tdd-spike-auto

Orchestrate interactive design spikes into autonomous plan, audit, implement, and results phases.

4|1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/CurtisThe/three-pillars-plugin --skill tdd-spike-auto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tdd-spike-auto
Source: https://github.com/CurtisThe/three-pillars-plugin/tree/main/skills/tdd-spike-auto
Command: npx skills add https://github.com/CurtisThe/three-pillars-plugin --skill tdd-spike-auto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables teams to design an initial spike interactively and then autonomously execute plan, audit, implement, and results steps while maintaining a centralized decision log for morning review.

Core Features & Use Cases

  • Phase 1: Interactive design to surface hypotheses, success criteria, and experiments, with user prompts to refine scope and link to parent designs.
  • Phase 2: Autonomous execution that runs plan → audit → implement → results without further prompts, all decisions recorded in a decisions.md log.
  • Artifact generation and linking: creates docs/tdd-designs/<spike-name> with design.md, decisions.md, spike-results.md, and demos, enabling traceability and reviews.

Quick Start

Provide a spike-name to start the interactive design; then confirm to run autonomous execution to generate decisions.md and spike-results.md.

Frequently Asked Questions about tdd-spike-auto

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

FAQPage Schema
How do I automate spike execution and maintain a decision log for design exploration?

Autonomous spike execution is orchestrated by running interactive design phases to define hypotheses, then automatically executing plan, audit, implement, and results steps while recording all decisions in a centralized decisions.md log.

What is the best way to structure a design spike workflow from planning to artifact generation?

Structure a design spike by starting with interactive design to surface success criteria, then proceed through autonomous execution phases that generate design.md, decisions.md, and spike-results.md artifacts in a docs/tdd-designs directory for full traceability.

How do I link a spike to a parent design for scoping experimental projects?

Link a spike to a parent design by providing a spike-name and the optional --parent flag during the interactive design phase, which scopes the spike and connects it to the existing parent design documentation.

Can I run experimental planning and implementation phases without continuous user prompts?

Yes, after the interactive design phase confirms hypotheses and scope, the workflow runs plan, audit, implement, and results phases autonomously without further prompts, recording all outcomes in the decision log.

How does a centralized decision log work for morning review of spike results?

The centralized decision log works by automatically recording every decision made during the autonomous execution phases into decisions.md, enabling teams to review spike outcomes and traceability during morning reviews.

What artifacts are generated when running an autonomous spike workflow?

Artifacts generated include design.md, decisions.md, spike-results.md, and demos, all created within the docs/tdd-designs/<spike-name> directory to enable artifact linking and comprehensive project reviews.