Skip to navigation
Results & CI

Bring Skill Evaluation to Your Repository

View as Markdown

Bring SkillEvaluator to the repository where your team builds skills. Choose your skill folders and get results automatically when skills change.

No evaluation code to write. No scanner installations to manage. The shared container brings the Tier 1 runtime to your CI runner, including SkillSpector for specialized skill security scanning.

How it works

Skill changes CI runs SkillEvaluatorwith SkillSpector Results and reports

The job reads your skills, checks the changes, and saves a report. It does not require copying SkillEvaluator or SkillSpector source code into your repository.

GitHub Actions

Use the guided CLI or copy a workflow to check skills in pull requests, with optional hosted reports and comments.

GitLab CI/CD

Include the reusable job in your pipeline to evaluate changed skills in merge requests and download the report.

Copy a template

No local installation is required for the template route. Both platforms’ templates live in the public NVIDIA/SkillEvaluator repository. Open the file, copy the filled-in version, and set your skill folders and score threshold.

Your platformReady-to-use templatePut it in your repository
GitHubskill-checks.yml.github/workflows/skill-checks.yml
GitLabgitlab-skill-checks.yml.gitlab-ci.yml, or merge into your existing root configuration

The ready-to-use templates include the scan workflows and optional GitHub publisher, with reviewed workflow and image versions already filled in. Open a file and use GitHub’s Raw view to copy its full contents. The template catalog explains customization and optional LLM checks.

What you get

  • Automatic checks: evaluate changed skills in pull requests or merge requests; run the configured collection on the default branch.
  • Quality and security: run Tier 1 checks, including SkillSpector security scanning, without adding evaluator code to the repository.
  • Control: choose skill directories and a minimum quality score; the job fails when required checks fail or cannot complete.
  • Results you can inspect: see a concise outcome in CI and download the detailed HTML, JSON, Markdown and SARIF reports.
Example report table showing a failed skill with a quality score of 98.2
A real demo result: one changed skill scored 98.2 but failed a 100-point quality threshold.

Browse report, log and PR comment examples in the public repository. No demo-repository access is needed.

The released CI image runs Tier 1, including SkillSpector. It does not run Tier 2 or Tier 3. GitHub and GitLab use the same scanner image with platform-specific workflow files.

Other CI systems

The container contains the same evaluator runtime, and the CLI can also run in other CI systems. The CI integration guide covers the CLI, exit codes and report formats. The GitHub and GitLab integrations above have separate platform-specific configurations; another platform needs its own integration and validation.