What problem does it solve? Setting up Spec-Driven Development in a project requires manually detecting the tech stack, test tooling, and conventions, then wiring up persistence and a skill registry. This Skill automates that initialization so SDD phases start from accurate, detected project context instead of guesses. ## Core Features & Use Cases - Stack and Tooling Detection: Inspects package.json, go.mod, pyproject.toml, CI, and lint/test configs to identify the real stack, test runner, coverage, linter, type checker, and formatter. - Flexible Persistence Modes: Supports engram, openspec, hybrid, and none modes, writing Engram observations, openspec/config.yaml, or both. - Skill Registry Generation: Builds .atl/skill-registry.md by scanning user-level and project-level skill directories with deduplication rules. - Use Case: A developer starting SDD on an existing repository runs the init phase to detect that pytest with coverage is available, enables strict TDD, and persists testing capabilities plus a registry for downstream /sdd-explore and /sdd-new phases. ## Quick Start Ask the agent to initialize SDD for this project and detect the stack, testing capabilities, and persistence mode.
