Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_student_skillsA
列出所有支持的高校学生申报书与申请材料赛道(共 35 个)。

参数:
  category: 可选分类过滤。支持:
    - 'research': 科研立项 / 大创(创新训练、创业训练、创业实践等)
    - 'competition': 学科竞赛(挑战杯、互联网+、红旅赛道等)
    - 'scholarship': 奖学金(国家奖学金、国家励志、校级、企业专项等)
    - 'honor': 荣誉评优(优秀毕业生、三好学生、优秀学生干部等)
    - 'political': 政治身份(入团申请、思想汇报、转正申请等)
    - 'practice': 实践活动(三下乡社会调查、支教、科技服务、西部计划等)
    - 'study_abroad': 公派留学 / 国际交流
    - 'military': 应征入伍
    - 'other': 转专业等
route_student_skillB
根据学生的意图或诉求描述(如“我想写一个计算机视觉的大创”、“准备申请国家奖学金”),
智能匹配并推荐最合适的前 N 个申报材料赛道。

参数:
  query: 用户的自然语言诉求或关键词
  top_n: 返回推荐赛道的数量(默认 3)
get_skill_infoA
获取指定申报材料赛道的详细元数据与配置。

参数:
  skill_name: 赛道名称或标识(如 'innovation-research', 'national-scholarship', 'challenge-cup')
get_skill_requirementsA
获取指定赛道的信息采集清单(必填项、字段规范、评分避坑要点)。
Agent 在为用户撰写申报书前,应调用此工具获取必须向用户询问的关键信息清单。

参数:
  skill_name: 赛道名称(如 'innovation-research', 'national-scholarship')
list_school_templatesA

列出当前内置支持的高校特定排版样式模板。 支持清华、北大、浙大、武大等高校的标准页边距、字号和红头格式。

generate_student_docA
根据采集到的结构化申报数据,自动执行本地渲染脚本,生成一份标准规范的 Word (.docx) 文档。

参数:
  skill_name: 赛道名称(如 'innovation-research', 'challenge-cup' 等)
  data: 申报书数据字典(若 demo=True 则此项可为空)
  output_path: 生成的目标 .docx 绝对路径(可选;默认自动生成在 outputs 或 /tmp 下)
  school: 学校版式模板(如 'tsinghua', 'pku', 'whu', 'zju', 'default')
  demo: 是否使用内置示例数据快速体验生成
simulate_student_reviewA
对学生的申报文本或申报数据执行评审模拟与打分。
输出各维度得分、总体等级、评委意见、一票否决预警、查重预检及具体改进建议。

参数:
  skill_name: 赛道名称(如 'innovation_research', 'challenge_cup' 等)
  text: 申报正文文本(可选)
  data: 申报结构化数据字典(可选)

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a distinct role: listing templates, listing tracks, routing a query, fetching metadata, fetching data-collection requirements, generating a document, and simulating review. The only near-overlap is get_skill_info vs get_skill_requirements, but the descriptions clearly separate metadata/config from required-field checklists.

Naming Consistency5/5

All seven tools follow a consistent snake_case verb_noun pattern (list_*, route_*, get_*, generate_*, simulate_*). The naming is predictable and readable throughout.

Tool Count5/5

Seven tools is well-scoped for the domain: discovery, routing, requirements gathering, generation, and review are each covered by one or two tools. No tool feels redundant or missing at this count.

Completeness4/5

The set covers the core lifecycle from finding a track and gathering requirements to generating a .docx and simulating review. Minor gaps remain around explicitly editing/updating an already generated document or inspecting existing outputs, but agents can work around this by regenerating after review.

Maintenance

ActivityActive
ResponsivenessSyncing