food-tour

Plan culinary travel experiences — local food tours, Michelin restaurants, street food crawls, cooking classes, food markets, and regional specialty tasting...

Security Scan

The skill consistently expects a third‑party CLI (flyai-cli) and to write execution logs, but the registry metadata does not declare those dependencies or storage behaviors — this mismatch and the global npm install instruction are reasons for caution.

Purpose & Capability

SKILL.md requires and instructs installing and running the @fly-ai/flyai-cli to produce all answers, which is coherent with the skill's purpose, but the published skill metadata declares no required binaries, no install spec, and no config/credential requirements. The missing manifest entries (required binary/install) are an incoherence: a user would expect the skill to declare that it depends on a CLI and may need credentials.

Instruction Scope

The instructions mandate that every answer come only from flyai CLI output (never from training data) and require re-running until each result includes a [Book]({detailUrl}) link. The runbook also instructs writing detailed execution logs including user_query and request_id to .flyai-execution-log.json if filesystem writes are available. That introduces persistent storage of user queries and runtime data which is not declared in the skill metadata and can contain sensitive information.

Install Mechanism

There is no install spec in the registry, but SKILL.md 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-risk operation (postinstall scripts, code from npm registry). The instruction points to a named npm package (not a shortener or personal URL), which is expected for this functionality, but the skill should have declared this dependency explicitly in its install metadata.

Credentials

The skill declares no required environment variables or credentials, yet the flyai CLI it depends on may require API keys or account credentials (not documented here). Additionally, the runbook's suggested logs capture raw user_query and CLI commands/results; retaining these without declaring them is disproportionate to the skill manifest and raises privacy concerns.

Persistence & Privilege

always:false (normal), but SKILL.md/runbook instructs persistent logging to a local file (.flyai-execution-log.json) if filesystem writes are available. That means the skill may create/append files on disk and store user queries and CLI outputs — behavior not declared in the registry. The skill also directs global npm installs which modify the host environment.

What to consider before installing

This skill wraps a third‑party CLI (flyai-cli) and instructs installing it globally and writing execution logs to disk, but the package dependency and logging behavior are not declared in the skill metadata. Before installing or enabling the skill: 1) Inspect the @fly-ai/flyai-cli npm package and its source (repo, maintainers, postinstall scripts). 2) Confirm whether the CLI requires API keys or accounts and where those credentials are stored. 3) Be aware the skill may write .flyai-execution-log.json containing request_id and user_query; if that is unacceptable, do not install or run in an environment where persistent logs are allowed. 4) Prefer running the CLI manually in a sandbox to verify behavior before granting the agent capability to install/run it automatically. 5) If you proceed, monitor file writes and network activity and consider running the skill only when needed (do not set always:true).

⚠️ 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: food-tour

Overview

Plan culinary travel experiences — local food tours, Michelin restaurants, street food crawls, cooking classes, food markets, and regional specialty tasting routes.

When to Activate

User query contains:

• English: "food tour", "culinary", "local food", "foodie", "where to eat"
• Chinese: "美食之旅", "吃什么", "美食推荐", "当地小吃"

Do NOT activate for: night market → night-market

Prerequisites

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

Parameters

Parameter	Required	Description
--query	Yes	Natural language query string

Core Workflow — Multi-command orchestration

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: Food Tour

Trigger: "food tour in {city}"

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

Output: Comprehensive food exploration.

Playbook B: Street Food

Trigger: "street food {city}"

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

Output: Street food hotspots.

Playbook C: Cooking Class

Trigger: "cooking class {city}"

flyai keyword-search --query "烹饪课程 {city}"

Output: Cooking class experiences.

Playbook D: Fine Dining

Trigger: "Michelin {city}"

flyai keyword-search --query "米其林餐厅 {city}"

Output: Top-rated restaurants.

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 "Chengdu" --category "市集"
flyai keyword-search --query "美食 成都"

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.

China's food capitals: Chengdu/Chongqing (Sichuan spice), Guangzhou (Cantonese dim sum), Xi'an (Muslim Quarter), Shanghai (xiaolongbao), Lanzhou (hand-pulled noodles), Changsha (Hunan spice). International: Bangkok (street food capital), Tokyo (most Michelin stars worldwide), Istanbul, Mexico City. Food tour tip: go hungry, share dishes, eat where locals eat (not tourist zones).

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