ancient-town-explorer

Discover preserved ancient towns, water villages, and traditional settlements — stone bridges, wooden houses, and time-frozen streetscapes. Also supports: fl...

Security Scan

The skill is internally coherent: it wraps a third‑party CLI (flyai-cli) to return real‑time POI and booking links for ancient towns and does not request unrelated credentials or obscure installs, but there are a few operational details you should review before use.

Purpose & Capability

The name/description (discover ancient towns, booking links, Fliggy/flyai) aligns with the instructions: all runtime actions are flyai-cli commands (search-poi, keyword searches) and output formatting for booking links. Nothing in the SKILL.md asks for unrelated cloud credentials or external services beyond flyai-cli, so requested capabilities are proportionate to the stated purpose.

Instruction Scope

The SKILL.md confines runtime actions to the flyai CLI and explicitly forbids answering from training data; it does not instruct reading unrelated system files or environment variables. Two points to note: (1) the 'Self-test' rule requiring every response to contain a [Book](...) link and the re-execute-on-failure loop could cause repeated re-execution if the CLI returns no booking links, possibly causing livelock. (2) The runbook suggests appending an execution log to .flyai-execution-log.json if filesystem writes are available — this explicitly persists user_query and other metadata locally, which may include PII.

Install Mechanism

This is an instruction-only skill with no bundled install script. It tells the agent/user to install @fly-ai/flyai-cli via 'npm i -g' if the flyai binary is missing. Installing a public npm CLI is a standard, expected step; no downloads from untrusted URLs or embedded binaries are present in the skill itself.

Credentials

The skill declares no required environment variables, credentials, or config paths. The only privacy-sensitive behavior is local log persistence (request_id, user_query) described in runbook.md — not an external credential request, but you should be aware logs may include user input and CLI responses.

Persistence & Privilege

The skill does not request always:true or any elevated platform privileges and does not modify other skills. However, the runbook instructs appending an execution log file (.flyai-execution-log.json) to disk when possible. This creates local persistence of queries/results; review whether you want such logs stored in the agent's working directory.

Assessment

This skill is a thin wrapper around the public flyai CLI and appears coherent with its travel/booking purpose. Before installing/using it: (1) verify the legitimacy of the @fly-ai/flyai-cli npm package (source repo, maintainer, network behavior) because that CLI performs network calls and returns booking links; (2) be aware the skill may write a local log file (.flyai-execution-log.json) containing your queries and CLI results — remove or inspect that file if you care about local retention; (3) the skill enforces that every response include a [Book](...) link and will re-run CLI commands if none are present — expect repeat attempts if the CLI returns no booking links; (4) avoid running global npm installs as root unless you trust the package. If you want to reduce risk, inspect the flyai-cli code or run it manually to verify outputs before allowing the agent to invoke this skill autonomously.

⚠️ 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: ancient-town-explorer

Overview

Discover preserved ancient towns, water villages, and traditional settlements — stone bridges, wooden houses, and time-frozen streetscapes.

When to Activate

User query contains:

• English: "ancient town", "old village", "water town", "traditional village"
• Chinese: "古镇", "古村", "水乡", "老镇"

Do NOT activate for: inn stays → ancient-town-inn

Prerequisites

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

Parameters

Parameter	Required	Description
--city-name	Yes	City name
--keyword	No	Attraction name or keyword
--poi-level	No	Rating 1-5 (5 = top tier)
--category	No	--category "古镇古村"

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: Ancient Towns

Trigger: "ancient town"

flyai search-poi --city-name "{city}" --category "古镇古村"

Output: Ancient towns and villages.

Playbook B: Water Towns

Trigger: "water town"

flyai search-poi --city-name "{city}" --keyword "水乡"

Output: Jiangnan water villages.

Playbook C: Ethnic Villages

Trigger: "ethnic village"

flyai search-poi --city-name "{city}" --keyword "古村"

Output: Minority ethnic villages.

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-poi --city-name "Jiaxing" --category "古镇古村"

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.

Top ancient towns: Wuzhen (best preserved), Xitang (lively nightlife), Zhouzhuang (oldest), Lijiang (Naxi culture), Fenghuang (riverside charm), Pingyao (walled city), Hongcun (ink-painting village). Visit weekdays to avoid crowds. Stay overnight for the best experience — most day-trippers leave by 5pm.

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