manage-runs

Official

Browse inspect, compare, and clean pipeline runs.

Authorai-analyst-lab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Browse, inspect, compare, and clean up past pipeline runs. Each run is a self-contained directory under working/runs with its own working files, outputs, and pipeline state.

Core Features & Use Cases

  • Scan run directories under working/runs and extract pipeline_state.json fields for quick summaries.
  • View details of a specific run, compare two runs side-by-side, and see agent progress and timing.
  • Clean up runs older than 30 days with user confirmation and view output artifacts and validation confidence when available.
  • Handle edge cases such as missing pipeline_state.json, unknown statuses, or legacy formats with graceful messaging.

Quick Start

Ask to list runs, view details, or compare two runs to get immediate insights.

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: manage-runs
Download link: https://github.com/ai-analyst-lab/ai-analyst-plugin/archive/main.zip#manage-runs

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.