graduation-trip

Book flights for graduation trips and post-graduation vacations. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, itinera...

Security Scan

The skill's instructions mostly line up with being a CLI-driven flight search helper, but there are mismatches and operational risks (unknown CLI publisher, mandatory global npm install, and a false 'powered by Fliggy' claim) that do not add up and warrant caution.

Purpose & Capability

The skill claims to be 'powered by Fliggy (Alibaba Group)', but all runtime work is forced through an unrelated CLI called 'flyai' (npm package @fly-ai/flyai-cli). No homepage or source is provided to verify this claim. Requesting a third-party CLI install is plausible for a booking/search skill, but the branding mismatch and lack of provenance is incoherent and unexplained.

Instruction Scope

SKILL.md tightly constrains behavior: the agent must not use training data and must obtain every piece of output from the flyai CLI, re-running if outputs lack a [Book]({detailUrl}) link. It explicitly instructs installing the CLI if absent and to never proceed without it. This gives the skill broad runtime control (installing software, executing commands). While appropriate for a CLI-first skill, the instructions also force repeated CLI installs/exec and strict re-execution loops which could lead to excessive system changes or repeated network activity if the CLI is untrusted.

Install Mechanism

There is no package or code bundled in the skill; instead the runbook tells the agent to run 'npm i -g @fly-ai/flyai-cli' if the CLI is missing. Installing a global npm package is a moderate-to-high risk runtime action when the package/vendor is unverified. The skill does not point to a vetted release host, repository, or publisher identity. This is an install-time action that would write binaries to the host system.

Credentials

The skill declares no required environment variables or credentials, which is consistent with the described behavior (search-only using CLI). However, typical booking flows often require credentials; the skill sidesteps booking/auth by returning booking links only. The absence of credential requests is not itself a problem but should be confirmed against the actual flyai CLI behavior (the CLI might prompt for credentials or expect config files).

Persistence & Privilege

The skill does not request 'always:true' and does not modify other skills. Nevertheless, it instructs installing a global CLI binary, which introduces persistent system-level artifacts (global npm package). That persistent change is significant and not documented in provenance metadata (homepage/source).

What to consider before installing

This skill is instruction-only and expects to install and run a third-party npm CLI (@fly-ai/flyai-cli). Before installing or enabling it: 1) Verify the CLI package publisher and source (npm page, GitHub repo, maintainer identity) and confirm it is legitimate and matches the 'Fliggy / Alibaba' claim. 2) Prefer skills that include a homepage or source repository; absence of these is a red flag. 3) If you must test it, run the npm install in a controlled sandbox or VM rather than your primary environment. 4) Expect the agent to run shell commands and to install a global binary—if you are uncomfortable with that, do not install the skill. 5) Ask the publisher for evidence that booking links (detailUrl) are safe and that no hidden credentials or telemetry are being sent. If the publisher cannot be verified, treat this skill as potentially risky.

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: graduation-trip

Overview

Graduation Trip Flights.

When to Activate

User query contains:

• English: "graduation trip flight", "grad vacation flight", "post graduation travel", "college graduation trip", "plan a trip"
• Chinese: "毕业旅行航班", "毕业季机票", "毕业出游", "散伙饭出行", "出行规划"

Do NOT activate for: student → student-flights; graduation → graduation

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: 3 (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: "graduation trip flight", "毕业旅行航班"

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

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 3

Output Rules

1. Conclusion first — lead with best option
2. Graduation tip — June-July is peak; book early for popular destinations
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
"graduation trip" / "毕业旅行"	--sort-type 3
"grad direct" / "毕业直飞"	--journey-type 1 --sort-type 3

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