skills.rest
coval-ai
coval-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

watch-run

Monitors Coval evaluation runs via CLI and API polling for live progress and final results.

2|Updated Feb 17, 2026
Search Tags:#automation#testing#monitoring#evaluation#opentelemetry#coval
One-click install
npx skills add https://github.com/coval-ai/coval-external-skills --skill watch-run
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: watch-run
Source: https://github.com/coval-ai/coval-external-skills/tree/main/skills/runs/watch-run
Command: npx skills add https://github.com/coval-ai/coval-external-skills --skill watch-run

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the lack of visibility into long-running evaluation processes by providing live progress updates and automated status reporting.

Core Features & Use Cases

  • Live Progress Tracking: View real-time completion percentages and test case status updates.
  • Automated Summarization: Automatically fetch and report final results, including pass/fail counts and duration, once a run finishes.
  • Use Case: Use this when you have triggered a large-scale evaluation and need to know exactly when it finishes without manually polling the API.

Quick Start

Ask the agent to watch the progress of your most recent Coval run by providing the run ID.

Frequently Asked Questions about watch-run

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

FAQPage Schema
How do I monitor real-time progress of AI evaluation runs?▼

You can monitor AI evaluation runs by polling the execution status in real time. This skill tracks test case completion percentages and status transitions automatically, providing live visibility without manual API polling.

What is the best way to track Coval evaluation status without manual polling?▼

Automated tracking of Coval evaluation status is the best way to avoid manual polling. The skill continuously polls the Coval API, reporting live progress updates and fetching final pass/fail counts and duration once the run finishes.

Do I need the Coval CLI to interface with the Coval API for status retrieval?▼

Yes, you need the Coval CLI to interface with the Coval API for status retrieval. The CLI acts as the bridge for real-time polling, enabling automated data reporting and status transitions for your evaluation workflows.

How do I get automated summarization of final test case results?▼

Automated summarization of final test case results is fetched by polling the evaluation run until completion. Once finished, it automatically aggregates and reports final pass/fail counts and total duration.

When do I need real-time monitoring for long-running evaluation processes?▼

Real-time monitoring for long-running evaluation processes is needed when you trigger large-scale AI evaluations. It provides live progress updates and automated status reporting, solving the lack of visibility during extended test runs.

Related Skills

Explore More Software Engineering Skills→
coval-aicoval-ai
2

launch-run

Orchestrate AI agent evaluation runs via the Coval CLI.

Official
Intermediate
yonyon
3

/test — Run Test Suite

Run project test suites with options for unit, integration, or end-to-end tests.

Community
Intermediate
coval-aicoval-ai
2

debug-traces

Diagnose OpenTelemetry trace ingestion failures and correlation errors in Coval workflows.

Official
Advanced
BankrBotBankrBot
80

Bankr Agent - Job Workflow

Submit Bankr API prompts and track them as asynchronous jobs.

Official
Advanced