The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and TypeScript code snippets. There are no executable scripts, installers, or automation logic that could perform unauthorized actions.- [EXTERNAL_DOWNLOADS]: The skill references external URLs in the documentation, including GitHub and a technical blog (tkdodo.eu). These are provided as informational sources for the code patterns and do not involve remote code execution or automated downloads.- [PROMPT_INJECTION]: The markdown body uses labels like 'CRITICAL' and 'HIGH' to categorize common programming mistakes in React Query implementation. These are technical descriptions of logic bugs and do not represent attempts to override agent instructions or bypass safety filters.

tanstack-query-intent-core-concurrent-optimistic-updates