feature-spec-author

Draft bounded feature specifications and feature_delivery_case JSONL records from requirements.

Updated Jun 1, 2026
One-click install
npx skills add https://github.com/aurora-atoms/lattice --skill feature-spec-author-aurora-atoms
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feature-spec-author
Source: https://github.com/aurora-atoms/lattice/tree/main/skills/feature-spec-author
Command: npx skills add https://github.com/aurora-atoms/lattice --skill feature-spec-author-aurora-atoms

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the ambiguity and lack of structure in early-stage feature requirements, ensuring that raw ideas are transformed into actionable, bounded specifications without exposing sensitive internal data.

Core Features & Use Cases

  • Structured Specification: Automatically generates feature specs including scope, non-goals, and acceptance criteria.
  • Evidence Mapping: Produces feature_delivery_case JSONL records that align with standardized delivery schemas.
  • Use Case: Use this when you have a raw, high-level requirement and need to generate a formal specification document and a corresponding delivery case record for the Feature Delivery Harness.

Quick Start

Use the feature-spec-author skill to draft a bounded feature specification and delivery case record based on the provided raw requirement text.

Frequently Asked Questions about feature-spec-author

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

FAQPage Schema
How do I write a bounded feature specification from raw requirements?

To write a bounded feature specification from raw requirements, use this Skill to automatically generate structured scope, non-goals, and acceptance criteria, transforming ideas into actionable documents.

What is a feature delivery case JSONL record?

A feature delivery case JSONL record is a standardized data format mapping evidence needs and acceptance criteria to align with the Feature Delivery Harness for structured governance tracking.

How do I generate acceptance criteria and evidence needs for early-stage feature requirements?

Generate acceptance criteria and evidence needs by processing synthetic or open requirements through the feature specification author, which drafts bounded specifications and corresponding delivery case records.

Can I use internal Jira traces and repository logs to draft feature specifications?

You cannot use internal Jira traces or repository logs, as this Skill adheres to strict safety constraints by excluding company-specific internal data and raw repository logs from the specification drafting process.

Does the feature specification author work with the Feature Delivery Harness?

Yes, the feature specification author operates within the context of the Feature Delivery Harness to define scope and produce JSONL records aligning with standardized delivery schemas.