last-seat-flight

Search for last available seats on nearly full flights. Also supports: flight booking, hotel reservation, train tickets, attraction tickets, itinerary planni...

Security Scan

The skill's requirements and runtime instructions are consistent with a CLI-based flight search/booking helper, but it relies on installing and running a third-party npm CLI at runtime which carries non-trivial risk and should be vetted before use.

Purpose & Capability

The name/description (last-seat flight search and booking) align with the instructions: all queries are to be satisfied by the flyai CLI. There are no unrelated credential requests or unrelated binaries required.

Instruction Scope

The SKILL.md restricts the agent to gather data only by running the flyai CLI, enforces parameter usage, and does not instruct reading arbitrary files, environment variables, or contacting unknown endpoints. It does require installing and executing a third-party CLI when not present, but otherwise keeps scope limited to constructing CLI calls and formatting results.

Install Mechanism

Although no install spec is published in the registry, the runtime instructions explicitly tell the agent to run `npm i -g @fly-ai/flyai-cli` when `flyai` is missing. Installing a global npm package at runtime downloads and executes third-party code on the host and can run arbitrary scripts — this is expected for a CLI-based skill but carries real risk and should be validated (publisher, package contents, permissions, and trustworthiness).

Credentials

The skill requests no environment variables, no credentials, and no config paths, which is appropriate for a CLI-only search/booking helper. Note: it implicitly requires the ability to run shell commands and network access for npm and the CLI.

Persistence & Privilege

The skill is not marked always:true, does not demand persistent system-wide changes beyond an optional global npm install, and does not request changes to other skills or system configuration. Autonomous invocation is allowed by default (normal) but not exceptional here.

Assessment

This skill appears to do what it says (it runs a flight-search CLI and formats booking links) but at runtime it may install and execute a third‑party npm package (@fly-ai/flyai-cli). Installing global npm packages can run arbitrary code and access the network. Before installing or letting an agent run this skill: 1) verify the @fly-ai/flyai-cli package on npmjs.com (publisher, homepage, maintainers, recent releases, and source repo); 2) prefer that you or an administrator install the CLI in a controlled environment (or decline the global install) rather than allowing the agent to install it autonomously; 3) run the package in a sandbox or VM if possible; 4) confirm that generated booking links (detailUrl) point to legitimate vendor domains before clicking or sharing payment info. If you cannot verify the CLI package, treat this skill as higher risk and avoid granting it runtime installation privileges.

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: last-seat-flight

Overview

Last Seat Flights.

When to Activate

User query contains:

• English: "last seat flight", "final seat flight", "fully booked flight", "near full flight", "book a flight"
• Chinese: "最后座位航班", "满座查询机票", "最后一张机票", "尾票", "订机票"

Do NOT activate for: urgent → urgent-flights; last minute → last-minute

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)
--max-price	No	Price ceiling in CNY

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: "last seat flight", "最后座位航班"

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. Last seat tip — check multiple dates; connecting flights may have availability
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
"last seat" / "最后座位"	--sort-type 2
"any available" / "有座即可"	--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