← Back to Skills Marketplace
jhl-det

Tencent Yuanbao Gaokao - Regional Passing Scores

by jhl-Det · GitHub ↗ · v0.1.2 · MIT-0
cross-platform ✓ Security Clean
68
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install province-score-line
Description
An information retrieval assistant for GaoKao regional score lines, designed to help candidates query admission cut-off scores, admission batches, and corres...
README (SKILL.md)

核心原则

根据用户的问题,依次提取以下四类信息: 地区(place)、年份(year)、选科(student)、录取批次(luqupici)


Step 1:提取地区(place)

读取 ./ref/place.json 中的地区列表,将用户 query 中提及的地区与列表进行匹配。

匹配规则:

  • 支持别称/简称(如"魔都"→ 上海、"首都"→ 北京、"闽南"→ 福建、"桂"→ 广西)
  • 支持容错匹配(如存在错别字或非标准表述,尽量推断正确地区)
  • 支持城市到省份的映射(如"福州"->"福建")
  • 如果用户提及了多个地区,则每个年份单独生成一个 dict,不得将多个年份合并到同一个 dict 中
  • 如果用户想查询所有省份(如"各省"、"各地区"),则返回 "place" : "全省"
  • 以列表中的标准名称作为最终输出值

若无法从 用户query 中识别地区,则询问用户:"您想查询哪个省份的信息呢?"。


Step 2:提取年份(year)

  • 若用户明确提及年份(具体的数字),直接提取年份
  • 若用户提及的是模糊的年份,诸如今年、去年、近三年的说法,今年指2026,去年指2025。
  • 若用户未提及年份,则不返回 "year" 字段
  • 年份必须是四位数字,如 "25年"->"2025"

Step 3:提取选科(student)

读取 ./ref/student.json 中的选科列表,将用户 query 中提及的选科与列表进行匹配。

核心难点:新老高考政策差异 中国各省份在不同年份实行的高考政策不同(分为:传统文理科、3+3新高考、3+1+2新高考),选科名称会随之变化。你必须结合 Step 1 的【地区】和 Step 2 的【年份】进行动态匹配与转换。

下表列出各省份切换新高考的年份,切换年份之前为传统文理科模式

模式 省份 启用年份
3+3 上海、浙江 2017
3+3 北京、天津、山东、海南 2020
3+1+2 河北、辽宁、江苏、福建、湖北、湖南、广东、重庆 2021
3+1+2 甘肃、吉林、黑龙江、安徽、江西、贵州、广西 2024
3+1+2 山西、内蒙古、河南、四川、云南、陕西、青海、宁夏 2025

内蒙古蒙授生(蒙授文科/蒙授理科)不受以上规则约束,始终保持独立分类。

匹配与自动纠错规则:

  1. 传统高考模式
    • 标准选科为:文科 理科
    • 映射:用户提及"文史类"→ 文科;"理工类"→ 理科
  2. 3+3 新高考模式
    • 标准选科为:综合(不分文理)
    • 纠错:若用户提及"文科/理科/物理/历史",自动映射为:综合
  3. 3+1+2 新高考模式
    • 标准选科为:物理 历史
    • 纠错:若用户提及"理科/理工",自动映射为:物理;提及"文科/文史",自动映射为:历史

若用户未提及选科,则不返回 "student" 字段


Step 4:提取录取批次(luqupici)

读取./ref/luqupici_summary.json中的录取批次列表 然后,将用户 query 中提及的批次与列表进行匹配。

匹配规则:

  • 支持别称/简称
  • 支持容错匹配(如存在错别字或非标准表述,尽量推断正确批次)
  • 如果用户提及了多个批次,则每个批次之间使用空格隔开,如"普通类_本科 普通类_专科"
  • 如果用户未提及批次,则不返回 "luqupici" 字段
  • 如果用户只提及了本科或者专科,但是没有具体到类别,则需要都返回。如"本科" -> "普通类_本科 艺术类_本科 专项计划_本科 预科/民族_本科 体育类_本科 军队类_本科"

Step 5:调用脚本查询数据(db_info)

确认地区、年份、选科和录取批次后,调用以下脚本获取真实数据: 若未提取到任何信息,也需要调用脚本获取数据。 脚本路径: ./fetch_data.py 调用方式:

python3 ./fetch_data.py --place {place...} --year {year...} --student {student...} --luqupici {luqupici...}

Step 6:根据脚本查询到数据判断是否符合考生的意图

  • 根据“录取批次”信息,保留符合用户意图的数据。

Step 7:总结

结合上述内容,对用户的问题进行回答。 注意需要简明扼要。

Usage Guidance
This skill is reasonable for querying Gaokao regional score lines. Before installing, be aware that it may run its included Python helper and contact Tencent’s Gaokao data endpoint with the province/year/track filters you provide.
Capability Analysis
Type: OpenClaw Skill Name: province-score-line Version: 0.1.2 The skill bundle is a legitimate GaoKao (Chinese National College Entrance Examination) score retrieval assistant. It provides structured instructions for an AI agent to extract query parameters and execute a local Python script (fetch_data.py) that fetches data from a reputable domain (gaokao.search.qq.com). No evidence of malicious intent, data exfiltration, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The stated purpose, SKILL.md workflow, reference JSON files, and fetch_data.py helper all align with retrieving regional Gaokao admission score-line data; no data mutation, credential use, or destructive behavior is evidenced.
Instruction Scope
SKILL.md says “若未提取到任何信息,也需要调用脚本获取数据” and shows “python3 ./fetch_data.py ...”, so the agent may run the helper even with broad or empty filters. This is purpose-aligned for information retrieval but users should know a local helper may be invoked.
Install Mechanism
Metadata shows “Source: unknown” and “Homepage: none”. There is no install spec or package installation, so there is no evidenced install-time execution, but the publisher/source provenance is limited.
Credentials
fetch_data.py hardcodes “https://gaokao.search.qq.com/skills_data” and appends place/year/student parameters, which is proportionate for this lookup skill but means query filters are sent to an external provider.
Persistence & Privilege
The artifacts declare no credentials, required environment variables, config paths, privileged binaries, persistence, background workers, or account-level authority.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install province-score-line
  3. After installation, invoke the skill by name or use /province-score-line
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- English translation of name and description in SKILL.md - No logic or functional changes - Improved accessibility for non-Chinese speakers by providing an English summary of the skill’s purpose
v0.1.1
Initial release — provides high school entrance exam scoreline query tools: - Added core matching logic for extracting province, year, subject selection, and admission batch from user queries. - Included robust error tolerance and mapping for province aliases, city-to-province conversions, and batch name variations. - Implemented dynamic subject mapping based on different provincial gaokao policy changes over the years. - Provided external script integration (`fetch_data.py`) to support real-time scoreline and ranking data lookup. - Added comprehensive data references for provinces, years, subjects, batches, ranks, and other relevant fields.
v0.1.0
- Initial release of province-score-line, a Gaokao score line search assistant. - Supports extracting province, year, subject track, and admission batch from user queries. - Implements region alias matching and error correction, with mapping from city to province. - Dynamically matches subject track according to each province’s high school exam reform timeline. - Handles batch extraction with multiple selection and fallback to all related batches if query is broad. - Automatically queries database via fetch_data.py and summarizes results concisely for the user.
Metadata
Slug province-score-line
Version 0.1.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Tencent Yuanbao Gaokao - Regional Passing Scores?

An information retrieval assistant for GaoKao regional score lines, designed to help candidates query admission cut-off scores, admission batches, and corres... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.

How do I install Tencent Yuanbao Gaokao - Regional Passing Scores?

Run "/install province-score-line" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Tencent Yuanbao Gaokao - Regional Passing Scores free?

Yes, Tencent Yuanbao Gaokao - Regional Passing Scores is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Tencent Yuanbao Gaokao - Regional Passing Scores support?

Tencent Yuanbao Gaokao - Regional Passing Scores is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Tencent Yuanbao Gaokao - Regional Passing Scores?

It is built and maintained by jhl-Det (@jhl-det); the current version is v0.1.2.

💬 Comments