The Agent Skills Directory

[SAFE]: The skill serves as a configuration auditor and security linter for the OpenClaw platform. It instructs the agent to look for potential misconfigurations, deprecated features, and security risks in the user's workspace files.
[COMMAND_EXECUTION]: The skill recommends using the platform-native CLI tool openclaw doctor --fix to remediate configuration issues discovered during validation. This is a standard administrative function within the platform's ecosystem.
[EXTERNAL_DOWNLOADS]: References the docs-research skill to fetch updated configuration schemas and documentation from official sources, including well-known web search and scraping services (e.g., Exa, Perplexity, Firecrawl).
[DATA_EXPOSURE]: While the skill processes potentially sensitive configuration files like openclaw.json, it proactively includes checks for hardcoded credentials (bot tokens) and explicitly instructs the agent to recommend secure alternatives such as SecretRef patterns and environment variables.

config-validation