What problem does it solve? Setting up spec-driven development (SDD) in a project requires manually detecting the tech stack, test tooling, and conventions, then wiring up persistence and registries. This Skill automates that initialization so AI agents start with accurate project context. ## Core Features & Use Cases - Stack and Tooling Detection: Inspects package.json, pyproject.toml, go.mod, CI configs, and lint/test setups to identify the real stack, test runner, coverage, linter, and formatter without guessing. - Flexible Persistence Modes: Supports engram, openspec, hybrid, and none modes, writing context to Engram observations, openspec/config.yaml, or both. - Skill Registry Generation: Scans user-level and project-level skill directories to build .atl/skill-registry.md as an index of available skills. - Use Case: When starting SDD on a new repository, run the init phase to detect that the project uses Vitest and pytest, enable strict TDD mode, persist testing capabilities, and produce a registry for downstream phases like /sdd-explore or /sdd-new. ## Quick Start Ask the agent to initialize SDD in this project and detect the stack, testing tools, and persistence mode.
