extended-stay

Find serviced apartments and hotels for extended stays — weekly or monthly rates, kitchenettes, laundry, and home-like amenities for long-term travelers. Als...

Security Scan

The skill largely behaves like a thin wrapper around an external CLI (flyai-cli) which is plausible for hotel searches, but the README/description over-promises features, the runtime instructions require installing a global npm package and write local execution logs without declaring any credential requirements — these mismatches and local persistence warrant caution.

Purpose & Capability

The description claims broad travel capabilities (flights, train tickets, visas, insurance, car rental) and is branded 'powered by Fliggy', but the SKILL.md and playbooks only specify flyai-cli hotel search commands and hotel-focused playbooks. This overstatement of scope is an incoherence — either the skill is only for hotels or the other capabilities are implemented elsewhere (not present in this package).

Instruction Scope

The runtime instructions mandate executing flyai CLI commands for all answers (never use training data) and require installing the CLI via 'npm i -g @fly-ai/flyai-cli' if missing. The references include a runbook that will append an execution log to .flyai-execution-log.json when filesystem writes are available (i.e., the skill will persist logs locally). The SKILL.md enforces re-execution until results contain booking links, which could lead to repeated CLI calls. The instructions do not reference or declare any environment variables or credential handling for the flyai CLI, even though that CLI may require auth — this gap is noteworthy.

Install Mechanism

There is no formal install spec — this is instruction-only — but SKILL.md explicitly tells the agent/user to run a global npm install of @fly-ai/flyai-cli. Installing a scoped npm package globally is a moderate risk (it fetches and runs third-party code). The skill itself does not ship code, so the platform won't automatically vet the package; the user should verify the npm package and its publisher before installing.

Credentials

The skill declares no required env vars or credentials, yet it will execute a networked CLI that likely needs API keys or stored credentials to reach booking providers. The SKILL.md offers no guidance on where flyai-cli stores credentials or whether it will prompt for them. The absence of declared credentials is an inconsistency that could hide credential prompts or local config reads by the CLI.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. However, the runbook includes an instruction to append execution logs to .flyai-execution-log.json in the working directory if filesystem writes are available, meaning the skill will persist logs locally. It does not appear to modify other skills or system-wide configurations.

What to consider before installing

Before installing or enabling this skill, consider the following: - Verify scope: The skill description lists many travel services (flights, visas, insurance), but the included SKILL.md and playbooks only implement hotel/long-stay searches via flyai-cli. Ask the publisher which features are actually implemented. - Inspect the CLI: The skill requires running 'npm i -g @fly-ai/flyai-cli'. Review the @fly-ai package on npm (maintainer, source repo, recent activity) before installing a global package you don't trust. Global npm installs can add executables to your PATH. - Expect network calls and credentials: The CLI will make network requests and may require API keys or an account. The skill does not declare any required env vars or explain where credentials are stored, so assume the CLI may prompt for or read local config files. Do not provide secrets to the agent; prefer running the CLI yourself to see what it asks for. - Local persistence: The runbook indicates the agent will append an execution log to .flyai-execution-log.json if filesystem writes are allowed. If you are concerned about local data leakage, restrict filesystem access or review logs created by runs. - Looping/retries: The skill enforces re-execution until results include [Book](...) links. That could produce repeated CLI calls if responses are malformed. Monitor for excessive calls or unexpected traffic. - Verify branding and provenance: The skill mentions 'Powered by Fliggy' and references an external parent repo; confirm these claims and the publisher's identity before trusting booking links or following through on purchases. If you still want to try it: run the flyai CLI yourself in a controlled environment (inspect what network endpoints it contacts and whether it requires account credentials), confirm the npm package source, and only then allow the agent to run the skill. If any answers require you to provide API keys or secrets, decline and perform bookings directly through trusted official channels.

⚠️ 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: extended-stay

Overview

Find serviced apartments and hotels for extended stays — weekly or monthly rates, kitchenettes, laundry, and home-like amenities for long-term travelers.

When to Activate

User query contains:

• English: "long stay", "monthly", "extended stay", "apartment", "weekly rate"
• Chinese: "长住", "月租", "长租公寓", "服务式公寓"

Do NOT activate for: short stay → budget-hotel

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: price_asc (best long-term value)
--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 — Single-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: Monthly Stay

Trigger: "monthly rental", "月租"

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

Output: Long-stay options, cheapest first.

Playbook B: Serviced Apartment

Trigger: "serviced apartment"

flyai search-hotel --dest-name "{city}" --key-words "服务式公寓" --sort rate_desc --check-in-date {in} --check-out-date {out}

Output: Apartment-style with hotel services.

Playbook C: With Kitchen

Trigger: "有厨房的住宿"

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

Output: Accommodation with cooking facilities.

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-hotel --dest-name "Shanghai" --key-words "长租" --sort price_asc --check-in-date 2026-05-01 --check-out-date 2026-06-01

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.

Long-stay tips: negotiate directly for stays >7 nights (20-40% discount typical). Serviced apartments often cheaper than hotels for 2+ weeks. Check: kitchen facilities, laundry, WiFi speed, workspace. Popular platforms for monthly: Ziroom, locals' recommendations.

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