Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →automateyournetwork/anta-validation
Validate Arista EOS network state with structured pass/fail verdicts using ANTA.
Passed 15 of 18 test cases with the skill, and 4 of 18 without it.
and 20 more in the full report
13 fixed5 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to find all available test assertions related to NTP without running them on any device. Which tool call should be used and with what parameters?
| Checked | Without skill | With skill |
|---|---|---|
| The request uses anta_list_tests for test discovery. | Missed | Passed |
| The request passes keyword or category parameters for NTP. | Passed | Passed |
The instructions your model reads when the skill loads.
Every other NetClaw source reads state. This one asserts on it and returns a verdict you can act on.
Server: anta-mcp (NetClaw-authored over ANTA 1.9.0, Apache-2.0, own virtualenv) · 4 tools ·
1,272 tokens · 208 tests in the catalogue
Three servers touch Arista. They answer different questions, and picking the wrong one gives a confidently wrong answer.
| Plane | Server | Answers |
|---|---|---|
| Validation | this skill | does the state match what it should be — pass/fail |
| Management | arista-cvp-mcp | what does CloudVision say — inventory, tags, compliance as CVP sees it |
| Device CLI | pyats-*, multivendor-cli | what is the raw state — show-command output |
Use this skill to assert, not to fetch. If the question is "what is the interface MTU", that is the CLI plane. If the question is "is the MTU what it should be", that is this one.
| Verdict | Means | Never counts as |
|---|---|---|
pass | tested, expectation held | — |
fail | tested, expectation did not hold | — |
not_applicable | the feature is not configured — nothing was tested | fail |
skipped | ANTA declined to run it | pass |
error | device unreachable or the run broke | fail |
not_applicable is the one that mattersANTA natively reports a test for an unconfigured feature as a failure. Measured on a lab switch:
VerifyBGPPeerCount → failure
"'show bgp summary vrf all' failed on veos1: BGP inactive"
test cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.