skill-evals-run

Execute the OpenCode skill-evals evaluation suite to validate skill behavior.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/chandima/opencode-config --skill skill-evals-run
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-evals-run
Source: https://github.com/chandima/opencode-config/tree/main/.codex/skills/skill-evals-run
Command: npx skills add https://github.com/chandima/opencode-config --skill skill-evals-run

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables running the OpenCode skill-loading evaluation suite locally to quickly verify skill implementations when requested to run skill evals or the skill-evals-run command.

Core Features & Use Cases

  • Orchestrates the local skill-eval runner for reproducible tests and rapid feedback during development.
  • Validates skill-loading pipelines by executing the eval suite against the repository and surfacing failures for remediation.
  • Use Case: When you need to confirm that skills behave correctly, this guide runs the eval suite from the repo root with the configured dataset and matrix.

Quick Start

Run the skill-evals-run command from the repository root to execute the evaluation suite with the configured dataset and matrix.

Frequently Asked Questions about skill-evals-run

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

FAQPage Schema
How do I run local skill evaluations to validate OpenCode skill behavior?

To run local skill evaluations, execute the skill-evals-run command from your repository root to validate OpenCode skill behavior against the configured dataset and matrix.

What are OpenCode skill-evals used for in a development workflow?

OpenCode skill-evals are used to validate skill-loading pipelines and verify skill implementations, providing rapid feedback and automated verification for development and CI workflows.

Do I need specific configurations to execute the OpenCode evaluation suite?

Yes, executing the evaluation suite requires the OpenCode runner, repository context, and access to dataset and matrix configurations located under the .opencode/evals/skill-loading directory.

Can I integrate skill-evals into CI workflows for automated verification?

Yes, you can integrate skill-evals into CI workflows for automated verification, using the local evaluation runner to surface skill-loading failures for remediation in continuous integration pipelines.

Why are my OpenCode skill evaluations failing during local runs?

Local skill evaluations fail when the dataset and matrix configurations under .opencode/evals/skill-loading are missing or incorrect, or if the OpenCode runner lacks the necessary repository context.

What is the best way to test OpenCode skills locally before pushing changes?

The best way to test skills locally is by running the skill-evals-run command from the repository root, which orchestrates reproducible tests against your configured evaluation matrix.