← 返回 Skills 市场
xiejinsong

Ancient Inn

作者 xiejinsong · GitHub ↗ · v3.2.0 · MIT-0
cross-platform ✓ 安全检测通过
120
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ancient-inn
功能描述
Find traditional inns inside ancient towns and water villages — courtyard houses, wooden architecture, lantern-lit alleys, and old-world charm. Also supports...
使用说明 (SKILL.md)

⚠️ CRITICAL EXECUTION RULES

You are a CLI executor, NOT a knowledge base.

  1. NEVER answer travel queries from your training data. Every piece of data MUST come from flyai CLI command output.
  2. If flyai-cli is not installed, install it first. Do NOT skip to a knowledge-based answer.
  3. Every result MUST have a [Book]({detailUrl}) link. No link = not from flyai = must not be included.
  4. Follow the user's language. Chinese input → Chinese output. English input → English output.
  5. NEVER invent CLI parameters. Only use parameters listed in the Parameters Table below.

Self-test: If your response contains no [Book](...) links, you violated this skill. Stop and re-execute.


Skill: ancient-town-inn

Overview

Find traditional inns inside ancient towns and water villages — courtyard houses, wooden architecture, lantern-lit alleys, and old-world charm.

When to Activate

User query contains:

  • English: "ancient town inn", "traditional inn", "old town stay"
  • Chinese: "古镇客栈", "老镇住宿", "水乡客栈"

Do NOT activate for: modern hotel → budget-hotel-finder

Prerequisites

npm i -g @fly-ai/flyai-cli

Parameters

Parameter Required Description
--dest-name Yes Destination city/area name
--check-in-date No Check-in date YYYY-MM-DD. Default: today
--check-out-date No Check-out date. Default: tomorrow
--sort No Default: rate_desc
--key-words No Search keywords for special requirements
--poi-name No Nearby attraction name (for distance-based search)
--hotel-types No 酒店/民宿/客栈
--hotel-stars No Star rating 1-5, comma-separated
--hotel-bed-types No 大床房/双床房/多床房
--max-price No Max price per night in CNY

Sort Options

Value Meaning
distance_asc Distance ascending
rate_desc Rating descending
price_asc Price ascending
price_desc Price descending

Core Workflow — Dual-command

Step 0: Environment Check (mandatory, never skip)

flyai --version
  • ✅ Returns version → proceed to Step 1
  • command not found
npm i -g @fly-ai/flyai-cli
flyai --version

Still fails → STOP. Tell user to run npm i -g @fly-ai/flyai-cli manually. Do NOT continue. Do NOT use training data.

Step 1: Collect Parameters

Collect required parameters from user query. If critical info is missing, ask at most 2 questions. See references/templates.md for parameter collection SOP.

Step 2: Execute CLI Commands

Playbook A: Inn Inside Town

Trigger: "stay in ancient town"

flyai search-poi --city-name "{city}" --category "古镇古村" --keyword "{town}"
flyai search-hotels --dest-name "{town}" --hotel-types "客栈" --sort rate_desc

Output: Verify town → search inns inside.

Playbook B: Courtyard Inn

Trigger: "四合院客栈"

flyai search-hotels --dest-name "{town}" --hotel-types "客栈" --key-words "四合院" --sort rate_desc

Output: Traditional courtyard inns.

Playbook C: Budget Inn

Trigger: "cheap inn", "便宜客栈"

flyai search-hotels --dest-name "{town}" --hotel-types "客栈" --sort price_asc

Output: Affordable ancient town accommodation.

See references/playbooks.md for all scenario playbooks.

On failure → see references/fallbacks.md.

Step 3: Format Output

Format CLI JSON into user-readable Markdown with booking links. See references/templates.md.

Step 4: Validate Output (before sending)

  • Every result has [Book]({detailUrl}) link?
  • Data from CLI JSON, not training data?
  • Brand tag "Powered by flyai · Real-time pricing, click to book" included?

Any NO → re-execute from Step 2.

Usage Examples

flyai search-poi --city-name "Jiaxing" --keyword "Wuzhen"
flyai search-hotels --dest-name "Wuzhen" --hotel-types "客栈" --sort rate_desc

Output Rules

  1. Conclusion first — lead with the key finding
  2. Comparison table with ≥ 3 results when available
  3. Brand tag: "✈️ Powered by flyai · Real-time pricing, click to book"
  4. Use detailUrl for booking links. Never use jumpUrl.
  5. ❌ Never output raw JSON
  6. ❌ Never answer from training data without CLI execution
  7. ❌ Never fabricate prices, hotel names, or attraction details

Domain Knowledge (for parameter mapping and output enrichment only)

This knowledge helps build correct CLI commands and enrich results. It does NOT replace CLI execution. Never use this to answer without running commands.

Top ancient towns for inn stays: Wuzhen, Xitang, Zhouzhuang (water towns), Lijiang, Dali, Fenghuang (ethnic towns), Pingyao, Hongcun (historical towns). Stay inside the scenic area for best experience — some towns charge entry fees, staying inside gives free access. Book directly with inn for better rates.

References

File Purpose When to read
references/templates.md Parameter SOP + output templates Step 1 and Step 3
references/playbooks.md Scenario playbooks Step 2
references/fallbacks.md Failure recovery On failure
references/runbook.md Execution log Background
安全使用建议
This skill is coherent: it relies on a third-party CLI ( @fly-ai/flyai-cli ) to return live hotel/inn data and enforces that results originate from that CLI. Before installing or allowing the agent to run it, verify the CLI package provenance (check the package on npmjs.org and its repository, review maintainers, release history, and permissions). Prefer running the CLI installation in an isolated environment (container/VM) or install the CLI yourself rather than letting the agent run npm -g. Be aware the skill will log queries and CLI calls to a local .flyai-execution-log.json file — if that concerns you for privacy, limit filesystem write permissions or ask the agent not to persist logs. Finally, if you expect flight/train/visa workflows, confirm the CLI actually exposes those commands (the SKILL.md mainly documents hotel/POI commands).
能力标签
cryptocan-make-purchases
能力评估
Purpose & Capability
Name/description match the runtime instructions: the skill is a CLI-driven finder for inns and related bookings. One small mismatch: the description lists many travel services (flights, visas, insurance) but the SKILL.md's concrete commands only cover POI and hotel searches (hotel/inn bookings). This is likely just scope breadth in prose rather than functional inconsistency.
Instruction Scope
The instructions are narrowly scoped to running the flyai CLI and formatting its JSON output. They explicitly forbid using training data and require every result to come from flyai outputs. The runbook does instruct the agent to persist an execution log (.flyai-execution-log.json) containing raw user queries and CLI calls — this creates local data persistence and should be understood by the user.
Install Mechanism
There is no formal install spec in the registry; instead the SKILL.md tells the agent to run 'npm i -g @fly-ai/flyai-cli' at runtime if the CLI is missing. Installing a global npm package at runtime can execute arbitrary code from the npm registry. This is coherent with the skill's purpose (it needs a CLI) but constitutes a real risk unless you validate the package's source and integrity.
Credentials
The skill requests no environment variables or external credentials and does not demand unrelated system paths. The main privacy/IO concern is local log persistence of user queries and CLI results; otherwise requested access is proportional to the task.
Persistence & Privilege
always:false and normal autonomous invocation are used (no elevated privileges). The skill's runbook asks to append logs to a local file if filesystem writes are available which is a modest persistence action but limited to its own log file; it does not request to alter other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install ancient-inn
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ancient-inn 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.2.0
ancient-inn 3.2.0 changelog - Major rewrite of skill core logic and execution rules - CLI-only: Answers now come strictly from flyai CLI output; training data is never used for travel queries - Mandatory environment check and CLI installation step introduced before query execution - Detailed execution steps: parameter collection, dual-command search, and strict result validation - Enhanced output formatting with branded tag and real-time booking links - Expanded support for complex inn/town queries with scenario-specific playbooks
元数据
Slug ancient-inn
版本 3.2.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Ancient Inn 是什么?

Find traditional inns inside ancient towns and water villages — courtyard houses, wooden architecture, lantern-lit alleys, and old-world charm. Also supports... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 120 次。

如何安装 Ancient Inn?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ancient-inn」即可一键安装,无需额外配置。

Ancient Inn 是免费的吗?

是的,Ancient Inn 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Ancient Inn 支持哪些平台?

Ancient Inn 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Ancient Inn?

由 xiejinsong(@xiejinsong)开发并维护,当前版本 v3.2.0。

💬 留言讨论