finalize-run

Community

Enforce and save validated benchmark results.

Authorslabgorb
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmark runs often fail to enforce a consistent finalization step, risking unreliable results and audit gaps.

Core Features & Use Cases

  • Strict data validation for agent, judge, and score fields, including timestamp formats and token counts.
  • Guardrail enforcement ensuring every run passes through a single save point before results are stored.
  • Multi-judge support for relay-style evaluations with consistent score verification and timestamp sanity.

Quick Start

Invoke the finalize-run skill with a complete JSON payload to validate the run and write the results to the specified output path.

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: finalize-run
Download link: https://github.com/slabgorb/sidequest/archive/main.zip#finalize-run

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.