The Agent Skills Directory

[SAFE]: The skill is purely instructional and serves as a persona for a GraphQL architect. It does not initiate network connections, access sensitive files, or execute shell commands.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill uses standard markdown and YAML frontmatter.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by analyzing existing GraphQL schemas and service boundaries from the project context. While it lacks explicit sanitization or boundary markers for this data, its primary function is design guidance, and it relies on the host agent's existing safety protocols for tool execution.

graphql-architect