Skill Eval Preflight

Validate OpenClaw skills during authoring. Use when creating, revising, or preparing a skill for release and you need to scaffold `evals/` files, check readi...

This skill appears coherent and appropriate for authors: it reads SKILL.md and evals/ files and creates eval scaffolding and run artifacts under the target skill directory. Before installing or running: (1) review the included Python scripts yourself (they are small and local) to confirm you trust operations that read/write files in the target directory; (2) run the tools on a copy or a non-production repo if you want to avoid creating run folders in-place; (3) note the scripts do not perform network calls or require credentials, so there is low risk of secret exfiltration. If you need the agent to run this autonomously, remember autonomous invocation is allowed by default—only enable that if you trust the skill and its inputs.

Type: OpenClaw Skill Name: skill-eval-preflight Version: 1.0.0 The skill bundle is a developer utility for scaffolding and validating OpenClaw skill metadata and evaluation files. The Python scripts (e.g., check_eval_readiness.py, run_eval.py, init_eval.py) perform standard file I/O, JSON parsing, and string validation to identify placeholder content and ensure proper directory structure. There is no evidence of malicious intent, network activity, shell execution, or data exfiltration; the code uses only standard libraries and follows the stated purpose of providing an authoring-side preflight check.