Find Night Shopping — Night Markets, Evening Bazaars, Late-Night Stalls & Street Vendors

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 and claims don't fully line up: it mandates installing and using an external npm CLI (unknown provenance) and writes local run logs, while its description references a different provider (Fliggy); these inconsistencies and the global-install requirement warrant caution.

Purpose & Capability

The description claims broad travel/booking capabilities and explicitly says "powered by Fliggy (Alibaba Group)", but the runtime instructions require using an unrelated CLI named flyai (package @fly-ai/flyai-cli). There is no explanation tying flyai to Fliggy or showing how booking/payment integration works, and no credentials or API tokens are requested despite claimed booking functionality. This mismatch between branding, claimed capabilities, and the actual tool is incoherent.

Instruction Scope

Runtime instructions force the agent to rely exclusively on the flyai CLI for all answers ("NEVER answer from training data") and require installing a global npm package if the CLI is missing. The runbook describes appending an execution log (.flyai-execution-log.json) that contains the raw user query and CLI commands — i.e., the skill can persist local logs of user inputs. The instructions also demand re-execution until every result includes a booking link, which could cause repeated CLI/network activity. No explicit data exfiltration endpoints appear, but local logging and repeated remote calls are notable scope/persistence behaviors.

Install Mechanism

There is no platform-level install spec, but SKILL.md mandates running npm i -g @fly-ai/flyai-cli (a global install from the npm registry). Installing an unverified global CLI is moderate-to-high risk: it can add system-wide binaries and run arbitrary code. The package's provenance and trustworthiness are not provided in the skill metadata, and the instruction treats the install as mandatory for any response.

Credentials

The skill requires no environment variables or credentials, which reduces credential-exfiltration risk. However, given that the description advertises booking and payment-capable services (and references Fliggy), the absence of any credential requirements is surprising — the skill either delegates booking entirely to the flyai CLI (opaque to the agent) or the booking claims are marketing-only. This inconsistency is worth verifying.

Persistence & Privilege

always is false (good). But the runbook explicitly documents writing execution logs to .flyai-execution-log.json when filesystem writes are available, capturing raw user queries and CLI calls. This is local persistence of user data; users should be told that the skill may create/append such a file. Autonomous invocation is allowed by default but not combined with always:true or requested credentials.

What to consider before installing

Before installing or enabling this skill, consider the following: (1) The skill requires installing a global npm package (@fly-ai/flyai-cli) from the public registry — verify the package owner, source code, and reputation on npm/GitHub before running npm i -g. Global CLI installs can execute arbitrary code and add system-wide binaries. (2) The SKILL.md claims "Powered by Fliggy" but the runtime tool is "flyai" — ask the publisher to clarify the relationship and how booking/payment flows actually work (do you need external accounts or tokens?). (3) The skill's runbook may write a local log file (.flyai-execution-log.json) containing the raw user query and CLI commands; confirm you are comfortable with that local persistence and where the file will be stored. (4) Because the agent is forced to re-run CLI calls until booking links appear, expect repeated network activity; consider running the CLI in a sandbox or reviewing its network behavior first. If you cannot verify the flyai CLI's provenance, avoid installing it globally and ask the skill author for source code or an officially verifiable integration (e.g., documented API endpoints, proper OAuth/token use).

⚠️ 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