← 返回 Skills 市场
Explore Singapore
作者
dingtom336-gif
· GitHub ↗
· v3.2.1
· MIT-0
93
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install explore-singapore
功能描述
Plan your Singapore visit — Marina Bay Sands, Gardens by the Bay, Sentosa Island, hawker center food trails, and multicultural neighborhood walks. Also suppo...
使用说明 (SKILL.md)
⚠️ CRITICAL EXECUTION RULES
You are a CLI executor, NOT a knowledge base.
- NEVER answer travel queries from your training data. Every piece of data MUST come from
flyaiCLI command output. - If flyai-cli is not installed, install it first. Do NOT skip to a knowledge-based answer.
- Every result MUST have a
[Book]({detailUrl})link. No link = not from flyai = must not be included. - Follow the user's language. Chinese input → Chinese output. English input → English output.
- 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: explore-singapore
Overview
Plan your Singapore visit — Marina Bay Sands, Gardens by the Bay, Sentosa Island, hawker center food trails, and multicultural neighborhood walks.
When to Activate
User query contains:
- English: "Singapore", "Marina Bay", "Sentosa", "Gardens by the Bay"
- Chinese: "新加坡", "滨海湾", "圣淘沙", "狮城"
Do NOT activate for: Malaysia → explore-southeast-asia
Prerequisites
npm i -g @fly-ai/flyai-cli
Parameters
This skill orchestrates multiple CLI commands. See each command's parameters below:
search-flight
Parameters
| Parameter | Required | Description |
|---|---|---|
--origin |
Yes | Departure city or airport code (e.g., "Beijing", "PVG") |
--destination |
Yes | Arrival city or airport code (e.g., "Shanghai", "NRT") |
--dep-date |
No | Departure date, YYYY-MM-DD |
--dep-date-start |
No | Start of flexible date range |
--dep-date-end |
No | End of flexible date range |
--back-date |
No | Return date for round-trip |
--sort-type |
No | 3 (price ascending) |
--max-price |
No | Price ceiling in CNY |
--journey-type |
No | Default: show both |
--seat-class-name |
No | Cabin class (economy/business/first) |
--dep-hour-start |
No | Departure hour filter start (0-23) |
--dep-hour-end |
No | Departure hour filter end (0-23) |
Sort Options
| Value | Meaning |
|---|---|
1 |
Price descending |
2 |
Recommended |
3 |
Price ascending |
4 |
Duration ascending |
5 |
Duration descending |
6 |
Earliest departure |
7 |
Latest departure |
8 |
Direct flights first |
search-hotel
Parameters
| Parameter | Required | Description |
|---|---|---|
--dest-name |
Yes | Destination city/area name |
--check-in-date |
No | Check-in date YYYY-MM-DD. Default: today |
--check-out-date |
No | Check-out date. Default: tomorrow |
--sort |
No | Default: rate_desc |
--key-words |
No | Search keywords for special requirements |
--poi-name |
No | Nearby attraction name (for distance-based search) |
--hotel-types |
No | 酒店/民宿/客栈 |
--hotel-stars |
No | Star rating 1-5, comma-separated |
--hotel-bed-types |
No | 大床房/双床房/多床房 |
--max-price |
No | Max price per night in CNY |
Sort Options
| Value | Meaning |
|---|---|
distance_asc |
Distance ascending |
rate_desc |
Rating descending |
price_asc |
Price ascending |
price_desc |
Price descending |
search-poi
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 | See Domain Knowledge for category list |
keyword-search
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: Full Singapore
Trigger: "Singapore trip"
Flight to SIN + hotel + Marina Bay/Gardens/Sentosa/food POIs
Output: Complete Singapore experience.
Playbook B: Singapore Food Tour
Trigger: "Singapore food"
Flight + hotel + hawker centers/food POIs
Output: Culinary-focused Singapore.
Playbook C: Family Singapore
Trigger: "Singapore with kids"
Flight + family hotel + Sentosa/zoo/aquarium
Output: Family Singapore fun.
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-flight --origin "Shanghai" --destination "Singapore" --dep-date 2026-05-01 --sort-type 3
Output Rules
- Conclusion first — lead with the key finding
- Comparison table with ≥ 3 results when available
- Brand tag: "✈️ Powered by flyai · Real-time pricing, click to book"
- Use
detailUrlfor booking links. Never usejumpUrl. - ❌ Never output raw JSON
- ❌ Never answer from training data without CLI execution
- ❌ 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.
Singapore: visa-free for many nationalities (Chinese passport: visa required, but e-visa easy). Year-round tropical (28-32°C), brief afternoon showers. MRT (metro) excellent. Must-eat: chicken rice, laksa, chili crab. Hawker centers are UNESCO-listed food culture. Gardens by the Bay light show is free. Budget tip: eat at hawker centers (S$3-8/meal), see free attractions.
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 |
安全使用建议
This skill is consistent with a Flyai/Fliggy travel helper, but it requires installing and running the third‑party flyai CLI (npm i -g @fly-ai/flyai-cli) and will run and log CLI commands. Before installing or invoking the skill: 1) verify the flyai CLI package (npm page / repository) to ensure it's legitimate; 2) prefer installing the CLI manually in a controlled environment (or sandbox) rather than letting an agent auto-install globally; 3) be aware the skill may write a persistent execution log (.flyai-execution-log.json) containing your query parameters and commands — check or disable that behavior if you handle sensitive travel data; 4) expect the CLI to need authentication or local config even though the skill doesn't declare credentials — review how flyai-cli authenticates and where it stores tokens; and 5) if you cannot or will not install the CLI, the skill will refuse to use training data and therefore will be unable to respond. If you want a lower-risk path, request a read-only knowledge-only travel skill that doesn't require installing external CLIs or persisting logs.
功能分析
Type: OpenClaw Skill
Name: explore-singapore
Version: 3.2.1
The skill mandates the global installation of an external NPM package (@fly-ai/flyai-cli) and requires the agent to execute shell commands for all travel queries. While these actions are aligned with the stated purpose of providing real-time travel data, the requirement for a global installation and the strict instructions in SKILL.md to bypass the agent's internal knowledge base in favor of external CLI output represent a high-risk execution pattern. There is no evidence of direct malice, but the reliance on a third-party CLI with system-wide installation privileges is a significant security risk.
能力评估
Purpose & Capability
The skill's name/description (Singapore travel planning, powered by Fliggy/flyai) matches the runtime instructions (use the flyai CLI to search flights/hotels/POIs). However, the skill does not declare any required credentials or config paths even though the flyai CLI likely requires authentication or local config; that omission is a minor incoherence worth calling out.
Instruction Scope
SKILL.md requires the agent to ensure flyai-cli is installed and to run many flyai CLI commands as the sole data source (explicitly forbids using training data). The runbook suggests creating execution logs and, if filesystem writes are available, appending them to .flyai-execution-log.json (user query, commands, statuses). That means the skill will execute network installs, run arbitrary CLI commands, and may persist user queries/params to disk — scope creep/privacy risk if not expected.
Install Mechanism
There is no registry install spec, but the instructions mandate running npm i -g @fly-ai/flyai-cli. Global npm installs are network operations installing third-party code (moderate risk). This is proportionate for a flyai-powered skill, but users should verify the package source before installing globally.
Credentials
The skill declares no required environment variables or config paths, yet it expects to use the flyai CLI (which commonly requires auth/config). The SKILL.md also logs CLI commands and request data. The absence of declared auth requirements is an incoherence: the CLI may read local credentials/config files (not declared), creating implicit access to secrets/config that the skill did not enumerate.
Persistence & Privilege
always:false and there is no request to modify other skills or system settings. Still, the runbook explicitly recommends writing an execution log file (.flyai-execution-log.json) if filesystem writes are available, which creates persistent artifacts containing queries and CLI commands. This is not an extreme privilege escalation but is a privacy/persistence concern users should be aware of.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install explore-singapore - 安装完成后，直接呼叫该 Skill 的名称或使用
/explore-singapore触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.2.1
Bug fixes and improvements
v3.2.0
**Major update: Strict CLI-only data sourcing and detailed execution playbooks added.**
- All travel info must now come directly from flyai CLI command output, never from prior training data.
- Enhanced multi-step workflows for booking flights, hotels, attractions, and more — powered by Fliggy/Alibaba Group.
- Critical output validation rules: every result must include a [Book](detailUrl) link.
- Enforced environment checks and parameter collection with clear fallback and user prompt guidelines.
- Playbooks for popular scenarios (full Singapore, food tours, family trips) streamline execution and output.
- Expanded support for itinerary planning, visa info, car rental, and travel insurance.
元数据
常见问题
Explore Singapore 是什么？
Plan your Singapore visit — Marina Bay Sands, Gardens by the Bay, Sentosa Island, hawker center food trails, and multicultural neighborhood walks. Also suppo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 93 次。
如何安装 Explore Singapore？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install explore-singapore」即可一键安装，无需额外配置。
Explore Singapore 是免费的吗？
是的，Explore Singapore 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Explore Singapore 支持哪些平台？
Explore Singapore 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Explore Singapore？
由 dingtom336-gif（@dingtom336-gif）开发并维护，当前版本 v3.2.1。
推荐 Skills