Skylv Agent Evaluator

Evaluate AI agent behavior on accuracy, efficiency, clarity, safety, and helpfulness, providing scores, grades, and improvement suggestions.

This package appears to be a local, heuristic-based evaluator (reads a file and applies regex rules). Before installing or using it, note that the SKILL.md claims 'LLM-as-judge' and a different set of evaluation dimensions/weights than the code actually implements — ask the author to explain which implementation is authoritative. If you plan to use it: (1) run it on non-sensitive sample logs in a sandbox to confirm behavior; (2) verify which criteria and weightings are used by inspecting the code (CRITERIA in agent_evaluator.js); (3) if you expect LLM-based scoring, do not trust the current code as-is — it makes no external calls; (4) consider forking or adjusting the script if you need LLM judgement or different metrics. The tool does not request secrets or network access, so the direct security risk is low, but the documentation/implementation mismatch could lead to mistaken trust in its results.

Type: OpenClaw Skill Name: skylv-agent-evaluator Version: 1.0.2 The skill is a utility for evaluating AI agent logs based on predefined metrics like accuracy and safety. The core logic in `agent_evaluator.js` uses simple regex-based scoring and local file reading without any network calls, shell execution, or credential access. The instructions in `SKILL.md` and `README.md` are consistent with the tool's stated purpose and do not contain malicious prompt injections.