← Back to Skills Marketplace
Model Switcher
by
PUASERVICE
· GitHub ↗
· v1.0.2
1059
Downloads
0
Stars
20
Active Installs
4
Versions
Install in OpenClaw
/install model-switcher
Description
Automatically switch between different AI models based on task complexity. Supports all available models in your OpenClaw setup. Triggers when detecting comp...
Usage Guidance
This skill appears to do what it says: detect complexity and call session_status to switch models. Before installing, confirm that your agent platform provides a session_status tool and determine the exact model identifiers it expects (the SKILL.md shows both full model names and shorter tokens — update them to match your environment). Consider adding trigger keywords in other languages if you need that coverage, and set sensible rate-limiting or batching to avoid frequent unnecessary switches. Also verify you trust the custom model endpoints listed (they appear to be custom-hosted model names) since switching will route requests to those models managed by whoever controls them.
Capability Analysis
Type: OpenClaw Skill
Name: model-switcher
Version: 1.0.2
The OpenClaw AgentSkills bundle 'model-switcher' is designed to automatically switch between different AI models (haiku/sonnet) based on task complexity detected in user messages. All instructions in SKILL.md, including model configuration and workflow, are consistent with this stated purpose. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent for harmful activities. The custom model identifiers like `custom-kiro-cli-vipdump-eu-org/claude-haiku-4-5` are used for model selection, not for external communication or exfiltration.
Capability Assessment
Purpose & Capability
Name/description (auto-switching between fast vs powerful models) match the SKILL.md's detection rules and explicit session_status calls to change models. There are no unrelated environment variables, binaries, or installs requested.
Instruction Scope
Instructions are narrowly scoped to detecting keywords and calling the session_status tool to change models. Minor issues: trigger keywords are only provided in Chinese (may miss other languages), and the implementation examples use short model identifiers ("kiro-cli", "haiku", "default") that do not exactly match the full model strings listed earlier (e.g., "custom-kiro-cli-vipdump-eu-org/claude-haiku-4-5"), which is an operational inconsistency but not a security problem. The doc also leaves behavioral choices (how often to switch, batching) to agent discretion; this is functional scope rather than a covert action.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is written to disk or downloaded by an installer, which minimizes install-time risk.
Credentials
No environment variables, credentials, or config paths are requested. The skill does reference custom model names (hosted models) — users should be aware that switching uses whatever models are available in their environment, but the skill itself doesn't request secrets or unrelated credentials.
Persistence & Privilege
always is false and autonomous invocation is allowed (the platform default). The skill does not request persistent system presence or access to other skills' configs. Autonomous invocation combined with no credential access is low risk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install model-switcher - After installation, invoke the skill by name or use
/model-switcher - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Initial release: Auto-switch between haiku and sonnet based on task complexity
v1.0.2
Update summary to remove specific model references
v1.0.1
Remove specific API endpoints, support all models universally
v1.0.0
- Initial release of model-switcher skill.
- Automatically switches between fast (haiku) and powerful (sonnet) models based on detected task complexity.
- Detects complex tasks using Chinese keywords related to analysis, design, optimization, and more.
- Checks current model with session_status before switching.
- Briefly notifies the user when a model switch occurs.
- Intelligent handling to avoid unnecessary switches and maintain context during ongoing complex conversations.
Metadata
Frequently Asked Questions
What is Model Switcher?
Automatically switch between different AI models based on task complexity. Supports all available models in your OpenClaw setup. Triggers when detecting comp... It is an AI Agent Skill for Claude Code / OpenClaw, with 1059 downloads so far.
How do I install Model Switcher?
Run "/install model-switcher" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Model Switcher free?
Yes, Model Switcher is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Model Switcher support?
Model Switcher is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Model Switcher?
It is built and maintained by PUASERVICE (@puaservice); the current version is v1.0.2.
More Skills