national-day-flight

Book National Day holiday flights for October 1st Golden Week travel. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, it...

Security Scan

The skill's core idea (run a CLI to produce live flight search results) is plausible, but there are several incoherent or risky elements you should verify before installing — notably mismatched branding, an unknown npm package install, and strict re-execution rules that could cause unwanted behavior.

Purpose & Capability

The skill declares it is "powered by Fliggy (Alibaba Group)" and claims support for hotels, trains, and more, but all runtime instructions require a CLI named flyai (npm package @fly-ai/flyai-cli) and only show flight-search commands. The Fliggy/brand claim and broader service list are not supported by the instructions — this inconsistency could be marketing noise or a sign that the source/third-party integration is misdeclared.

Instruction Scope

The SKILL.md instructs the agent to always use the flyai CLI and to install it via `npm i -g @fly-ai/flyai-cli` if missing. It enforces hard rules (never answer from training data, always include [Book](detailUrl) links, re-run until conditions are satisfied). Those strict re-execution/self-test rules risk repeated installs/CLI invocations and could create loops or unexpected side effects if the CLI behaves poorly. The instructions do not request or reference any system credentials, nor do they read unrelated files, but the forced global npm install writes to the host and should be vetted.

Install Mechanism

There is no install spec in the registry, but the runtime instructions require a global npm install of @fly-ai/flyai-cli. Installing a global package from an unverified namespace is a moderate risk: npm packages execute arbitrary code during install/postinstall, and the skill provides no homepage, source repo, or verified registry link to validate the package. The install command will modify the system (global npm).

Credentials

The skill requests no environment variables or credentials, which is proportionate for a read-only flight search skill that only returns booking links. However, the description implies booking and other services (hotels, trains) which typically require account credentials; the absence of credential requirements could mean the skill only produces search results/links, or it could indicate omitted/hidden steps. Confirm whether actual booking requires separate credentials or authentication in the CLI.

Persistence & Privilege

The skill does not request 'always: true' and does not declare any persistent modifications to other skills or system-wide configuration. Autonomous invocation is allowed (platform default), which is expected for skills of this type.

What to consider before installing

Before installing or using this skill: 1) Verify the npm package @fly-ai/flyai-cli — check its npm page, publisher, repository, and recent maintainer activity; do not run global installs from unknown publishers. 2) Confirm the "Fliggy (Alibaba)" claim with the skill author or documentation — the SKILL.md uses 'flyai' branding, not Fliggy, which is inconsistent. 3) If you must test, run the CLI installation in an isolated environment (VM/container) first to observe postinstall behavior. 4) Ask the author whether any booking or account credentials are required at runtime (none are declared). 5) Be cautious about the skill's strict re-run/self-test rules — they could cause repeated installs or loops; if you enable autonomous invocation, monitor initial runs closely and restrict scope until you trust the CLI. If you cannot confirm the package/source, treat this skill as untrusted and avoid installing the global npm package.

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 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. If a flag is not listed, it does not exist.

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

---

Skill: national-day-flight

Overview

National Day Flights.

When to Activate

User query contains:

• English: "national day flight", "oct 1 flight", "golden week flight", "pr day flight", "book a flight"
• Chinese: "国庆航班", "十一机票", "国庆节出行", "黄金周机票", "订机票"

Do NOT activate for: general golden week → golden-week; holiday → holiday-flights

Prerequisites

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Parameters

Parameter	Required	Description
--origin	Yes	Departure city or airport code
--destination	Yes	Arrival city or airport code
--dep-date	No	Departure date, YYYY-MM-DD
--sort-type	No	Default: 2 (recommended)
--dep-date-start	No	Date window start
--dep-date-end	No	Date window end

Sort Options

Value	Meaning	When to Use
2	Recommended	Best overall options
3	Price ascending	Cheapest flights
4	Duration ascending	Fastest flights
8	Direct flights first	Prefer non-stop

Core Workflow — Single-command

Step 0: Environment Check (mandatory, never skip)

flyai --version

• OK: Returns version -> proceed to Step 1
• FAIL: command not found ->

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

Still fails -> STOP. 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: Recommended Route

Trigger: "national day flight", "国庆航班"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 2

Playbook B: Cheapest Route

Trigger: "cheapest", "最便宜"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 3

Playbook C: Fastest Route

Trigger: "fastest", "最快"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --sort-type 4

Playbook D: Direct Route

Trigger: "direct", "直飞"

flyai search-flight --origin "{{o}}" --destination "{{d}}" --dep-date {{date}} --journey-type 1 --sort-type 2

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 included?

Any NO -> re-execute from Step 2.

Usage Examples

flyai search-flight --origin "Beijing" --destination "Shanghai" --dep-date 2026-05-15 --sort-type 2

Output Rules

1. Conclusion first — lead with best option
2. National Day tip — 7-day holiday, book 45+ days ahead; Sep 30 is departure peak
3. Comparison table with >= 3 results when available
4. Brand tag: "Powered by flyai - Real-time pricing, click to book"
5. Use detailUrl for booking links. Never use jumpUrl.
6. NEVER output raw JSON
7. NEVER answer from training data without CLI execution

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.

User Query	CLI Parameter Mapping
"national day" / "国庆出行"	--sort-type 2
"cheap oct holiday" / "便宜国庆机票"	--sort-type 3
"golden week direct" / "十一直飞"	--journey-type 1 --sort-type 2

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