← Back to Skills Marketplace
143
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install model-pilot
Description
Match task complexity to the right model. Quick heuristic check before expensive tasks — recommends cheaper models when quality won't suffer. Fetches live pr...
Usage Guidance
This skill appears coherent and lightweight: it only recommends models and fetches live pricing. Before installing: (1) confirm you trust the external domains it fetches (e.g., https://z.ai/pricing and search results) since the agent will make web requests when invoked; (2) clarify whether the agent will read your local OpenClaw config (the docs say "check the user's config" but don't state how); (3) note minor metadata mismatches (SKILL.md/version vs. _meta.json and registry version) — not dangerous but worth confirming the published package is the expected release. If uncomfortable, try it first on non-sensitive tasks and verify it only makes the expected pricing and search requests.
Capability Assessment
Purpose & Capability
Name and description (match tasks to cheaper models) align with the SKILL.md instructions: complexity heuristics, live pricing fetches, and cost-estimation formulas. Fetching provider pricing via web_search/web_fetch is expected for this purpose.
Instruction Scope
Instructions stay within scope: they recommend models, estimate cost, and advise not to switch automatically. They instruct the agent to use web_fetch/web_search for live pricing. One small ambiguity: the guide says to "Check the user's config for available aliases" but does not specify how (session API vs. reading config files). The skill does not explicitly instruct reading arbitrary files or credentials.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded. Low install risk.
Credentials
No required environment variables, credentials, or config paths are declared. The runtime instructions also do not request secrets or tokens. Live web lookups are used, which is proportional to the purpose.
Persistence & Privilege
Skill is not forced-always, does not request persistence or extra privileges, and explicitly states it does not persist or switch models automatically.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install model-pilot - After installation, invoke the skill by name or use
/model-pilot - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
Removed static model database. Live pricing via web_fetch. Simplified 3-tier classification. Quick heuristic check.
v1.1.0
Install command now inline for visibility
v1.0.0
Initial release: intelligent model routing with 3-tier task complexity classification, cross-provider model database (Z.ai, OpenAI, Anthropic, Google) with pricing and benchmarks, cost estimation, savings examples, edge case handling, and OpenClaw integration
Metadata
Frequently Asked Questions
What is Model Pilot?
Match task complexity to the right model. Quick heuristic check before expensive tasks — recommends cheaper models when quality won't suffer. Fetches live pr... It is an AI Agent Skill for Claude Code / OpenClaw, with 143 downloads so far.
How do I install Model Pilot?
Run "/install model-pilot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Model Pilot free?
Yes, Model Pilot is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Model Pilot support?
Model Pilot is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Model Pilot?
It is built and maintained by TommoT2 (@tommot2); the current version is v2.0.0.
More Skills