The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using npx @tanstack/cli. These commands are used for initializing projects, compiling add-ons, and querying metadata. This is standard behavior for a development-oriented CLI tool.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of the @tanstack/cli package via npx. It also includes an example of scaffolding an application using a remote GitHub template (https://github.com/acme/tanstack-template). These operations target well-known technology providers or serve as generic placeholders for user configuration.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by fetching and processing external content from remote documentation and metadata services.
Ingestion points: Commands like tanstack doc and tanstack search-docs in references/guides/tanstack-cli-query-docs-library-metadata-bf917a48.md fetch content from external documentation servers.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts within the fetched documentation content.
Capability inventory: The agent has capabilities for file system operations and further command execution via the CLI tool.
Sanitization: No specific sanitization or validation of the remote documentation content is described before it is presented to the agent. However, these sources are authoritative within the TanStack ecosystem.

tanstack-cli