTP GETs to https://market.ft.tech endpoints described in the SKILL.md and returns JSON or writes PDFs. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
Runtime instructions are narrow and map to the included handlers. Handlers perform only HTTP GETs to the declared BASE_URL and output JSON or save PDF files. Note: PDF downloads are written to disk (see persistence); handlers may print HTTP error bodies to stderr. They do not read other system files or environment variables.
Install Mechanism
No install specification; code is included and run in-place via run.py. No remote downloads or package installs are performed by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. The handlers only use network access to the single BASE_URL and command-line args; requested privileges are minimal and proportionate.
Persistence & Privilege
always is false and the skill is user-invocable. It writes downloaded PDFs to disk inside the current working directory (handlers restrict output to be under the base directory). Be aware run.py launches handlers with cwd set to the skill root, so saved files will be placed under the skill directory unless you run it differently.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ftshare-announcement-data
  3. After installation, invoke the skill by name or use /ftshare-announcement-data
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
v1.0.1 修复公告下载的路径遍历漏洞
v1.0.0
FTShare-announcements-data 1.0.0 – 初始发布 - 提供 A 股公告、研报历史与实时查询及下载工具,数据来源公开渠道。 - 支持按日期或股票代码查询公告/研报、分页浏览、下载 PDF。 - 统一入口脚本自动路由至对应子 skill,便于扩展与调用。 - 详细用法与问句示例,适配多种查询场景。
Metadata
Slug ftshare-announcement-data
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Skills of A-share announcement data released by ft.tech.?

A 股公告与研报数据技能集。覆盖指定日期全市场公告/研报、单只股票公告/研报历史、通过 url_hash 下载公告/研报 PDF(market.ft.tech)。用户询问某天公告列表、某只股票公告或研报、下载公告/研报时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 475 downloads so far.

How do I install Skills of A-share announcement data released by ft.tech.?

Run "/install ftshare-announcement-data" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Skills of A-share announcement data released by ft.tech. free?

Yes, Skills of A-share announcement data released by ft.tech. is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Skills of A-share announcement data released by ft.tech. support?

Skills of A-share announcement data released by ft.tech. is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Skills of A-share announcement data released by ft.tech.?

It is built and maintained by Shawn92 (@shawn92); the current version is v1.0.1.

💬 Comments