robots-txt

When the user wants to configure, audit, or optimize robots.txt. Also use when the user mentions "robots.txt," "crawler rules," "block crawlers," "AI crawler...

This skill is internally consistent and low-risk: it only contains prose instructions and needs no installs or credentials. Before installing, note that at runtime it may read project-context files (.claude/project-context.md or .cursor/project-context.md) if present to learn the site URL and indexing goals — remove or sanitize those files if they contain sensitive data you don't want shared. If you plan to audit a live site, the skill does not gain host credentials or make changes itself; provide robots.txt contents or site details explicitly when asked rather than granting broad access to production systems. If you prefer to avoid any automatic local-file reads, disable autonomous invocation for the skill or remove project-context files from the agent environment.

Type: OpenClaw Skill Name: robots-txt Version: 1.1.1 The skill bundle provides standard SEO guidance and instructions for an AI agent to assist users with robots.txt configuration and auditing. It includes technical best practices, crawler-specific strategies (e.g., GPTBot, ClaudeBot), and references to related SEO concepts like indexing and sitemaps. No malicious code, data exfiltration attempts, or harmful prompt injection instructions were found in SKILL.md or _meta.json.