experiment-driven-development

Community

Evidence-led development for reliable changes.

AuthorVictoriakaey
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Coordinating development in LLM systems often fails when changes rely on assumptions rather than real observed behavior. This skill enforces a disciplined process that begins with evidence from the live system, defines a testable hypothesis, and ends with a validation-driven commit.

Core Features & Use Cases

  • Structured, end-to-end change workflow: collect real-system evidence, formulate a hypothesis, execute a focused validation, and produce a traceable git commit.
  • Applicable to any implementation task in an LLM system, including prompt tuning, node logic updates, routing decisions, and architectural changes during development.
  • Maintains an iteration journal to capture decisions, known issues, and verifiable outcomes for future reuse.

Quick Start

Begin every change with verifiable system evidence, state a clear hypothesis, run a focused validation batch, and commit with a documented plan.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: experiment-driven-development
Download link: https://github.com/Victoriakaey/build-reliable-agents/archive/main.zip#experiment-driven-development

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.