Night Bazaar

Find night markets, food streets, and local culinary hotspots. Discover street food, local specialties, and the best evening food experiences. Also supports:...

Security Scan

The skill's instructions force installation and execution of a third-party CLI and write local logs, while its description (claims about Fliggy / booking features) is not supported by the provided commands — the pieces don't fully add up.

Purpose & Capability

The skill description advertises broad travel capabilities (flight/hotel/booking, “Powered by Fliggy”) but the SKILL.md only contains CLI commands for searching POIs (night markets). No booking commands, APIs, or credentials for Fliggy are provided — this is an unexplained mismatch between what the skill says it does and what it actually instructs the agent to do.

Instruction Scope

The runtime instructions require installing and running an external CLI (flyai) and insist every answer come exclusively from its output. The runbook also instructs writing an execution log to disk (.flyai-execution-log.json) if file writes are available. The skill enforces re-execution until results include a specific link format, which could cause repeated CLI calls. These behaviors go beyond a simple lookup skill and expand the agent's local-side actions.

Install Mechanism

There is no built-in install spec, but SKILL.md mandates 'npm i -g @fly-ai/flyai-cli' if the CLI is missing. Installing a global npm package from an unknown publisher (no homepage or source provided) is a moderate risk — the skill expects users/agents to fetch and run third-party code without checksums or publisher verification.

Credentials

The skill declares no required environment variables or credentials, which aligns with simple POI search. However, the description's claims about booking/Fliggy would normally require API keys or credentials — none are requested or documented. Additionally, the execution log may capture and persist user queries and results (potentially sensitive) without explicit consent or retention policy.

Persistence & Privilege

The skill is not marked 'always:true' and does not request elevated platform privileges. However, its runbook instructs appending execution logs to a file in the working directory if available, which gives it persistent local state (request IDs, queries, results). This is plausible for auditing but is a persistence behavior users should be aware of.

What to consider before installing

This skill requires installing and running a third-party npm CLI on your machine and will rely entirely on that CLI's output. Before installing or invoking it: 1) Verify the publisher and inspect the @fly-ai/flyai-cli package on the npm registry (or run it in a sandbox) — the skill provides no homepage/source. 2) Expect the skill to write a local execution log (.flyai-execution-log.json) containing request/response data; confirm you are comfortable with local persistence of queries and results. 3) Ask the skill author to explain the advertised Fliggy/booking capabilities and what credentials (if any) they require — currently those claims are unsupported by the runtime instructions. 4) If you proceed, run the npm install in a controlled environment first (or review the package code) and watch for repeated CLI calls if the skill enforces re-execution until a link format appears.

⚠️ 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: night-market

Overview

Find night markets, food streets, and local culinary hotspots. Discover street food, local specialties, and the best evening food experiences.

When to Activate

User query contains:

• English: "night market", "street food", "food market", "evening food"
• Chinese: "夜市", "小吃街", "美食街", "逛夜市"

Do NOT activate for: food tour → food-tour

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 "市集" --keyword "夜市"

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: Night Markets

Trigger: "night market"

flyai search-poi --city-name "{city}" --category "市集" --keyword "夜市"

Output: Night markets and food streets.

Playbook B: Food Streets

Trigger: "food street"

flyai search-poi --city-name "{city}" --category "市集"

Output: Local food markets.

Playbook C: Snack Street

Trigger: "street food"

flyai search-poi --city-name "{city}" --keyword "小吃街"

Output: Street food hotspots.

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 "Xian" --category "市集" --keyword "夜市"

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.

Famous night markets: Shilin (Taipei), Raohe (Taipei), Donghuamen (Beijing), Wangfujing (Beijing), Huimin Street (Xi'an), Nanjing Road area (Shanghai). Best night markets open 5pm-midnight. Arrive early (6-7pm) for best selection, 9-10pm for discounts on unsold food. Mobile payment essential in China.

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