Model-Selector

A powerful model routing skill that analyzes query intent and cost-efficiency to select the optimal LLM (Elite/Balanced/Basic) before execution.

This skill appears to do what it claims (choose a model tier) but has a few red flags you should consider before installing: - Code/instruction mismatch: SKILL.md references get_optimal_model and analyze_and_route, but the code provides ModelRouter.route(). Confirm the actual tool interface the agent will call and update the README or code so they match. - Local logging: It writes query_history.json with users' queries. If prompts may contain secrets or sensitive data, disable or audit this logging, restrict file permissions, or store history encrypted/ephemeral. - Unused/large dependencies: requirements.txt includes litellm and heavy ML libs (torch, sentence-transformers). If you install dependencies, do so in an isolated environment (venv/container) and consider trimming unused packages. - Minor bugs: The code uses torch.* inside ModelRouter.route but does not import torch at the top-level; running with semantic encoder enabled may raise a NameError. Test in a safe environment before trusting in production. If you want to proceed: run the skill in an isolated sandbox, inspect and clean up query_history.json, reconcile SKILL.md and code function names, and verify you understand where and how any later 'refine' step would send data (avoid sending raw history to third-party LLMs unless you have consent and appropriate safeguards). If you prefer, ask the publisher for a fixed version that removes logging by default, aligns interface names, and documents exactly how refinement would be performed.

Type: OpenClaw Skill Name: model-selector Version: 1.0.0 The OpenClaw skill 'Semantic Model Orchestrator' is designed to route LLM queries based on intent and cost-efficiency. The code in `scripts/model_router.py` and `scripts/train_router.py` implements this functionality, including a 'rolling adjustment' feature that logs user queries and their assigned tiers to a local file (`query_history.json`). This local logging is explicitly for refining intent keywords and is not indicative of data exfiltration. No evidence of malicious intent, such as unauthorized network calls, arbitrary code execution, credential theft, or prompt injection against the agent, was found. All dependencies listed in `scripts/requirements.txt` are standard for the described functionality.