The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill identifies and retrieves documentation from official sources within the TanStack ecosystem.
Evidence: Documentation and raw repository links such as https://tanstack.com/router/latest/docs/ and https://raw.githubusercontent.com/TanStack/router/main/docs/.
[COMMAND_EXECUTION]: The skill provides commands for project initialization and development workflows using standard package management tools.
Evidence: The project setup command bunx @tanstack/cli@latest create --router-only in references/setup-route-trees.md.
[PROMPT_INJECTION]: The skill operates on user-provided application source code, which creates a vulnerability surface for indirect prompt injection.
Ingestion points: The agent is instructed to read local route files, configuration files, and package metadata (src/routes/**, router.tsx, package.json).
Boundary markers: The skill does not provide instructions for the agent to use specific delimiters or ignore-embedded-instruction markers when processing external code.
Capability inventory: The skill includes instructions for route tree generation, type checking, and test execution, though it is primarily focused on code analysis and planning.
Sanitization: There are no defined procedures for escaping or validating the content of ingested source files before they are processed by the agent.

tanstack-router