agentsclimarketplace

Eval runner

Skill MarchRory/liushi_agent_settings/packages/harness/src/.agents/skills/eval-runner

Portable Codex agent harness and config monorepo with reusable roles, skills, validation, eval tooling, and safe project install sync.

Install
npx -y skills add MarchRory/liushi_agent_settings --skill eval-runner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when evaluating harness behavior against task fixtures, scoring rubrics, trace evidence, validation output, or baseline comparisons.

SKILL.md

0.7 KB, as published. Nobody here has run it

Eval Runner

Core Rule

Score only from evidence. A reusable harness is better only when comparable fixtures show better outcomes.

Workflow

  1. Read references/workflow.md for the eval run procedure.
  2. Use references/output-schema.md for the required eval record.
  3. Use examples/standard-output.yaml as a compact scoring template.

Resource Map

  • references/workflow.md: fixture, evidence, scoring, and lesson rules.
  • references/output-schema.md: canonical eval_record schema.
  • examples/standard-output.yaml: minimal valid eval record.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.