workspace/skills/suzieq-observability/SKILL.md
SuzieQ network observability — query current and historical network state, run validation assertions, get summary statistics, trace forwarding paths, and discover unique values across 20+ network tables. Use when investigating BGP/OSPF state, checking interface health, performing time-travel queries, validating network assertions, or tracing packet paths through the network via SuzieQ.
npx skillsauth add automateyournetwork/netclaw suzieq-observabilityInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
mcp-servers/suzieq-mcp/server.pySUZIEQ_API_URL, SUZIEQ_API_KEYSUZIEQ_VERIFY_SSL (default: true), SUZIEQ_TIMEOUT (default: 30s)suzieq_showQuery detailed network state data from any SuzieQ table. Supports filtering by device, namespace, time range, and columns. Use for current or historical (time-travel) network state queries.
table (string, required): SuzieQ table name (e.g., "bgp", "route", "interface")namespace (string): Filter by SuzieQ namespacehostname (string): Filter by device hostnamecolumns (string): Comma-separated column names to returnstart_time (string): Start time for time-travel query (ISO 8601 or relative e.g., "1h", "2d")end_time (string): End time for time-travel queryview (string): Data view: "latest", "all", or "changes"filters (string): Additional key=value pairs separated by ampersandUse when: Querying current network state, investigating specific devices, performing time-travel queries for historical analysis.
suzieq_summarizeGet aggregated statistics and summary views of any SuzieQ network table. Returns counts, distributions, and per-device breakdowns.
table (string, required): SuzieQ table namenamespace (string): Filter by SuzieQ namespacehostname (string): Filter by device hostnamestart_time (string): Start time for historical summaryend_time (string): End time for historical summaryUse when: Getting high-level network overview, distribution analysis, capacity planning.
suzieq_assertRun validation assertions against network state. Checks conditions like "all BGP peers established" or "no interface errors".
table (string, required): Must be one of: bgp, ospf, interface, evpnVninamespace (string): Filter by SuzieQ namespacehostname (string): Filter by device hostnameUse when: Validating network health, pre/post-change verification, compliance checks.
suzieq_uniqueGet distinct values and their counts for a specific column in a SuzieQ table.
table (string, required): SuzieQ table namecolumn (string, required): Column name to get unique values fornamespace (string): Filter by SuzieQ namespacehostname (string): Filter by device hostnameUse when: Understanding value distributions (unique VRFs, BGP states, interface types).
suzieq_pathTrace the forwarding path between two endpoints through the network.
namespace (string, required): SuzieQ namespacesource (string, required): Source IP addressdestination (string, required): Destination IP addressvrf (string): VRF name (default: "default")Use when: Troubleshooting connectivity, verifying forwarding paths, path analysis.
suzieq_show or suzieq_summarize to understand current network statesuzieq_assert to validate health (BGP established, OSPF full, interfaces up)suzieq_unique to explore value distributions for specific columnssuzieq_path to trace forwarding paths between endpointsstart_time/end_time on show/summarize for time-travel historical analysisaddress, arpnd, bgp, device, devconfig, evpnVni, fs, ifCounters, interface, inventory, lldp, mac, mlag, namespace, network, ospf, route, sqPoller, topology, vlan
tools
Federate your NetClaw with other NetClaw operators over the BGP mesh — exchange capability inventories and ask your claw what a peer can do. (US1; remote invocation and chat land in later phases.)
tools
3D network topology visualization and interactive digital twin in Unreal Engine 5.8 via the built-in UE5 MCP server.
testing
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
testing
IPv4 and IPv6 subnet calculator - CIDR breakdown, usable hosts, previous/next subnets, address classification, VLSM planning, and dual-stack analysis. Use when calculating subnets, figuring out how many hosts fit in a prefix, planning IP addressing, getting wildcard masks for ACLs, or checking if two IPs are in the same subnet.