The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting data from external sources such as Cloudflare D1 (SQL database), KV (Key-Value store), and R2 (Object storage).
Ingestion points: Data is retrieved via env.DB.prepare(), env.KV.get(), and env.BUCKET.get() within server functions (documented in SKILL.md).
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are included in the documented data access patterns.
Capability inventory: The skill uses Bash, Read, Write, and Edit tools. Scripts demonstrate commands for project creation, file manipulation (rm, mv), and deployment (wrangler deploy).
Sanitization: The provided code snippets do not explicitly show sanitization or validation of the data retrieved from external bindings before it might be used in further agent operations.
[EXTERNAL_DOWNLOADS]: The skill references and provides instructions for downloading various third-party resources.
Trusted Sources: It uses npm create cloudflare@latest, which is a tool from Cloudflare, a well-known service provider.
Dependency Installation: The skill instructs the user to install several Node.js packages including @tanstack/react-start, @tanstack/react-router, vite, and wrangler from the npm registry.
[COMMAND_EXECUTION]: The skill includes multiple bash command blocks for project setup, migration, and deployment. These are standard development workflows for the documented framework and tools.

TanStack Start