Verified:GitHub

gsd-ai-integration-phase

Generate an AI-SPEC.md design contract for AI system phases.

Updated Aug 23, 2026

Search Tags:#workflow orchestration #agent design #phase planning #research synthesis #framework selection #ai-spec #evaluation strategy

Ready to run

npx skills add https://github.com/BeiBei-Clic/ai-skills --skill gsd-ai-integration-phase-beibei-clic

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gsd-ai-integration-phase
Source: https://github.com/BeiBei-Clic/ai-skills/tree/main/gsd-ai-integration-phase
Command: npx skills add https://github.com/BeiBei-Clic/ai-skills --skill gsd-ai-integration-phase-beibei-clic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Converts a vague phase description into a concrete AI-SPEC.md contract, so the build-research-evaluate steps have a shared, verifiable blueprint and fewer misalignments.

Core Features & Use Cases

Framework-driven AI design: Guides the flow to select an AI framework suitable for the phase, then structures the remaining work around that choice.
Research-backed domain decisions: Pulls in phase-relevant research materials to ground domain assumptions and evaluation criteria.
Evaluation strategy planning: Produces an evaluation plan alongside the design contract so the phase outcome is measurable, not just described.
Use Case: Use it when planning an AI development phase (e.g., building a small agent workflow) and you need an AI-SPEC.md that aligns research, design, and how success will be tested.

Quick Start

Run the skill and request the next integration contract for phase 3 by writing: generate an AI-SPEC.md design contract for phase number 3.

Frequently Asked Questions about gsd-ai-integration-phase

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

FAQPage Schema

How do I create a design contract for AI system phase planning?▼

To create an AI-SPEC.md design contract for phase planning, you orchestrate framework selection, research synthesis, and evaluation strategy design to document architecture decisions and measurable success criteria. This converts vague phase descriptions into verifiable blueprints.

What is an AI-SPEC.md contract and when do I need it for workflow orchestration?▼

An AI-SPEC.md contract is a documented blueprint for AI system phases that captures assumptions, architecture decisions, and evaluation plans. You need it during project planning when build-research-evaluate steps require a shared, verifiable alignment.

How do I plan an evaluation strategy alongside AI agent design?▼

You plan an evaluation strategy by generating it alongside the design contract during phase planning, ensuring the AI agent workflow outcome is measurable. This grounds domain assumptions and defines how success will be tested.

Can I generate a phase design contract without specifying the phase number?▼

Yes, you can generate a design contract without a phase number because the system auto-detects the next unplanned phase. If you provide a phase number, it uses that specific context to structure the framework selection and research.

What is the best way to document framework selection decisions for AI development?▼

The best way to document framework selection decisions is through an AI-SPEC.md contract that structures the remaining work around the chosen AI framework. This grounds domain assumptions and aligns research with the evaluation strategy.

Does this approach preserve workflow gates when adding research synthesis to phase planning?▼

Yes, this approach preserves all workflow gates while integrating domain and AI research synthesis into the phase planning process. It uses provided context inputs to ensure the design contract maintains existing project workflow integrity.