← Back to Skills Marketplace
Solo Trip
by
dingtom336-gif
· GitHub ↗
· v3.2.0
· MIT-0
71
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install solo-trip
Description
Plan solo travel adventures — safe destinations, social hostels, solo-friendly activities, and tips for meeting fellow travelers on the road. Also supports:...
Usage Guidance
This skill is coherent as a CLI-driven travel planner, but it asks the agent to install and run a third-party npm CLI at runtime and to persist execution logs. Before installing or using it: (1) verify the @fly-ai/flyai-cli package and publisher on the npm registry (check package maintainers, versions, and reviews); (2) prefer to install the CLI yourself (not let the agent run npm i -g) so you control installation and can inspect what is installed; (3) confirm how the CLI authenticates to Fliggy and whether any credentials or tokens are required — don't provide secrets unless you trust the CLI and understand where they are stored; (4) ask whether execution logs will be stored locally and what they contain; if you need stronger assurances, decline or sandbox the skill (require explicit approval before any install or filesystem write).
Capability Analysis
Type: OpenClaw Skill
Name: solo-trip
Version: 3.2.0
The skill requires the agent to perform a global installation of an external NPM package (@fly-ai/flyai-cli) and execute shell commands to fetch travel data. It also includes instructions in references/runbook.md to log user queries and execution metadata to a local file (.flyai-execution-log.json). While these behaviors are plausibly aligned with the stated travel planning purpose, the combination of global package installation, shell execution, and local file logging represents a high-risk capability set that warrants caution.
Capability Assessment
Purpose & Capability
The skill claims to provide real-time travel bookings and names Fliggy (Alibaba Group) as the backend; requiring a CLI (flyai) to get live data is consistent with that purpose. However, the SKILL.md does not declare any credentials or explain how the CLI authenticates to Fliggy (or whether it will prompt for user credentials), which is a missing piece of justification.
Instruction Scope
The runtime instructions mandate installing and invoking @fly-ai/flyai-cli and require every answer to come exclusively from that CLI. The runbook also instructs the agent to create an internal execution log and suggests writing it to .flyai-execution-log.json if filesystem writes are available. These steps broaden scope to installing software, accessing network endpoints, and persisting potentially sensitive user queries and command outputs to disk.
Install Mechanism
There is no registry install spec, but the SKILL.md explicitly tells the agent to run a global npm install (npm i -g @fly-ai/flyai-cli) at runtime if the CLI is missing. That causes arbitrary code to be fetched and installed from the npm registry during execution — a moderate-to-high risk operation that is not vetted by the skill manifest and is executed without prior user-declared approval in the metadata.
Credentials
The skill declares no required environment variables, but the flyai CLI will likely need authentication to book or access live pricing. The SKILL.md does not explain where credentials come from or how they are protected. Additionally, the runbook/logging behavior may capture and persist user queries, commands run, and results — potentially containing PII or booking credentials — without describing retention or access controls.
Persistence & Privilege
The skill is not always-on and does not request special platform privileges. However, it instructs the agent to persist an execution log to disk when possible. Writing .flyai-execution-log.json with raw user_query and CLI outputs increases persistence and local data exposure; this is a notable behavior even if limited to the skill's own logs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install solo-trip - After installation, invoke the skill by name or use
/solo-trip - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.2.0
solo-trip 3.2.0
- Major update: Strict execution rules added to ensure all answers use real-time data from flyai CLI, never training data.
- Booking results must include a `[Book](detailUrl)` link; responses without links force a re-execution.
- Explicit brand tag and result formatting requirements for all outputs.
- Detailed parameters and output rules for flights, hotels, and POIs targeting solo travelers.
- Clear scenario playbooks for city trips, adventure travel, and safety-focused solo itineraries.
- Enhanced multilingual support: replies match user language automatically (English/Chinese).
Metadata
Frequently Asked Questions
What is Solo Trip?
Plan solo travel adventures — safe destinations, social hostels, solo-friendly activities, and tips for meeting fellow travelers on the road. Also supports:... It is an AI Agent Skill for Claude Code / OpenClaw, with 71 downloads so far.
How do I install Solo Trip?
Run "/install solo-trip" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Solo Trip free?
Yes, Solo Trip is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Solo Trip support?
Solo Trip is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Solo Trip?
It is built and maintained by dingtom336-gif (@dingtom336-gif); the current version is v3.2.0.
More Skills