← Back to Skills Marketplace
78
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-model-switcher
Description
Switch the OpenClaw default model safely. Triggers: switch model, change model, 切换模型, 换模型, switch to XX model. Use when the user wants to change the default...
Usage Guidance
This skill appears to do what it says: it edits ~/.openclaw/openclaw.json (or the path you pass), backs up to ~/.openclaw/config_backups, restarts the local 'openclaw' gateway, and rolls back on failure. Before running: (1) inspect the bundled script you will invoke (prefer scripts/model_switch.py which supports --config and the OPENCLAW_CONFIG env var); (2) ensure the 'openclaw' CLI on your PATH is the expected trusted binary (restart/status commands are invoked); (3) run a dry-run first to confirm behavior; (4) verify backups are created in ~/.openclaw/config_backups and test restoring manually if needed. The only notable issue is the duplicate files: the top-level script hardcodes the config path while the script under scripts/ honors overrides — be aware which file your agent will execute.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-model-switcher
Version: 1.0.0
The model-switcher skill is designed to update the default AI model in the OpenClaw configuration file (~/.openclaw/openclaw.json). The provided Python scripts (model_switch.py) implement a safe workflow including configuration backup, targeted JSON modification, service restart via the 'openclaw' CLI, and automatic rollback if the service fails to restart. No evidence of data exfiltration, unauthorized shell execution, or malicious prompt injection was found; the script's use of subprocess.run is restricted to hardcoded service commands and avoids shell injection risks.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, README, and the included scripts all focus on the same task: validate a model, backup ~/.openclaw/openclaw.json, update agents.defaults.model.primary, restart the OpenClaw gateway, health-check, and rollback on failure. No unrelated services, credentials, or binaries are requested.
Instruction Scope
Runtime instructions explicitly read the OpenClaw config, modify only agents.defaults.model.primary, and restart the gateway — all within the stated purpose. A minor inconsistency: README and scripts/supporting file (scripts/model_switch.py) honor OPENCLAW_CONFIG / --config, but the top-level model_switch.py hardcodes ~/.openclaw/openclaw.json (does not read OPENCLAW_CONFIG). This can cause surprising behavior if a user expects the env/config override to apply to both files. Otherwise the instructions do not instruct reading unrelated files or transmitting data externally.
Install Mechanism
No install spec; skill is instruction-only with bundled scripts. There are no downloads, third-party package installs, or archive extraction steps. The scripts run local filesystem operations and call the local 'openclaw' CLI — expected for this purpose.
Credentials
The skill does not require credentials or sensitive environment variables. README documents an optional OPENCLAW_CONFIG env var (reasonable). The only env-related inconsistency is that one included script honors OPENCLAW_CONFIG while the other ignores it; this is a usability issue but not a credential or exfiltration concern.
Persistence & Privilege
Skill is not always-enabled, is user-invocable, and does not request elevated or persistent privileges beyond modifying the user's OpenClaw config and restarting the local gateway (which is necessary for the stated function). It does not modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-model-switcher - After installation, invoke the skill by name or use
/openclaw-model-switcher - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Safe model switching with backup and auto-rollback, standalone script and OpenClaw skill support
Metadata
Frequently Asked Questions
What is OpenClaw Model Switcher?
Switch the OpenClaw default model safely. Triggers: switch model, change model, 切换模型, 换模型, switch to XX model. Use when the user wants to change the default... It is an AI Agent Skill for Claude Code / OpenClaw, with 78 downloads so far.
How do I install OpenClaw Model Switcher?
Run "/install openclaw-model-switcher" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw Model Switcher free?
Yes, OpenClaw Model Switcher is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OpenClaw Model Switcher support?
OpenClaw Model Switcher is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw Model Switcher?
It is built and maintained by Lv-Yezhen (@lv-yezhen); the current version is v1.0.0.
More Skills