sdd-authoring

Automate formal SPEC.md authoring for AI-native SDD pipelines.

86|9|Updated Jun 5, 2026
One-click install
npx skills add https://github.com/magnus919/hermes-profiles --skill sdd-authoring
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sdd-authoring
Source: https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-authoring
Command: npx skills add https://github.com/magnus919/hermes-profiles --skill sdd-authoring

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Specification authoring for AI-native SDD pipelines consolidates unclear requirements into a formal, machine-executable blueprint with a single source of truth that downstream artifacts can trace to.

Core Features & Use Cases

  • Formal specification authoring for AI-driven development cycles (Specify → Plan → Tasks → Implement).
  • Output is artifact-pyramid compliant SPEC.md with L1 executive summary, L2 dimensions, and L3 dossiers.
  • Loading Guidance and Templates: integrates quality gates, Gherkin patterns, and acceptance-criteria design references.
  • Trigger and governance: supports automated quality checks before downstream phases.

Quick Start

Create a SPEC.md from a project brief and run the spec-quality-check.sh script to validate it.

Frequently Asked Questions about sdd-authoring

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

FAQPage Schema
How do I write machine-executable specifications for AI-driven development?

Machine-executable specifications are authored by generating a SPEC.md that formalizes problem statements, scope, acceptance criteria, edge cases, and data contracts into a single source of truth for AI pipelines.

What is an artifact-pyramid compliant SPEC.md and when do I need one?

An artifact-pyramid compliant SPEC.md structures requirements into L1 executive summaries, L2 dimensions, and L3 dossiers, needed when projects require traceable, QA-friendly documentation for AI-native development cycles.

How do I validate acceptance criteria and quality gates in a specification?

Acceptance criteria and quality gates are validated by running the spec-quality-check.sh script against the generated SPEC.md, ensuring Gherkin patterns and non-functional requirements align with loading templates.

Can I use Gherkin patterns for acceptance criteria in formal specification authoring?

Gherkin patterns are integrated into the specification authoring process to design structured acceptance criteria, ensuring the output SPEC.md passes automated quality checks before downstream phases.

What's the best way to structure non-functional requirements and data contracts for AI pipelines?

Non-functional requirements and data contracts are structured within formal SPEC.md dossiers, consolidating unclear requirements into a machine-readable blueprint that downstream artifacts can trace.

Does specification authoring work without dependencies for automated quality checks?

Specification authoring runs without external dependencies, using bundled scripts and references to apply quality gates and governance artifacts before triggering downstream implementation phases.