T

Check weather forecasts and best travel seasons for any destination — temperature ranges, rainy seasons, typhoon risks, and what to wear. Also supports: flig...

Security Scan

The skill's purpose (travel weather + booking) is plausible, but the runtime instructions contain inconsistencies (references to nonexistent local files, a different brand vs CLI mismatch), require the agent to install a global npm package at runtime, and include a self-test that could force repeated executions — these issues merit caution before installing.

Purpose & Capability

The skill claims travel-weather and booking functionality 'powered by Fliggy', but all operational commands target a 'flyai' CLI (@fly-ai/flyai-cli). No credentials or service endpoints for Fliggy/booking are requested or documented. Booking capabilities usually require API keys or user auth; their absence and the Fliggy/flyai mismatch is inconsistent.

Instruction Scope

SKILL.md mandates using only flyai CLI outputs (never model knowledge), requires a global npm install at runtime, and enforces every response include a [Book]({detailUrl}) link. It also references several local docs (references/*.md) that are not included in the skill bundle — the agent would attempt to read non-existent files. The 'Self-test' rule (re-run if no links) could create repeated re-execution loops if the CLI fails to return expected fields.

Install Mechanism

No formal install spec is present in the registry (instruction-only), but SKILL.md instructs the agent to run 'npm i -g @fly-ai/flyai-cli' if flyai is missing. Installing a global npm package at runtime is a moderate-risk action: it's traceable (npm package), but the registry/maintainer trust and package behavior should be verified before allowing the agent to run it.

Credentials

The skill declares no required env vars or credentials despite offering booking and Fliggy-powered features, which typically require authentication. That omission could mean auth is handled by the CLI interactively or stored locally, but the lack of explicit credential requirements is unexpected and should be clarified.

Persistence & Privilege

The skill does not request 'always: true' and doesn't modify other skills or global agent config in the manifest. The primary extra privilege is the instruction to perform a global npm install at runtime, but that's an action the agent will execute only when invoked.

What to consider before installing

This skill is plausible but has red flags: (1) SKILL.md forces use of a third-party CLI (@fly-ai/flyai-cli) and tells the agent to install it globally — verify the npm package exists and is trustworthy before allowing the agent to run 'npm i -g'. (2) The doc mentions Fliggy as the provider but uses a different CLI (flyai); ask the author to explain how Fliggy integration/auth works and whether any API keys are required. (3) The instructions reference local files (references/*.md) that are not bundled — this will likely cause runtime errors. (4) The 'Self-test' requirement to re-run until a [Book](...) link appears could cause repeated executions if the CLI output format changes or fails. Recommend requesting: the package homepage/registry link for @fly-ai/flyai-cli, explicit auth requirements (what credentials are needed and where they are stored), and a corrected SKILL.md that either includes referenced templates or removes references. If you do not trust the npm package or cannot verify the provider, do not grant the agent permission to run global npm installs.

⚠️ 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: travel-weather

Overview

Check weather forecasts and best travel seasons for any destination — temperature ranges, rainy seasons, typhoon risks, and what to wear.

When to Activate

User query contains:

• English: "weather", "temperature", "rainy season", "when to go"
• Chinese: "天气", "温度", "几月去好", "什么时候去"

Do NOT activate for: packing → packing-list

Prerequisites

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

Parameters

Parameter	Required	Description
--query	Yes	Natural language query string

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: Weather Now

Trigger: "weather in {dest}"

flyai keyword-search --query "天气 {dest}"

Output: Current weather info.

Playbook B: Best Season

Trigger: "when to visit {dest}"

flyai keyword-search --query "最佳旅行季节 {dest}"

Output: Best travel season advice.

Playbook C: Monthly Weather

Trigger: "weather in {dest} in July"

flyai keyword-search --query "天气 {dest} 7月"

Output: Monthly weather details.

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 keyword-search --query "天气 东京 4月"

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.

General best seasons by region: NE Asia (Japan/Korea) spring + autumn, SE Asia (Thailand/Bali) Nov-Mar (dry season), Europe Apr-Oct, Maldives Nov-Apr. Typhoon risk: Jul-Oct for coastal China, Taiwan, Japan, Philippines. Monsoon: Jun-Sep for India, SE Asia. Always layer — weather changes fast in mountains.

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