Generate a living technical specification from a feature idea. Defines API contracts, database schemas, user stories with Given/When/Then acceptance criteria, UI hierarchy, security rules, and test requirements.

Transform a rough idea into a comprehensive implementation plan. Two-stage process: improve the prompt via codebase reconnaissance, then generate a detailed phased plan with atomic checkboxes, file paths, and signatures.

Comprehensive codebase health assessment across 5 quantitative dimensions: concept scattering, module depth vs. width, test health, coupling risk, and AI-agent readability. Produces a letter-grade scorecard.

Implement a feature using strict test-driven development. Enforces one-test-at-a-time discipline: write failing test (red), minimal code to pass (green), refactor, repeat. Catches regressions after every step.

Commit and push all uncommitted changes. Discovers modified and untracked files, generates diffs, drafts a descriptive commit message with bullet points, and presents it for approval before committing and pushing.

Audit a completed implementation plan against the actual codebase. Generates a tailored audit prompt, then verifies planned vs. actual — checking for missing implementations, broken integrations, and security gaps.

AI assistant configured for software engineers. TDD discipline, architecture-first planning, vertical slicing, and codebase health auditing.

Complete Snippbot setup for software engineers. Idea interrogation, spec generation, implementation planning, vertical slicing, strict TDD, architecture auditing, and smart git workflows — a full development lifecycle in one install.

Decompose a spec or plan into independently shippable vertical slices. Each slice cuts through all layers (DB, backend, API, frontend). Starts with a tracer bullet, builds a dependency graph, and creates GitHub issues.

Commit and push only files modified by the AI agent across the current session. Scans the conversation transcript to identify edited files and cross-references with git status to detect prior session changes.

Rigorous structured interview to stress-test an idea before building. Conducts themed rounds (intent, users, data, edges, integration) grounded in codebase reality. Produces a Decision Record.