karpathy-triplet-diag

Community

Diagnose loop-readiness by surface, metric, time

Authordrewid74
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps you determine whether a specific system is truly ready for automated optimization by forcing clarity on the editable surface, the optimization metric, and the experiment time budget.

Core Features & Use Cases

  • Editable-surface gatekeeping: Identifies what files/configs/prompts/parameters an agent can safely and reversibly change without unpredictable dependency cascades.
  • Metric readiness and suitability: Converts “performing well” into an automated, bounded-time, scalar (or weighted scalar) metric with a credible business linkage and sandbox computability.
  • Time-budget feasibility: Ensures the system can support hundreds of experiments in an isolated environment within a practical overnight cycle.

Quick Start

Use karpathy-triplet-diag to evaluate a concrete pipeline or codebase by answering the editable-surface, metric, and time-budget questions until the Skill produces either a program.md spec or a blocker report.

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: karpathy-triplet-diag
Download link: https://github.com/drewid74/ai_skills/archive/main.zip#karpathy-triplet-diag

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.