Onsen Hotel

Book hotels with genuine hot spring baths — natural onsen pools, private hot spring rooms, and Japanese-style ryokan experiences. Also supports: flight booki...

Security Scan

The skill's requests and runtime instructions are coherent with a booking helper that relies on a third‑party CLI, but it depends on installing and running an external npm package and will optionally persist an execution log — review the CLI package and local logging before installing.

Purpose & Capability

The skill's purpose (finding and booking onsen hotels) aligns with the CLI commands it mandates (flyai search-hotel / search-poi). It does not request unrelated credentials or binaries. Note: the skill relies entirely on the third-party flyai CLI (npm package @fly-ai/flyai-cli) for data and does not declare how authentication is handled (likely via the CLI), so users should expect interactive auth or locally-stored credentials.

Instruction Scope

All runtime instructions stay within the booking domain and require running specific flyai CLI commands; they explicitly forbid answering from training data. The runbook instructs the agent to persist an execution log (.flyai-execution-log.json) if filesystem writes are available. This log may include user queries and CLI results — a privacy consideration but not out of scope for the skill.

Install Mechanism

There is no packaged install spec in the registry, but the SKILL.md requires installing an npm package globally (npm i -g @fly-ai/flyai-cli). Installing a third-party npm CLI is a reasonable approach for a CLI-driven skill, but it is moderate risk compared to instruction-only skills because the external package's behavior and trustworthiness matter.

Credentials

The skill declares no environment variables or credentials, which is consistent with delegating auth to the flyai CLI. There are no requests for unrelated secrets or system config. Be aware the CLI itself may prompt for or store credentials locally; that behavior is external to the skill.

Persistence & Privilege

The skill does not request elevated privileges or 'always' presence. It does instruct writing an execution log to the working directory if possible; writing its own log is reasonable but may persist user queries/outputs without explicit per-request consent. This is a privacy/retention concern rather than a capability mismatch.

Scan Findings in Context

[no_code_files_to_scan] expected: The regex-based scanner had no code files to analyze; this is expected because the skill is instruction-only (SKILL.md and reference docs). Absence of findings does not guarantee safety — the runtime depends on an external npm CLI.

Assessment

This skill is coherent for booking onsen hotels but relies on a third-party npm CLI (@fly-ai/flyai-cli) and may write an execution log to your working directory. Before installing or running: (1) verify the npm package source and reputation (npm/GitHub) and prefer installing in an isolated environment if unsure; (2) be prepared for the CLI to prompt for authentication or store credentials locally; (3) know that the skill may persist .flyai-execution-log.json containing queries and results — inspect or disable this behavior if you don't want local logs; (4) confirm booking links are the detailUrl returned by the CLI as required. If any of these are unacceptable, do not install/run the CLI or run it in a sandbox/container.

⚠️ 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: onsen-hotel

Overview

Book hotels with genuine hot spring baths — natural onsen pools, private hot spring rooms, and Japanese-style ryokan experiences.

When to Activate

User query contains:

• English: "hot spring", "onsen", "thermal bath", "soak"
• Chinese: "温泉", "泡汤", "温泉酒店", "私汤"

Do NOT activate for: hot spring attraction → hot-springs

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: Hot Spring + Hotel

Trigger: "温泉酒店"

flyai search-poi --city-name "{city}" --category "温泉"
flyai search-hotel --dest-name "{city}" --key-words "温泉" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Find hot springs → nearby hotels with onsen.

Playbook B: Private Hot Spring

Trigger: "私汤"

flyai search-hotel --dest-name "{city}" --key-words "私汤" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Hotels with in-room private hot spring.

Playbook C: Hot Spring Resort Package

Trigger: "温泉度假"

flyai search-hotel --dest-name "{city}" --key-words "温泉度假" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Full resort experience with hot spring.

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 "Huangshan" --category "温泉"
flyai search-hotel --dest-name "Huangshan" --key-words "温泉" --sort rate_desc --check-in-date 2026-11-01 --check-out-date 2026-11-02

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.

China's top hot spring destinations: Tengchong (Yunnan), Huangshan (Anhui), Jiuhua Mountain, Nanjing Tangshan, Conghua (Guangzhou). Japan: Hakone, Beppu, Arima, Kusatsu. Best season: autumn/winter. Private onsen (私汤) costs 50-100% more but worth it for privacy. Book weekdays for 30% savings.

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