Kaoyan Navigator

调研中国硕士研究生考试(考研)目标院校与专业的历年招生数据,评估择校爆冷/爆热、缩招、推免挤压、复试线虚低、专业课变更和复试风险,并给出冲稳保建议。适用于用户询问考研择校、院校难度、报录比、复试线、招生计划、统考名额、推免比例、拟录取分数、某校会不会爆、目标分数或需要导入自有 CSV/JSON 数据时。应先搜索公开网络和官方来源,确实找不到关键数据后再向用户索取补充材料;支持 Codex、Claude Code 和其他能读取 Skill Markdown 的 agent。

38 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mcxiaoxiao/kaoyan-navigator-skill --skill kaoyan-navigator
Manual install
git clone --depth 1 https://github.com/mcxiaoxiao/kaoyan-navigator-skill.git /tmp/kaoyan-navigator-skill
mkdir -p ~/.claude/skills
cp -r /tmp/kaoyan-navigator-skill/. ~/.claude/skills/kaoyan-navigator

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Kaoyan Navigator

把择校判断当作有证据约束的导航研究,不承诺预测结果。

## 开始前

1. 确认入学年份、院校、学院、专业名称与代码、全日制/非全、学硕/专硕。
2. 用户未给全时,先用已有信息搜索;只有歧义会显著改变结果时才追问。
3. 令入学年份为 `Y`。优先分析 `Y-3` 至 `Y-1` 的完整周期;未结束年份只能标为暂定数据。
4. 涉及实时政策和最新招生信息时必须联网核实,并在结论中写明检索日期。

## 工具策略

- 优先使用当前环境已有的浏览器、搜索、抓取、PDF、表格和代码执行工具。
- Codex 中可使用 Web/Browser/Chrome 搜索,使用 shell、Python 或 spreadsheet 工具整理数据。
- 不假定某个专有工具一定存在;按能力选择替代工具。
- 遇到 PDF 表格、扫描版拟录取名单或网页动态表格时,先尝试解析/OCR,再请求用户上传。

## 研究工作流

### 1. 建立研究对象

规范化为:

`学校 / 学院 / 专业代码 / 专业名称 / 方向 / 培养方式 / 入学年份`

同名专业若属于不同学院或代码,不得混用。

### 2. 多路检索

并行扮演以下角色;工具不支持并行时顺序执行:

- **政策研究员**:招生简章、专业目录、考试科目、复试细则。
- **供给研究员**:招生计划、推免拟录取、统考名额、扩缩招。
- **分数研究员**:国家线、院线、复试线、拟录取最低/中位/平均分。
- **竞争研究员**:报考数、上线数、复录比、调剂与一志愿情况。
- **热度研究员**:搜索趋势、社媒推荐、机构内容;只作弱证据。
- **审计员**:核对年份、口径、冲突来源和缺失值,主动寻找反证。

搜索顺序、来源等级和查询模板见 [references/research-playbook.md](references/research-playbook.md)。
当用户还没有结构化历年数据时,先看 [references/data-acquisition-flow.md](references/data-acquisition-flow.md),并优先运行 `scripts/research_plan.py` 生成查询计划和缺失字段清单。

### 3. 先搜后问

对每个缺失字段至少尝试:

1. 学校研究生院、招生网、学院官网;
2. 政府/研招网或学校公开 PDF;
3. 可靠聚合页、新闻稿、缓存或搜索摘要;
4. 通过拟录取名单自行计算统计量。

仍缺失时再向用户索取最小必要材料,明确说明缺什么、接受什么格式、会影响哪个结论。不要笼统地说“请提供更多数据”。

可接受输入:

- CSV/Excel/JSON;
- 招生目录、复试细则、拟录取名单 PDF;
- 网页链接或截图;
- 用户手工提供的逐年数字。

数据格式见 [references/data-schema.md](references/data-schema.md)。CSV/JSON 可先运行:

```bash
python scripts/validate_data.py path/to/data.csv
```

如果用户需要“先自己找、找不到再问”的执行计划,使用 `scripts/research_plan.py` 先生成:
Read the full skill on GitHub

Details

Skill name
kaoyan-navigator
License
MIT
Repo updated
7 October 2026

FAQ

What does the Kaoyan Navigator skill do?

调研中国硕士研究生考试(考研)目标院校与专业的历年招生数据,评估择校爆冷/爆热、缩招、推免挤压、复试线虚低、专业课变更和复试风险,并给出冲稳保建议。适用于用户询问考研择校、院校难度、报录比、复试线、招生计划、统考名额、推免比例、拟录取分数、某校会不会爆、目标分数或需要导入自有 CSV/JSON 数据时。应先搜索公开网络和官方来源,确实找不到关键数据后再向用户索取补充材料;支持 Codex、Claude Code 和其他能读取 Skill Markdown 的 agent。

How do I install the Kaoyan Navigator skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mcxiaoxiao/kaoyan-navigator-skill --skill kaoyan-navigator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Kaoyan Navigator popular?

It lives in mcxiaoxiao/kaoyan-navigator-skill, which has 38 GitHub stars and 3 forks.

Related skills

Agentic Command Center

30

Forgemind-git/agentic-command-center

An advisory blueprint for planning your own AI command center — one chat or voice interface that runs your whole business by routing to internal systems you own. Guidance and architecture only; it explains the four phases (own your systems, connect your tools, expose them over MCP, unify under one command layer) but never writes code or builds anything. Use when someone wants to understand how to approach internal dashboards, integrations, MCP, and a unified agentic command layer.

AI, LLMs & Agents14

AI Delivery Spec

35

franklinxkk/ai-delivery-spec

Clarify, create, review or change product, service and office workflow requirements, PRDs and interactive prototypes. Use for vague goals, process improvements, spreadsheet/form rules, small UI edits and changes to existing systems, even without the word requirement. 中文:产品、服务及办公流程的需求判断、深挖澄清、PRD、原型、变更与验收;一句话想法、表单/表格规则和微小改动也适用。明确的纯翻译、排版、抄录或既定步骤执行由对应工具直接处理。

AI, LLMs & Agents

Booking Best Price

32

aiwithremy/claude-skills-booking-best-price

Use when the user pastes a holiday-rental or hotel listing link (Airbnb, Stayz, Vrbo, Expedia, Booking.com, HomeToGo, or similar) and wants to identify the actual property, find it listed on other sites, compare prices to book it cheaper, or track down the property manager / owner contact to book direct. Requires the Firecrawl MCP server. This skill verifies Firecrawl is installed and walks the user through setup first if it is not.

AI, LLMs & Agents

LLM Council

38

shuntacurosu/llm_council_skill

Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

AI, LLMs & Agents

Claude Capability Bridge

37

Abolfazlshahi/claude-capability-bridge-skill

Use when running as a third-party or non-default model inside Claude Code, Claude desktop/web, or any Claude-compatible host and the task needs real capabilities - files and git, shell and builds, browsers and web apps, MCP connectors, artifact delivery, GUI control, delegation, or provider/gateway diagnosis. Supplies evidence-first operating procedure - identify the host from live evidence, confirm what is actually exposed and permitted before acting, route to the matching capability card, verify the requested outcome instead of trusting tool success, and report UNKNOWN honestly. Also use whe

AI, LLMs & Agents

R00 Travisvn Awesome Claude Skills Datascience

50

WireTarantulaKnife/r09-travisvn-awesome-claude-skills-datascience

🤖 Data Science & AI/ML skill suite derived from travisvn/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.