Cisco Meraki Switching — port configuration, VLANs, port status, ACLs, QoS rules, port cycling.
SkillScore91Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/16/2026
What it changes
Passed 19 of 21 test cases with the skill, and 10 of 21 without it.
Without skill45%
With skill91%
Checks it passed that the model alone missed
The response utilizes semantic_search
The response identifies getDeviceSwitchWarmSpare
The response identifies getDeviceSwitchPortsStatusesPackets
and 10 more in the full report
10 fixed10 passed either way2 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+47%
Agent turns
0%
Response time
-38%
Model gemini-3.6-flashMeasured 8/16/2026v220 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
After running a complete port configuration audit across 10 Meraki switches using MCP execute_api tools, what mandatory tracking step must be performed to finalize the audit task?
What was checked, without and with the skill
Checked
Without skill
With skill
The response requires recording or logging the audit execution in GAIT
Missed
Passed
case-21 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
Requires: MERAKI_DASHBOARD_API_KEY — use a read-only dashboard key
Tools: exactly two — semantic_search (discover) and execute_api (invoke)
Read-only, structurally
All 431 mutating Meraki operations (174 POST, 186 PUT, 71 DELETE) are absent from the
capability catalogue. Only non-deprecated GETs are built in, so updateNetwork,
rebootDevice, blinkDeviceLeds and friends return Capability not found.
Do not attempt writes and do not offer them. There is no ServiceNow CR path here because
there is nothing to gate — a change must be made in the Meraki dashboard directly.
How to call it
Two capability IDs may be called directly; everything else must be discovered:
execute_api → getOrganizationNetworks — find network IDs in the chosen org
semantic_search → describe the intent in words → returns ranked capability_ids
execute_api → the chosen capability_id + its required parameters
Discover, do not guess. An earlier version of this skill hardcoded 80 method names and
54 of them did not exist in the Meraki API at all — they failed regardless of server.
semantic_search is the guard against that: it can only return IDs that exist.
Reading results honestly
One page only.execute_api returns a single page. Request a bounded page size when
supported, and never present a page as the complete dataset.
Empty is not absent.n=0 means this network reported none, never none exist.
Live proof from a real sandbox org: getOrganizationDevices returns 0 devices while
the same org has a fully configured network with 15 SSIDs.