sdd-init

Initializes SDD project context, testing capabilities, and skill registry with configurable persistence modes.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/Alountk/Bloodbowl_Project --skill sdd-init-alountk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-init
Source: https://github.com/Alountk/Bloodbowl_Project/tree/main/.opencode/skills/sdd-init
Command: npx skills add https://github.com/Alountk/Bloodbowl_Project --skill sdd-init-alountk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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 bootstrap 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. - Configurable persistence modes: Supports engram, openspec, hybrid, and none modes, writing Engram observations and/or openspec config files accordingly. - Strict TDD resolution and skill registry: Resolves strict_tdd from markers, config, or runner detection, and builds .atl/skill-registry.md by scanning user and project skill directories. - Use Case: A developer starting SDD on an existing Next.js repository runs the init phase to detect Vitest and Playwright, persist testing capabilities, and generate a registry of available skills for later phases. ## Quick Start Ask the agent to initialize SDD in this project with hybrid persistence mode.

Frequently Asked Questions about sdd-init

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I initialize SDD in an existing project?▼

Run the sdd-init phase, which inspects files like package.json, go.mod, and pyproject.toml to detect the stack and test tooling. It then persists context and testing capabilities according to the chosen mode and builds a skill registry.

What persistence modes does SDD initialization support?▼

Four modes are supported: engram saves context to Engram only, openspec writes openspec config files only, hybrid does both, and none returns detected context without writing SDD artifacts. The mode is selected via the mode input.

How is strict TDD mode determined during initialization?▼

Strict TDD is resolved from an explicit agent marker or openspec config first. If none exists but a test runner is detected, it defaults to true; with no test runner it is set to false with an explanation.

What happens if openspec already exists in the project?▼

The skill reports what already exists and asks before updating it, rather than overwriting existing openspec files. This prevents accidental loss of prior SDD configuration.

What does the skill registry scan include?▼

The scan covers user-level and project-level skill directories across many agent platforms, skipping sdd-*, _shared, and skill-registry entries. It deduplicates by name, preferring project-level skills, and writes the index to .atl/skill-registry.md.