← Back to Skills Marketplace
887
Downloads
2
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install models
Description
Choose AI models for coding, reasoning, and agents with cost-aware, task-matched recommendations.
Usage Guidance
This skill is coherent and low-risk: it's a bundle of best-practice guidelines for choosing models and doesn't require credentials or install anything. If you want to be extra cautious, note that the skill is model-invocable by default (it may be used autonomously); if you prefer explicit use only, set disableModelInvocation or require user invocation. Also verify the recommendations fit your specific cost/performance constraints before relying on them operationally.
Capability Analysis
Type: OpenClaw Skill
Name: models
Version: 1.0.0
The skill bundle contains a metadata file and a markdown document. The `SKILL.md` provides detailed, high-quality advice on AI model selection, covering topics like cost, task matching, and practical guidelines. There are no executable code blocks, shell commands, network calls, or any form of prompt injection attempts. The content is purely informational and fully aligned with its stated purpose, exhibiting no malicious or suspicious indicators.
Capability Assessment
Purpose & Capability
Name/description ('Models' for cost- and task-aware model recommendations) matches the SKILL.md content. There are no unexpected required binaries, env vars, or config paths.
Instruction Scope
SKILL.md contains high-level rules and pragmatic guidance for choosing models; it does not instruct the agent to read system files, access credentials, call external endpoints, or perform unrelated actions.
Install Mechanism
No install spec and no code files — nothing is downloaded or written to disk. This is the lowest-risk model (instruction-only).
Credentials
The skill declares no environment variables, credentials, or config paths. No sensitive secrets are requested or needed for the stated purpose.
Persistence & Privilege
No 'always: true' flag and no install; however disableModelInvocation is not set, so the model could invoke the skill autonomously by default. For a non-sensitive guidance-only skill this is generally acceptable, but you can require explicit invocation if you prefer.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install models - After installation, invoke the skill by name or use
/models - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Models?
Choose AI models for coding, reasoning, and agents with cost-aware, task-matched recommendations. It is an AI Agent Skill for Claude Code / OpenClaw, with 887 downloads so far.
How do I install Models?
Run "/install models" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Models free?
Yes, Models is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Models support?
Models is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Models?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.
More Skills