sdd-review-specs

Review AI-generated spec artifacts for scope, completeness, and executability.

1|Updated Feb 27, 2026

Search Tags:#code review #spec-driven development #spec-driven workflow #spec artifact review #AI-generated spec

Ready to run

npx skills add https://github.com/9Ashwin/aswin-skills --skill sdd-review-specs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sdd-review-specs
Source: https://github.com/9Ashwin/aswin-skills/tree/main/skills/sdd-review-specs
Command: npx skills add https://github.com/9Ashwin/aswin-skills --skill sdd-review-specs

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill guarantees that AI-generated spec artifacts are thoroughly reviewed, reducing the risk of implementation issues and enhancing the quality of spec-driven development processes.

Core Features & Use Cases

Pre-Implementation Review: Ensures every AI-generated spec artifact is reviewed by a human before code writing.
Tier-Based Review: Offers different review depths based on the change's scope.
Task Granularity: Directs the use of superpowers:writing-plans for refining tasks into bite-sized units.
Red Flags Identification: Helps identify and address potential issues early in the development cycle.
Common Failures Analysis: Offers guidance on common pitfalls in spec-driven development and how to avoid them.

Quick Start

Review the 'proposal.md', 'specs/', 'design.md', and 'tasks.md' artifacts of the AI-generated spec before proceeding with implementation.

Frequently Asked Questions about sdd-review-specs

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

FAQPage Schema

How do I review AI-generated spec artifacts before implementation?▼

Reviewing AI-generated spec artifacts involves validating scope, completeness, design decisions, and task executability before code writing. This ensures human oversight early in the spec-driven workflow, reducing the risk of implementation issues.

What is the best way to validate task executability in spec-driven development?▼

Validating task executability in spec-driven development requires refining tasks into bite-sized units. Using a plan-writing integration helps refine tasks from the spec artifact to ensure robust implementation.

How do I identify red flags in AI-generated specs?▼

Identifying red flags in AI-generated specs involves analyzing common failures in spec-driven workflows. A tier-based review process helps flag potential design and scope issues early in the development cycle.

Does tier-based review work for evaluating spec artifacts of different scopes?▼

Tier-based review works for spec artifacts by offering different review depths based on the change's scope. This ensures appropriate validation effort is applied to both small and large AI-generated specifications.

What files do I need to review for a pre-implementation spec check?▼

A pre-implementation spec check requires reviewing the 'proposal.md', 'specs/', 'design.md', and 'tasks.md' artifacts. Examining these files ensures the AI-generated spec is complete before proceeding with implementation.

Why should I not skip human review of AI-generated specs?▼

Skipping human review of AI-generated specs risks introducing implementation issues due to unvalidated design decisions. Common failures in spec-driven development often stem from inadequate scope analysis and poor task granularity.