PluginEval Core

Self-contained PluginEval quality evaluation engine. Measures 6 dimensions, detects anti-patterns, assigns badges. No external dependencies.

This skill appears coherent and self-contained. Before running it: (1) run in read-only modes first (e.g., --layer1, --anti-patterns, or --auto-fix without --allow-write) to inspect outputs; (2) review the full scripts/eval.py to confirm there are no hidden network calls or LLM API invocations in the portions not shown (Layer 2 mentions an LLM judge — verify it doesn't require external API keys or make outbound requests); (3) run the provided tests in a sandbox; and (4) don't use --allow-write until you've inspected the auto-fix code and are comfortable with changes and backups (the script creates backups in the same skill directory). If you want higher assurance, ask for the remainder of eval.py (the truncated section) to confirm there are no unexpected network or credential accesses.

Type: OpenClaw Skill Name: plugineval-core Version: 1.0.0 The plugineval-core skill bundle is a static analysis utility designed to evaluate and improve the quality of other OpenClaw skills. The primary logic in scripts/eval.py performs heuristic checks on SKILL.md files (e.g., checking for descriptions, triggers, and formatting) and includes an 'auto-fix' feature that can modify files or delete empty references. These potentially destructive actions are protected by a mandatory --allow-write flag and an automatic backup mechanism, and the script lacks any network capabilities, credential access, or obfuscation that would indicate malicious intent.