Skip to content

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

docs(readme): say what get started offers and name the harness check in its heading (#708)

Christopher Kevin1f481a22c3cd
diff --git a/README.md b/README.md
index 3c51808b..f897128a 100644
--- a/README.md
+++ b/README.md
@@ -26,7 +26,7 @@ the [NVIDIA Verified Skills pipeline](https://github.com/NVIDIA/skills).
## Get started
-Three ways in, one CLI, same results.
+Check skills from your terminal, CI, or agent.
<table><thead><tr>
<th width="33%" align="left">1. Run the CLI directly</th>
@@ -88,7 +88,7 @@ See the [agent guide](https://docs.nvidia.com/skills/skillevaluator/agent-skill)
</td>
</tr></tbody></table>
-### ⚡ Will your agent load your skill? Know in seconds.
+### ⚡ [Harness check](https://docs.nvidia.com/skills/skillevaluator/harness-check): will your agent load your skill? Know in seconds.
No LLM inference · No model key · No agent run
@@ -107,10 +107,8 @@ skillevaluator harness-check ./my-skill
╰────────────────────────────────────────────────────────────────── ❌ 2 of 6 not loaded ─╯
```
-`validate` above runs [this check](https://docs.nvidia.com/skills/skillevaluator/harness-check)
-by default, as part of Tier 1.
-
-> 🧪 **Ready to go deeper?** Try a [live agent evaluation](https://docs.nvidia.com/skills/skillevaluator/tier3-live-evaluation) (Tier 3).
+`validate` above runs it by default, as part of Tier 1. 🧪 **Ready to go deeper?** Try a
+[live agent evaluation](https://docs.nvidia.com/skills/skillevaluator/tier3-live-evaluation) (Tier 3).
## Quickstart