← Back to Skills Marketplace
Trails - pay with any token from any chain
by
JamesLawton
· GitHub ↗
· v1.0.0
1879
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install trails
Description
Integrate Trails cross-chain infrastructure — Widget, Headless SDK, or Direct API
Usage Guidance
This skill appears to do what it says: it helps you integrate Trails by examining your project, recommending Widget/Headless/API approaches, and producing code. Before installing or using it, consider: 1) the skill will look for API keys in your project and environment — only allow access if you trust the agent and do not want secrets scanned or exposed; 2) follow the docs' guidance about using server-side (TRAILS_API_KEY) vs client-side (NEXT_PUBLIC_TRAILS_API_KEY) keys — never publish server keys in client code or commit them to source control; 3) verify you trust the Trails endpoints (docs.trails.build, dashboard.trails.build, api.trails.build) and the package names the snippets reference (e.g., @0xtrails/trails); 4) prefer adding API keys to environment variables on the server, test calldata flows on testnets first, and avoid pasting full keys into chat unless you explicitly intend to share them. If you want extra assurance, ask the skill author for a signed repository link or review the upstream GitHub release/source code before using their npm packages.
Capability Analysis
Type: OpenClaw Skill
Name: trails
Version: 1.0.0
The skill instructs the AI agent to read environment variables and `.env` files (e.g., `TRAILS_API_KEY`, `NEXT_PUBLIC_TRAILS_API_KEY`) from the user's project, as detailed in `SKILL.md` and `README.md`. While this is presented as necessary for the skill's stated purpose of integrating the Trails API (api.trails.build), granting an AI agent direct access to local environment configurations is a high-risk capability. This could be exploited via prompt injection to exfiltrate other sensitive environment variables or local files. Additionally, the skill instructs the agent to install dependencies without version pins (`@0xtrails/trails`, `@0xtrails/trails-api`), which introduces a supply chain risk.
Capability Assessment
Purpose & Capability
The name, description, docs, and code snippets all consistently implement a Trails integration assistant (Widget, Headless SDK, Direct API). One small mismatch: the registry metadata declares no required environment variables, but the SKILL.md and docs repeatedly instruct the agent to look for and use TRAILS_API_KEY / NEXT_PUBLIC_TRAILS_API_KEY. That difference is minor but worth noting (the skill doesn't force a credential at install time, but its runtime behavior expects you to provide one).
Instruction Scope
The runtime instructions explicitly tell the agent to scan the project for an API key (search .env files, environment variables, and config files) before generating integration code. That behavior is coherent with the goal (the skill must know whether an API key exists and whether it is client- or server-side). It does mean the agent will be directed to access workspace files and environment variables, which are sensitive — appropriate here but worth the user's awareness.
Install Mechanism
No install spec is provided (instruction-only skill with embedded docs and code snippets). The included code samples reference npm/pnpm packages (e.g., @0xtrails/trails, @0xtrails/trails-api) and official-looking endpoints (api.trails.build, docs.trails.build). There are no downloads from unknown URLs, no extract/install operations, and no obfuscated installers.
Credentials
The skill does not declare required env vars in the registry metadata, but the documentation and SKILL.md legitimately instruct users to supply TRAILS_API_KEY or NEXT_PUBLIC_TRAILS_API_KEY for server/client flows. That credential request is proportionate to the service (Trails API). The docs also correctly point out the difference between server-only keys and client-exposed keys (NEXT_PUBLIC_ prefix). There are no demands for unrelated secrets or multi-service credentials.
Persistence & Privilege
The skill is not configured as always:true and does not request persistent modification of other skills or system-wide settings. disable-model-invocation is false (normal). It acts as an on-demand integration helper and provides guidance/code snippets only.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install trails - After installation, invoke the skill by name or use
/trails - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Trails integration skill for native cross-chain interactions and enabling agents to execute any onchain transaction seamlessly.
Metadata
Frequently Asked Questions
What is Trails - pay with any token from any chain?
Integrate Trails cross-chain infrastructure — Widget, Headless SDK, or Direct API. It is an AI Agent Skill for Claude Code / OpenClaw, with 1879 downloads so far.
How do I install Trails - pay with any token from any chain?
Run "/install trails" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Trails - pay with any token from any chain free?
Yes, Trails - pay with any token from any chain is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Trails - pay with any token from any chain support?
Trails - pay with any token from any chain is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Trails - pay with any token from any chain?
It is built and maintained by JamesLawton (@jameslawton); the current version is v1.0.0.
More Skills