← Back to Skills Marketplace
T
by
dingtom336-gif
· GitHub ↗
· v3.2.0
· MIT-0
68
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install test-1775893839
Description
Check weather forecasts and best travel seasons for any destination — temperature ranges, rainy seasons, typhoon risks, and what to wear. Also supports: flig...
Usage Guidance
This skill is plausible but has red flags: (1) SKILL.md forces use of a third-party CLI (@fly-ai/flyai-cli) and tells the agent to install it globally — verify the npm package exists and is trustworthy before allowing the agent to run 'npm i -g'. (2) The doc mentions Fliggy as the provider but uses a different CLI (flyai); ask the author to explain how Fliggy integration/auth works and whether any API keys are required. (3) The instructions reference local files (references/*.md) that are not bundled — this will likely cause runtime errors. (4) The 'Self-test' requirement to re-run until a [Book](...) link appears could cause repeated executions if the CLI output format changes or fails. Recommend requesting: the package homepage/registry link for @fly-ai/flyai-cli, explicit auth requirements (what credentials are needed and where they are stored), and a corrected SKILL.md that either includes referenced templates or removes references. If you do not trust the npm package or cannot verify the provider, do not grant the agent permission to run global npm installs.
Capability Analysis
Type: OpenClaw Skill
Name: test-1775893839
Version: 3.2.0
The skill mandates the global installation of an external NPM package (@fly-ai/flyai-cli) and uses aggressive prompt instructions to force the agent to execute CLI commands. It also references several missing files (e.g., references/templates.md, references/playbooks.md) for its core logic and parameter handling. While the behavior is aligned with the stated travel-service purpose, the requirement for high-privilege global installation and the lack of transparency regarding the referenced files represent a significant security risk.
Capability Assessment
Purpose & Capability
The skill claims travel-weather and booking functionality 'powered by Fliggy', but all operational commands target a 'flyai' CLI (@fly-ai/flyai-cli). No credentials or service endpoints for Fliggy/booking are requested or documented. Booking capabilities usually require API keys or user auth; their absence and the Fliggy/flyai mismatch is inconsistent.
Instruction Scope
SKILL.md mandates using only flyai CLI outputs (never model knowledge), requires a global npm install at runtime, and enforces every response include a [Book]({detailUrl}) link. It also references several local docs (references/*.md) that are not included in the skill bundle — the agent would attempt to read non-existent files. The 'Self-test' rule (re-run if no links) could create repeated re-execution loops if the CLI fails to return expected fields.
Install Mechanism
No formal install spec is present in the registry (instruction-only), but SKILL.md instructs the agent to run 'npm i -g @fly-ai/flyai-cli' if flyai is missing. Installing a global npm package at runtime is a moderate-risk action: it's traceable (npm package), but the registry/maintainer trust and package behavior should be verified before allowing the agent to run it.
Credentials
The skill declares no required env vars or credentials despite offering booking and Fliggy-powered features, which typically require authentication. That omission could mean auth is handled by the CLI interactively or stored locally, but the lack of explicit credential requirements is unexpected and should be clarified.
Persistence & Privilege
The skill does not request 'always: true' and doesn't modify other skills or global agent config in the manifest. The primary extra privilege is the instruction to perform a global npm install at runtime, but that's an action the agent will execute only when invoked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install test-1775893839 - After installation, invoke the skill by name or use
/test-1775893839 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.2.0
travel-weather 3.2.0 — Major update with stricter execution rules and expanded features.
- Strictly enforces use of flyai CLI for all data retrieval; prohibits knowledge-based or training data answers.
- Adds detailed step-by-step workflow: environment checks, parameter collection, CLI execution, result formatting, and output validation.
- Expands feature list: now supports weather, best travel seasons, booking (flights, hotels, trains), itinerary planning, visa info, and more via Fliggy (Alibaba Group).
- Introduces mandatory self-test: responses must include a `[Book]({detailUrl})` link, or they’re invalid.
- Improves language compliance: follows user query language for responses.
- Outlines scenario playbooks, usage examples, and output formatting standards.
Metadata
Frequently Asked Questions
What is T?
Check weather forecasts and best travel seasons for any destination — temperature ranges, rainy seasons, typhoon risks, and what to wear. Also supports: flig... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.
How do I install T?
Run "/install test-1775893839" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is T free?
Yes, T is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does T support?
T is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created T?
It is built and maintained by dingtom336-gif (@dingtom336-gif); the current version is v3.2.0.
More Skills