What problem does it solve? AI-generated framework code often relies on stale training data, producing deprecated APIs and outdated patterns that break against current library versions. This Skill grounds every framework-specific implementation decision in official documentation so the code you receive is verifiable and current. ## Core Features & Use Cases - Stack Detection: Reads dependency files like package.json, composer.json, requirements.txt, go.mod, Cargo.toml, or Gemfile to identify exact framework versions before writing code. - Documentation-Grounded Implementation: Fetches the relevant official docs page, follows documented API signatures, avoids deprecated patterns, and treats fetched content as untrusted data to resist prompt injection. - Source Citation: Adds full-URL citations in code comments and conversation, quotes supporting passages, and explicitly flags anything that could not be verified. - Use Case: You are building a form in a React 19 project. The Skill detects React 19.1.0 from package.json, fetches the official useActionState reference, implements the documented pattern instead of a manual useState loading flag, and cites the source so you can verify it. ## Quick Start Ask the agent to implement a framework-specific feature using source-driven development so every pattern is verified against the official docs and cited.
