← Back to Skills Marketplace
omguptaind

Hudl AI Openclaw Model Switch

by Om Gupta · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
291
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install hudl-model-switch
Description
Switch between LLM models on the Huddle01 GRU gateway. Use this skill whenever the user mentions switching models, changing models, upgrading, downgrading, "...
README (SKILL.md)

hudl-model-switch

Switch the active LLM model for this OpenClaw agent via the Huddle01 GRU gateway.

Non-negotiable rules

  • This skill only applies to the hudl provider backed by gru.huddle01.io.
  • The target model value in config must always be hudl/\x3Cmodel-id>.
  • Never edit JSON manually for model switching. Always use scripts/switch-model.sh.
  • Never modify provider wiring during a switch (models.providers.hudl.baseUrl, apiKey, and other unrelated keys stay unchanged).
  • Treat any post-switch mismatch, missing model field, or non-hudl/ result as a hard failure. Do not restart in that state.
  • For status/reporting, the active agent model is the source of truth. agents.defaults.model.primary is only a default and may be stale.

Prerequisites

This skill only works when the OpenClaw config has a hudl provider pointing at gru.huddle01.io. If the provider is missing or the baseUrl is different, stop and tell the user this skill requires the Huddle01 GRU gateway.

Step-by-step

On any switch/change request

Step 1: Validate provider + config path (required)

Run:

bash \x3Cskill_dir>/scripts/validate.sh
  • Exit 0: continue.
  • Exit 1: stop. Show the exact validation error and tell the user no config changes were made.
  • Validation resolves config in this order: OPENCLAW_CONFIG, ~/.openclaw/config.json, ~/.openclaw/openclaw.json.
  • The provider check is strict: the hudl provider must exist, apiKey must be present, and baseUrl must point at host gru.huddle01.io.

Step 2: Resolve the exact target model ID (required)

Use \x3Cskill_dir>/references/models.md to map user intent to a canonical model.

Normalization rules:

  • If the resolved model does not start with hudl/, prepend hudl/.
  • If the user already supplied hudl/..., keep it unchanged.
  • Never write a non-hudl/ model into config.
  • Reject empty model IDs, hudl/ by itself, or values with spaces.
  • For unknown models, still normalize to hudl/\x3Cuser-value> and warn clearly that the model must exist on GRU or requests will fail.

Ambiguity rules:

  • If request is ambiguous (for example "claude" could be Opus/Sonnet/Haiku), choose the catalog default alias mapping (currently hudl/claude-opus-4.6) and state what was chosen.
  • If the user asks for a specific variant, obey that exact variant.

Step 3: Capture current state before mutation (required)

Read and note current values so the response can show before/after:

  • active agent model (agents.list[*].model.primary, preferring agent id: "main")
  • default model (agents.defaults.model.primary)
  • If .agents.list has no entries, stop. This skill is for switching an active agent model, so a config with no agent entries is not a valid target.
  • When active and default differ, describe that as a mismatch and treat the active agent model as the model currently in use.

Step 4: Switch model via script (required)

Run:

bash \x3Cskill_dir>/scripts/switch-model.sh \x3Chudl-model-id>

switch-model.sh is the source of truth and must be used instead of manual edits.

Expected behavior from script:

  • Updates agents.defaults.model.primary
  • Updates active agent model (agents.list[*].model.primary, preferring id: "main", otherwise first agent)
  • Normalizes models.providers.hudl.models[*].id so every catalog ID is hudl/...
  • Ensures the target model exists in models.providers.hudl.models
  • Preserves unrelated configuration
  • Fails if the resulting active/default model fields are empty, not hudl/-prefixed, or do not exactly match the requested target
  • Fails if the provider model catalog still contains non-hudl/ IDs or is missing the target model

Failure handling:

  • If script fails, stop and show the script error.
  • Do not "repair" the config manually inside the skill. If the script does not leave config in a valid final state, stop and surface the failure.

Step 5: Verify post-switch values before restart (required)

Confirm both fields now point to the normalized target model and both are hudl/....

  • If aligned: continue.
  • If not aligned: report mismatch and stop. Do not restart.

Step 6: Restart + report final state (required)

Before restart, tell the user:

  • restart is starting now
  • service may take a couple of minutes to come back
  • you will confirm applied model values after restart

Run:

openclaw restart

After restart, report:

  • restart completion status
  • previous active/default model values
  • new active/default model values
  • alignment status (aligned or mismatch)
  • exact final model ID in use
  • provider catalog normalization status

On "what model am I on" / "current model"

  1. Run validation (scripts/validate.sh).
  2. Read the resolved config (config.json or openclaw.json).
  3. Report:
    • current active agent model (agents.list[*].model.primary, prefer id: "main")
    • current default model (agents.defaults.model.primary)
    • whether they are aligned
    • whether each value is correctly hudl/-prefixed
    • config path used for the check

Reporting rules:

  • Do not say "current model is X" based only on agents.defaults.model.primary.
  • If agents.list[*].model.primary and agents.defaults.model.primary differ, say the active agent model is currently in use and the default is stale/misaligned.
  • When the user asks to "show on file" or "prove it from config", show both paths and values:
    • agents.list[main-or-first].model.primary
    • agents.defaults.model.primary

No restart is needed for read-only status checks.

Example exchanges

Switch to Opus:

User: switch to opus
Agent: Checking GRU gateway config... verified.
Agent: Resolved target model: hudl/claude-opus-4.6.
Agent: Current models -> active: hudl/minimax-m2.5, default: hudl/minimax-m2.5.
Agent: Running switch script... success.
Agent: Provider model catalog normalized and includes hudl/claude-opus-4.6.
Agent: Restarting gateway now; it may take a couple minutes.
Agent: Restart complete. Active: hudl/claude-opus-4.6, default: hudl/claude-opus-4.6 (aligned).

Mismatched config on status check:

User: what model am I on?
Agent: Config path: /home/ubuntu/.openclaw/openclaw.json
Agent: Active model in use: hudl/minimax-m2.5 (from agents.list[id=main].model.primary)
Agent: Default model: gpt-4.1 (from agents.defaults.model.primary)
Agent: Status: mismatch. The gateway is currently using hudl/minimax-m2.5; the default value is stale and should not be reported as the live model.

No hudl provider:

User: switch to opus
Agent: (validate.sh failed)
Agent: This skill requires the Huddle01 GRU gateway (hudl provider with baseUrl gru.huddle01.io) in your OpenClaw config. No changes were made.

Unknown model:

User: switch to deepseek-r2
Agent: Heads up: deepseek-r2 is not in the known catalog. I will set hudl/deepseek-r2; requests will fail unless that model exists on your GRU gateway.
Agent: Switching to hudl/deepseek-r2...
Usage Guidance
This skill appears to implement what it claims (switching the active model via the Huddle01 GRU gateway), but there are a few things you should do before installing or using it: - Verify the source: the registry 'Source' is unknown and there is no homepage; prefer code from a known/trusted repository. Inspect the included scripts yourself. - Backup your OpenClaw config(s) (~/.openclaw/config.json and ~/.openclaw/openclaw.json) before running this skill — the scripts edit these files in-place. Use version control or a copy. - Ensure prerequisites are present: install jq and confirm the openclaw CLI is available (the metadata omitted these runtime requirements). Validate that validate.sh runs and exits 0 on your system before attempting a switch. - Confirm the hudl provider and apiKey in your config: validate.sh will refuse to run if the hudl provider or apiKey is missing; the script reads that apiKey from local files but does not send it anywhere during validation. - Test cautiously: run validate.sh manually, then consider running switch-model.sh against a disposable/test config or after backing up the real config; the scripts have no dry-run mode and will perform changes and require a restart. - Review restart impacts: openclaw restart will bring the agent down and back up; plan for potential disruption. If you want higher assurance, ask the skill author for a canonical repository/homepage, or request that the registry metadata be corrected to list required binaries (jq, openclaw) and any expected environment variables (OPENCLAW_CONFIG if used).
Capability Analysis
Type: OpenClaw Skill Name: hudl-model-switch Version: 1.0.3 The skill bundle is designed to automate LLM model switching for OpenClaw agents using the Huddle01 GRU gateway. It employs local shell scripts (scripts/validate.sh and scripts/switch-model.sh) to validate the provider configuration and use 'jq' to safely mutate the agent's config.json. The logic includes strict input validation (regex for model IDs) and state verification before and after changes. No evidence of data exfiltration, malicious prompt injection, or unauthorized network activity was found; the administrative actions (config modification and service restart) are transparent and aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The skill's name, README, SKILL.md, and scripts consistently describe switching the agent's model via the Huddle01 GRU gateway; the scripts validate the provider, update the OpenClaw config, and restart the service — all coherent with the stated purpose. However, the registry metadata claims 'required binaries: none' and 'required env vars: none' even though the scripts require 'jq' and assume the 'openclaw' CLI is available for restart. This metadata omission is inconsistent with the skill's actual needs.
Instruction Scope
SKILL.md explicitly instructs the agent to run the included validate.sh and switch-model.sh scripts, read and update OpenClaw config files (~/.openclaw/config.json or openclaw.json), and run 'openclaw restart'. Those actions are within the scope of model-switching. The instructions do not attempt to read unrelated system secrets or other skill configs. They do modify user configuration files and perform a service restart — expected but intrusive operations that should be noted.
Install Mechanism
This is instruction-only with included scripts (no download/extract install step). There is no network fetch during install in the spec. The lack of an install spec is lower risk, but the README includes optional clone/install instructions from GitHub/ClawHub; verify sources before using those commands.
Credentials
The skill declares no required env vars or binaries, yet validate.sh and switch-model.sh require 'jq' and use OPENCLAW_CONFIG optionally; the SKILL/README also expect an accessible 'openclaw' command for restart. validate.sh also requires that the hudl provider have an apiKey present in the OpenClaw config (it reads sensitive config data from local files). While reading/writing the OpenClaw config is necessary for changing models, the registry metadata should have listed jq and the need to allow restarts. The skill does not itself request external credentials via env vars, but it will read the API key from your local OpenClaw config file — ensure that is acceptable.
Persistence & Privilege
The skill does not request 'always: true' and is user-invocable only. It modifies the user's OpenClaw config files and issues a restart of the service — legitimate for this purpose, but potentially disruptive. It does not attempt to modify other skills' configs or request persistent system-wide privileges beyond editing OpenClaw config files and restarting OpenClaw.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install hudl-model-switch
  3. After installation, invoke the skill by name or use /hudl-model-switch
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Initial release with 30+ models across OpenAI, Anthropic, Google, DeepSeek, xAI, Qwen, MiniMax, Moonshot, Meta, Mistral
v1.0.2
Initial release with 30+ models across OpenAI, Anthropic, Google, DeepSeek, xAI, Qwen, MiniMax, Moonshot, Meta, Mistral
v1.0.1
Initial release with 30+ models across OpenAI, Anthropic, Google, DeepSeek, xAI, Qwen, MiniMax, Moonshot, Meta, Mistral
v1.0.0
Initial release with 30+ models across OpenAI, Anthropic, Google, DeepSeek, xAI, Qwen, MiniMax, Moonshot, Meta, Mistral
Metadata
Slug hudl-model-switch
Version 1.0.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Hudl AI Openclaw Model Switch?

Switch between LLM models on the Huddle01 GRU gateway. Use this skill whenever the user mentions switching models, changing models, upgrading, downgrading, "... It is an AI Agent Skill for Claude Code / OpenClaw, with 291 downloads so far.

How do I install Hudl AI Openclaw Model Switch?

Run "/install hudl-model-switch" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Hudl AI Openclaw Model Switch free?

Yes, Hudl AI Openclaw Model Switch is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Hudl AI Openclaw Model Switch support?

Hudl AI Openclaw Model Switch is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Hudl AI Openclaw Model Switch?

It is built and maintained by Om Gupta (@omguptaind); the current version is v1.0.3.

💬 Comments