suggest-features

Feature discovery from a codebase analyzes build files, README, source layout, and recent git history to identify missing or partially-implemented capabilities. It produces a ranked list of feature proposals with rationale tied to concrete code evidence and implementation notes.

Gap analysis for product discovery inspects existing code patterns and modules to find absent or incomplete user-facing and developer-experience features. It prioritizes these opportunities by impact, grounding suggestions in evidence like missing integration tests or authentication stubs.

Feature suggestion analysis supports common language ecosystems including Java/Kotlin, JavaScript/Node, Python, and Rust. It reads build and manifest files from these environments to determine frameworks and important modules before generating ranked feature proposals.

Evidence-backed feature proposals are generated by reading your repository's source code, README, and commit history. The analysis ties rationale directly to concrete code evidence, such as recommending an authentication plugin when partial auth stubs lack integration tests, and includes suggested next steps.

Project analysis inspects your repository's source layout and documentation to find incomplete features, prioritizing them by impact. It examines manifest files and recent git history to produce a ranked list of high-value feature suggestions aligned with your project's domain.

Automated feature discovery relies on existing code patterns, manifest files, and git history to suggest features, meaning highly domain-specific or entirely novel capabilities may be missed. It works best when common language ecosystems like Python, Node, Java, or Rust are used.