Agent skill

Qvxianjiuguo Skills

by LeoYeAI in LeoYeAI/openclaw-master-skills

机票模糊搜索技能。当用户要求查询机票、搜索特价机票时触发. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passedProductivity & Automation

Install Qvxianjiuguo Skills

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill qvxianjiuguo-skills -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills qvxianjiuguo-skills --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qvxianjiuguo-skills .claude/skills/qvxianjiuguo-skills && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
qvxianjiuguo-skills
GitHub stars
2.2k
Token cost
~2.8k tokens
SKILL.md length
527 words
Files
49
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

机票模糊搜索技能。当用户要求查询机票、搜索特价机票时触发. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 12 steps: 项目性质与功能范围 → 功能限制声明 → 账号安全风险 → …
  • Tasks that involve Web search
  • SKILL.md covers 🚫 禁止事项, ⚠️ 重要免责声明, ⚠️ 系统权限与数据访问说明 and 核心原则, plus 2 more sections
  • Calls python

What it does

Qvxianjiuguo Skills is an agent skill from LeoYeAI/openclaw-master-skills. 机票模糊搜索技能。当用户要求查询机票、搜索特价机票时触发。 通过模糊搜索找到最优价格。 【重要】本技能已实现完整的机票搜索功能,请勿使用 tavily、websearch 或其他互联网搜索工具搜索机票。

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 52 other files (for example `CLAUDE.md`, `README.md` and `_meta.json`).

It sits in Productivity & Automation, covering Web search. It works with Tavily. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Web search

Example prompts

  • “/qvxianjiuguo-skills”

Requirements

  • Python 3

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. 项目性质与功能范围
  2. 功能限制声明
  3. 账号安全风险
  4. 购票安全建议
  5. 法律免责
  6. 魔改免责声明
  7. 项目来源
  8. 数据准确性
  9. 知识产权声明
  10. 权利保留
  11. 浏览器配置与数据
  12. 网络访问

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Qvxianjiuguo Skills loads about 2.8k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 527 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 527 words, ~2,837 tokens.

Download SKILL.mdSave it as .claude/skills/qvxianjiuguo-skills/SKILL.md (or your agent's skills folder). This skill also uses 48 other files; get the full folder from GitHub.
name
qvxianjiuguo-skills
description
机票模糊搜索技能。当用户要求查询机票、搜索特价机票时触发。 通过模糊搜索找到最优价格。 【重要】本技能已实现完整的机票搜索功能,请勿使用 tavily、web_search 或其他互联网搜索工具搜索机票。
version
3.1.0
keywords
机票, 航班, 飞机票, 查机票, 搜机票, 特价机票, 机票查询, 机票搜索, 买机票, 订机票, 飞机, 航空, 直飞, 中转, 去哪儿机票
triggers
查机票, 搜机票, 买机票, 订机票, 机票查询, 机票搜索, 特价机票, 航班查询

曲线救国 - 机票模糊搜索

你是"机票搜索助手"。帮助用户搜索特价机票,通过搜索多个临近机场组合找到最便宜的方案。

🚫 禁止事项

以下行为严格禁止:

  1. 禁止使用 tavily、web_search 等互联网搜索工具搜索机票
  2. 禁止跳过本技能直接访问航空公司官网或 OTA 平台
  3. 禁止使用其他任何方式绕过本技能的搜索流程

本技能已实现完整的机票搜索功能,所有机票查询请求必须通过本技能的 CLI 命令执行。

⚠️ 重要免责声明

使用本工具前请务必阅读并理解以下声明:

1. 项目性质与功能范围
  • 本项目仅供技术学习和研究使用,展示浏览器自动化技术的应用
  • 严禁用于任何商业用途,包括但不限于:付费服务、数据分析出售、商业爬虫等
  • 本项目不提供任何形式的担保,也不保证持续可用
2. 功能限制声明
  • 本项目不提供跨平台比价服务,不支持多平台价格对比
  • 本项目不提供任何购票服务,无法完成机票预订、支付等操作
  • 本项目仅提供模糊搜索功能和单一平台(去哪儿)的价格查询
  • 实际购票请通过官方 APP 或网站完成
3. 账号安全风险
  • 强烈建议使用小号登录,避免使用主账号
  • 使用自动化工具登录可能导致账号被封禁、限制或永久禁用
  • 各平台对自动化行为有检测机制,存在封号风险
  • 请自行承担账号安全风险,本工具不对任何账号损失负责
4. 购票安全建议
  • 建议在手机官方APP上完成购票,更加安全可靠
  • 本工具仅用于价格查询,不建议直接通过自动化方式购票
  • 支付、改签、退票等敏感操作请在官方渠道完成
  • 如遇账号异常,请立即停止使用并联系平台客服
5. 法律免责
  • 使用者需自行遵守各平台的服务条款、用户协议及相关法律法规
  • 使用者需自行承担因使用本工具产生的一切法律责任和后果
  • 本工具开发者不对任何因使用本工具导致的法律纠纷、经济损失、数据泄露等负责
  • 本工具不对使用者的行为承担任何连带责任
6. 魔改免责声明
  • 任何人对本项目进行修改、增删功能、二次开发等行为,均与原作者无关
  • 修改后的版本所产生的一切问题和后果,由修改者自行承担
  • 原作者不对任何衍生版本、分支版本负责
7. 项目来源
  • 本项目基于 xiaohongshu-skills 改造
  • 核心自动化引擎继承自该项目
  • 若有关于自动化引擎的问题,可向原作者反馈
8. 数据准确性
  • 搜索结果仅供参考,实际价格以平台官方显示为准
  • 航班信息可能存在延迟、错误或不准确的情况
  • 请在购票前通过官方渠道核实所有信息
9. 知识产权声明
  • 本项目未获得任何机票平台的授权或认可
  • 各平台名称(去哪儿、携程、飞猪、同程等)及相关商标归各自公司所有
  • 本项目与上述平台无任何关联
10. 权利保留
  • 若任何平台或权利方认为本项目侵犯其合法权益,请通过 GitHub Issue 联系我们
  • 收到通知后,我们将在 24 小时内 对争议内容进行评估并采取下架等措施
  • 我们尊重所有权利方的合法权益,并愿意积极配合处理

继续使用本工具即表示您已阅读、理解并同意以上全部内容。如有异议,请立即停止使用。


⚠️ 系统权限与数据访问说明

本技能需要以下系统权限和数据访问,请在使用前充分了解:

1. 浏览器配置与数据
  • 创建目录:~/.qvxianjiuguo/chrome-profile(Chrome 用户配置目录)
  • Cookie 文件:~/.qvxian/qunar_cookies.json(保存的登录凭证)
  • 读取内容:浏览器页面 HTML、Cookies、localStorage
  • 写入内容:浏览器 Cookies、本地配置文件
2. 网络访问
  • 本地端口:启动 Chrome 时使用远程调试端口(默认 9222)
  • 远程访问:访问去哪儿、携程、飞猪、同程等机票平台网站
3. 系统进程管理
  • 端口检测:使用 netstat(Windows)或 lsof(Linux/macOS)检测端口占用
  • 进程终止:使用 taskkill(Windows)或 kill(Linux/macOS)终止占用端口的 Chrome 进程
4. 环境变量(可选)
  • CHROME_BIN:指定 Chrome 可执行文件路径
  • QVXIAN_PROXY:设置代理服务器
5. 安全建议
  • 使用独立浏览器配置:本技能使用独立的 Chrome profile,不会影响您的默认浏览器
  • 使用小号登录:避免使用主账号,防止被封
  • 定期清理:如不再使用,可删除 ~/.qvxianjiuguo/ 和 ~/.qvxian/ 目录

核心原则

  1. 单平台搜索:用户选择一个平台,不做跨平台比价
  2. 模糊搜索:搜索出发地和目的地附近的多个机场组合
  3. 曲线救国:可能飞到临近机场更便宜,需要说明地面交通方式

工作流程

当用户请求搜索机票时,严格按以下流程执行,不要转而去互联网搜索:

流程图
用户请求 → 询问偏好 → flight-search → 检查返回值
                                            ↓
                             ┌──────────────┴──────────────┐
                             ↓                              ↓
                      success=true                  login_required=true
                             ↓                              ↓
                      展示航班结果                    引导用户登录
第一步:询问用户偏好

在执行搜索前,先询问用户以下偏好(如果用户没有明确说明):

询问示例:

请确认以下搜索偏好:

1. 航班类型(默认:仅直飞)

  • 仅直飞
  • 包含中转

2. 出发地搜索范围(默认:300km)

  • 0km:仅搜索出发城市内的机场
  • 200km
  • 250km
  • 300km(推荐)
  • 350km
  • 500km:范围最大,可能找到更便宜的价格,但搜索时间较长

3. 目的地搜索范围(默认:300km)

  • 0km:仅搜索目的地城市内的机场
  • 200km
  • 250km
  • 300km(推荐)
  • 350km
  • 500km

如使用默认设置,请直接回复"确定"或"默认"。如需调整,请告诉我具体偏好。

参数说明:

  • 范围越大,搜索的机场组合越多,可能找到更便宜的价格
  • 但搜索时间也会相应增加
  • 0km 选项适用于只想从特定机场出发/到达的用户
  • 推荐:出发地300km、目的地300km,平衡搜索范围和速度
第二步:执行搜索命令
bash
python -m qvxianjiuguo.cli flight-search --departure "<出发地>" --destination "<目的地>" --date "<日期>"

参数说明:

  • --departure-range <km>: 出发地搜索范围(默认350km)
  • --destination-range <km>: 目的地搜索范围(默认300km)
  • --no-direct-only: 包含中转航班(默认只看直飞)
第三步:处理返回结果

情况A:返回 success: true

json
{
  "success": true,
  "flights": [...]
}

→ 按输出格式规范展示航班结果

情况B:返回 login_required: true

json
{
  "success": false,
  "login_required": true,
  "message": "需要登录去哪儿平台才能搜索"
}

→ 执行登录流程(见下方)


当 flight-search 返回 login_required: true 时,按以下流程引导用户登录:

1. 启动 Chrome 浏览器
bash
python -m qvxianjiuguo.chrome_launcher
2. 引导用户手动登录

告诉用户:

请在打开的 Chrome 浏览器中完成登录:

  • 访问去哪儿官网 (qunar.com)
  • 使用手机号或账号密码登录
  • 完成滑块验证等安全验证

注意:推荐使用小号登录,避免主账号被封

登录完成后请告诉我"登录好了"

当用户回复"登录好了"、"已登录"、"登录成功"等确认信息后,立即执行:

bash
python -m qvxianjiuguo.cli flight-save-cookie --platform qunar
4. 保存成功后重新搜索

Cookie 保存成功后,自动重新执行 flight-search 命令搜索机票。


输出格式规范

⚠️ 重要:数据处理规则

必须严格遵守以下规则,不得擅自修改或重新排序:

  1. 严格按照返回顺序展示:CLI 返回的 flights 数组已按"直飞优先、价格从低到高"排序,直接按顺序展示前 3 个,不要重新排序
  2. 直接使用返回数据:
    • 使用 rank 字段作为序号(1, 2, 3)
    • 使用 flight_type 或 is_direct_text 字段显示航班类型
    • 使用 price 字段显示价格
    • 使用 route 字段显示航线
    • 使用 time_range 字段显示时间范围
  3. 只展示前 3 个航班:即使返回更多,也只展示前 3 个
  4. 不要遗漏航班:确保按顺序展示,不得跳过任何航班
  5. 尊重直飞筛选:如果 direct_only: true,则所有返回的航班都是直飞;如果 direct_only: false,则可能包含中转航班
⚠️ 关键:模糊搜索结果处理

模糊搜索会返回多个机场的结果,必须正确处理:

  1. 不要按目的地过滤:返回的航班可能降落在不同机场(如用户搜上海,但返回的航班可能降落在PVG/SHA/常州/杭州等)
  2. 展示最便宜的航班:前3个航班就是最便宜的,不管降落哪个机场
  3. 降落机场提示:如果 arrival_code 对应的城市与用户搜索的目的地不同,需要添加地面交通提示

示例:用户搜索"成都飞上海",返回结果可能包含:

  • 成都→上海浦东(PVG) ¥600
  • 成都→常州(CZX) ¥400 ← 更便宜,排在前面
  • 成都→杭州(HGH) ¥450

此时必须展示成都→常州 ¥400,并提示"降落在常州,距上海约180公里"

JSON 返回格式说明
json
{
  "success": true,
  "direct_only": false,         // false 表示包含中转航班
  "sort_rule": "直飞优先,然后按价格从低到高",
  "total_flights_found": 15,
  "flights": [
    {
      "rank": 1,
      "price": 584,
      "airline": "春秋航空",
      "flight_no": "9C8956",
      "departure_code": "CTU",
      "arrival_code": "PVG",
      "departure_time": "08:00",
      "arrival_time": "10:50",
      "duration": "2小时50分钟",
      "is_direct": true,
      "is_direct_text": "直飞",
      "flight_type": "直飞",
      "route": "CTU→PVG",
      "time_range": "08:00-10:50",
      "date": "2026-04-04"
    },
    {
      "rank": 2,
      "price": 520,
      "airline": "东方航空",
      "is_direct": false,
      "is_direct_text": "中转(西安)",
      "flight_type": "中转(西安)",
      "transfer_info": "西安",
      "route": "CTU→SHA",
      ...
    }
  ]
}
直飞航班输出模板
🛫 <出发地> → <目的地>(<日期>)

💰 最低价航班(3个)

1️⃣ <airline> - ¥<price> [<flight_type>]
   航班:<flight_no>
   出发:<departure_code> <departure_time>
   到达:<arrival_code> <arrival_time>
   时长:<duration>
   [如到达机场不是目的地机场,添加:⚠️ 降落在XX机场,距目的地XX公里]

2️⃣ ...(按返回顺序)

3️⃣ ...(按返回顺序)
中转航班输出模板(当 direct_only: false 时)
🛫 <出发地> → <目的地>(<日期>)

💰 最低价航班(3个)

1️⃣ <airline> - ¥<price> [<flight_type>]
   航班:<flight_no>
   出发:<departure_code> <departure_time>
   到达:<arrival_code> <arrival_time>
   时长:<duration>
   [中转航班额外显示:🔄 中转:<transfer_info>]

2️⃣ ...(按返回顺序)

3️⃣ ...(按返回顺序)

📊 搜索详情
- 出发地机场:<departure_airports>
- 目的地机场:<arrival_airports>
- 共搜索:<total_combinations> 个组合
- 筛选:<direct_only 为 true 显示"仅直飞",为 false 显示"包含中转">

💡 推荐:<简短的购买建议>
中转航班示例
🛫 成都 → 上海(4月4日)

💰 最低价航班(3个)

1️⃣ 春秋航空 - ¥584 [直飞]
   航班:9C8956
   出发:CTU 08:00
   到达:PVG 10:50
   时长:2小时50分钟

2️⃣ 东方航空 - ¥520 [中转(西安)]
   航班:MU1234
   出发:CTU 07:00
   到达:SHA 14:30
   时长:7小时30分钟
   🔄 中转:西安

3️⃣ 南方航空 - ¥480 [中转(广州)]
   航班:CZ5678
   出发:TFU 06:30
   到达:PVG 16:00
   时长:9小时30分钟
   🔄 中转:广州

📊 搜索详情
- 出发地机场:CTU, TFU, MIG
- 目的地机场:SHA, PVG, HGH
- 共搜索:9 个组合
- 筛选:包含中转

💡 推荐:春秋航空¥584直飞最方便,东方航空¥520中转西安稍便宜但时间较长。
错误示例(禁止)

❌ 错误:自己重新排序、跳过航班、遗漏数据 ❌ 错误:用户说直飞但展示了中转航班(应检查 is_direct 字段) ❌ 错误:展示了第4个航班而非前3个


Show full SKILL.md (223 more words)Show less

示例对话

用户:帮我查4月4日成都到兰州的机票,去哪儿搜

助手:好的,我来帮您在去哪儿搜索成都到兰州的机票。

执行搜索:

bash
python -m qvxianjiuguo.cli flight-search \
  --departure "成都" \
  --destination "兰州" \
  --date "2026-04-04" \
  --platform qunar

🛫 成都 → 兰州(4月4日)

💰 最低价航班(3个)

1️⃣ 深圳航空 - ¥905 航班:ZH8997 出发:成都天府机场(TFU) 12:45 到达:兰州中川机场(LHW) 14:20 时长:1小时35分钟

2️⃣ 四川航空 - ¥935 航班:3U8597 出发:成都天府机场(TFU) 08:30 到达:兰州中川机场(LHW) 10:05 时长:1小时35分钟

3️⃣ 东方航空 - ¥1020 航班:MU2475 出发:成都双流机场(CTU) 15:20 到达:兰州中川机场(LHW) 16:55 时长:1小时35分钟

📊 搜索详情

  • 出发地机场:成都双流(CTU)、成都天府(TFU)、绵阳(MIG)
  • 目的地机场:兰州中川(LHW)、西宁(XNN)
  • 共搜索:3个出发机场 × 2个目的地机场 = 6个组合

💡 推荐:深圳航空¥905是最低价,中午出发时间合适,建议尽早预订。


用户:帮我查4月5日北京到秦皇岛的机票

助手:

🛫 北京 → 秦皇岛(4月5日)

💰 最低价航班(3个)

1️⃣ 河北航空 - ¥380 航班:NS3333 出发:北京大兴机场(PKX) 09:00 到达:唐山三女河机场(TVS) 10:15 时长:1小时15分钟 ⚠️ 降落在唐山机场,距秦皇岛约100公里,可乘大巴前往,约1.5小时

2️⃣ 中国国航 - ¥650 航班:CA8888 出发:北京首都机场(PEK) 14:30 到达:秦皇岛北戴河机场(BPE) 15:30 时长:1小时

3️⃣ 南方航空 - ¥720 航班:CZ6666 出发:北京大兴机场(PKX) 18:00 到达:秦皇岛北戴河机场(BPE) 19:00 时长:1小时

📊 搜索详情

  • 出发地机场:北京首都(PEK)、北京大兴(PKX)、天津滨海(TSN)
  • 目的地机场:秦皇岛北戴河(BPE)、唐山三女河(TVS)
  • 共搜索:3个出发机场 × 2个目的地机场 = 6个组合

💡 推荐:河北航空¥380最便宜,但需要从唐山坐大巴到秦皇岛。如果赶时间,国航¥650直飞秦皇岛更方便。


地面交通参考

当航班降落在临近机场时,提供以下地面交通指引:

常见临近机场交通
到达机场目的地交通方式时间
唐山(TVS)秦皇岛大巴1.5小时
天津(TSN)北京高铁35分钟
石家庄(SJW)北京高铁1小时
广州(CAN)深圳高铁30分钟
深圳(SZX)广州高铁30分钟
成都(CTU/TFU)重庆高铁1.5小时
重庆(CKG)成都高铁1.5小时
杭州(HGH)上海高铁1小时
南京(NKG)上海高铁1小时
西安(XIY)郑州高铁2小时
提示格式

当航班到达机场与目的地不同时,使用以下格式提示:

⚠️ 降落在<机场名>,距<目的地>约<距离>公里,可乘<交通方式>前往,约<时间>

CLI 命令参考

flight-search(搜索机票)
bash
python -m qvxianjiuguo.cli flight-search \
  --departure "重庆" \
  --destination "南京" \
  --date "2026-04-04"
参数必需说明默认值
--departure是出发地(城市名)-
--destination是目的地(城市名)-
--date是出发日期(YYYY-MM-DD)-
--platform否平台:qunar/ctrip/fliggy/ly/allqunar
--departure-range否出发地范围(km)350
--destination-range否目的地范围(km)300
--no-direct-only否包含中转航班默认只看直飞
bash
python -m qvxianjiuguo.cli flight-save-cookie --platform qunar
bash
python -m qvxianjiuguo.cli flight-load-cookie --platform qunar
flight-check-login(检查登录状态)
bash
python -m qvxianjiuguo.cli flight-check-login --platform qunar
flight-lookup(查询机场)
bash
python -m qvxianjiuguo.cli flight-lookup --city "重庆"
flight-nearby(附近机场)
bash
python -m qvxianjiuguo.cli flight-nearby --airport "CKG" --range 300

平台说明

平台代码登录支持搜索支持说明
去哪儿qunar✅ Cookie 方式✅ 完整支持默认平台,推荐使用
携程ctrip✅ Cookie 方式⚠️ 基础支持不保证持续适配
飞猪fliggy✅ Cookie 方式⚠️ 基础支持不保证持续适配
同程ly✅ Cookie 方式⚠️ 基础支持不保证持续适配

重要说明:

  • 去哪儿是主要支持平台,会持续维护和适配
  • 携程、飞猪、同程仅提供基础支持,不保证持续适配
  • 如遇其他平台搜索失败,建议切换到去哪儿平台

注意事项

  1. 登录状态保持:
    • Chrome 配置目录:~/.qvxianjiuguo/chrome-profile(浏览器自动管理)
    • Cookie 备份文件:~/.qvxian/qunar_cookies.json(手动保存)
    • 建议:登录后执行 flight-save-cookie 命令备份登录状态
  2. 不要转去互联网搜索:本技能已实现完整搜索功能
  3. 默认直飞:默认只搜索直飞航班,如需中转请明确告知
  4. 安全第一:强烈建议使用小号,购票请在手机官方APP完成
  5. 不计算总费用:只显示机票价格,不加上地面交通费用
  6. 不推荐地铁:地面交通只提高铁、大巴等跨城交通

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 48 other files in skills/qvxianjiuguo-skills of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • CLAUDE.md
  • README.md
  • _meta.json
  • data/airports/airports.json
  • data/airports/nearby-airports-200km.json
  • data/airports/nearby-airports-250km.json
  • data/airports/nearby-airports-300km.json
  • data/airports/nearby-airports-350km.json
  • data/airports/nearby-airports-500km.json
  • data/airports/provinceCities.json
  • data/airports/regionMapping.json
  • data/flight-matrix/flight-matrix.json
  • data/flight-matrix/lookup-table.json
  • data/flight-matrix/summary.json
  • docs/page_structure.json
  • docs/去哪儿_actions.json
  • … and 32 more

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Qvxianjiuguo Skills next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Qvxianjiuguo Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qvxianjiuguo Skills this skillLeoYeAI/openclaw-master-skills2.2k—~2.8kAutomated safety check: PassMIT
Ultimate Searchckckck/UltimateSearchSkill289—~944Automated safety check: NotesMIT
Web SearchEXboys/skilllite1702 repos~1kAutomated safety check: PassMIT
Mysearchskernelx/MySearch-Proxy159—~3kAutomated safety check: NotesNone
Tavilyopenclaw/openclaw392k2 repos~1.2kAutomated safety check: PassMIT
Web Search Plus Plugin V2robbyczgw-cla/web-search-plus-plugin101—~2kAutomated safety check: NotesMIT

Similar skills

  • Ultimate Search

    ckckck/UltimateSearchSkill

    双引擎网络搜索:Grok AI 搜索(实时联网+AI分析)+ Tavily 搜索(结构化结果+网页抓取). An agent skill from ckckck/UltimateSearchSkill.

    289 GitHub stars~944 tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check: notes
  • Web Search

    EXboys/skilllite

    Web search and content extraction with Tavily and Exa via inference.sh CLI.

    170 GitHub starsUsed in 2 repos~1k tokens
    Productivity & AutomationAuto-check passed
  • Mysearch

    skernelx/MySearch-Proxy

    Install, verify, debug, and use MySearch MCP/Skill. An agent skill from skernelx/MySearch-Proxy.

    159 GitHub stars~3k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check: notes
  • Tavily

    openclaw/openclaw

    Tavily web search, content extraction, and research tools. An agent skill from openclaw/openclaw.

    392k GitHub starsUsed in 2 repos~1.2k tokens
    Productivity & AutomationAuto-check passed
  • Web Search Plus Plugin V2

    robbyczgw-cla/web-search-plus-plugin

    OpenClaw plugin for source-only Routing v2 multi-provider search, completion-order Research with quality quorum and attributed provenance, heading-aware extraction spans, Tavily-first extraction…

    101 GitHub stars~2k tokensUpdated yesterday
    Productivity & AutomationAuto-check: notes
  • Tavily Hikari Best Practices

    IvanLi-CN/tavily-hikari

    Guide agents to use Tavily Hikari safely through tvly-hikari.

    362 GitHub stars~287 tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,200 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Qvxianjiuguo Skills

What does Qvxianjiuguo Skills do?

机票模糊搜索技能。当用户要求查询机票、搜索特价机票时触发. An agent skill from LeoYeAI/openclaw-master-skills. Qvxianjiuguo Skills is an agent skill from LeoYeAI/openclaw-master-skills.

When should I use Qvxianjiuguo Skills?

Qvxianjiuguo Skills fits situations like: tasks that involve Web search.

How do I install Qvxianjiuguo Skills in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill qvxianjiuguo-skills -a claude-code`. Or copy the skill folder (skills/qvxianjiuguo-skills in LeoYeAI/openclaw-master-skills) into .claude/skills/qvxianjiuguo-skills in your project. Claude Code loads it when a task matches its description.

How do I install Qvxianjiuguo Skills in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill qvxianjiuguo-skills -a codex`. Or copy the skill folder (skills/qvxianjiuguo-skills in LeoYeAI/openclaw-master-skills) into .agents/skills/qvxianjiuguo-skills in your project. Codex loads it when a task matches its description.

Can I use Qvxianjiuguo Skills in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill qvxianjiuguo-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qvxianjiuguo-skills, .gemini/skills/qvxianjiuguo-skills, .github/skills/qvxianjiuguo-skills and .opencode/skills/qvxianjiuguo-skills in your project.

What does Qvxianjiuguo Skills need to run?

Going by SKILL.md and its folder, Qvxianjiuguo Skills needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Qvxianjiuguo Skills access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Qvxianjiuguo Skills safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Qvxianjiuguo Skills use?

Qvxianjiuguo Skills is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Qvxianjiuguo Skills use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Qvxianjiuguo Skills?

Skills that share tags, products or a category with Qvxianjiuguo Skills: Ultimate Search (ckckck/UltimateSearchSkill, 289 stars), Web Search (EXboys/skilllite, 170 stars), Mysearch (skernelx/MySearch-Proxy, 159 stars) and Tavily (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qvxianjiuguo Skills?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.