workspace/skills/te-path-analysis/SKILL.md
Cisco ThousandEyes — path visualization, BGP route analysis, outage investigation, instant tests, endpoint agent diagnostics. Use when tracing network paths hop-by-hop, investigating why a site is slow, analyzing BGP route changes, diagnosing an internet outage, or troubleshooting VPN from endpoint agents.
npx skillsauth add automateyournetwork/netclaw te-path-analysisInstall 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.
src/server.py (stdio, Python 3.12+) — te_get_path_vis for path visualizationhttps://api.thousandeyes.com/mcp (remote HTTP) — full path vis, BGP, instant tests, anomalies, endpoint agents| Source | Tool | What It Does |
|--------|------|--------------|
| Community | te_get_path_vis | Hop-by-hop path from a specific agent to the test target |
| Official | Get Path Visualization | Network paths with routing details |
| Official | Get Full Path Visualization | Comprehensive path data aggregated across all agents |
Path visualization shows every network hop between agent and target:
| Tool | What It Does | |------|--------------| | Get BGP Test Results | BGP reachability — which BGP monitors see the prefix, which don't | | Get BGP Route Details | AS path, origin AS, prefix length, route stability |
BGP analysis provides external routing visibility:
| Tool | What It Does | |------|--------------| | Search Outages | Find network and application outages with time/scope filters | | List Events | Network/application problems with affected targets | | Get Event Details | Deep dive: impacted tests, affected agents, timeline |
| Tool | What It Does | |------|--------------| | Instant Tests | Run tests on demand from selected agents — don't wait for scheduled cycles | | Get Anomalies | Detect metric deviations from baseline over time | | Views Explanations | AI-powered explanation of test results and visualizations |
| Tool | What It Does | |------|--------------| | List Endpoint Agents and Tests | Endpoint agents on user workstations with test associations | | Get Endpoint Agent Metrics | WiFi signal, VPN tunnel latency, DNS response, HTTP performance |
The classic ThousandEyes troubleshooting workflow:
te_list_tests (community) filtered by target sitete_get_test_results (community) — is latency elevated? Packet loss?te_get_path_vis (community) — hop-by-hop analysisWhen ThousandEyes detects a broad outage:
te_get_path_vis (community) for affected tests — where does the path break?When users report VPN issues:
When validating BGP route security:
te_list_tests (community) filtered by BGP test typepyats-routing for internal BGP state confirmation| Skill | How They Work Together |
|-------|----------------------|
| te-network-monitoring | Monitoring provides context (tests, dashboards), path analysis provides deep investigation |
| pyats-routing | ThousandEyes external BGP + pyATS internal BGP = complete routing picture |
| pyats-troubleshoot | ThousandEyes internet path + pyATS device-level CLI diagnostics |
| meraki-security-appliance | ThousandEyes path through MX + Meraki VPN status for SD-WAN troubleshooting |
| aws-network-ops | ThousandEyes cloud agent + AWS VPC flow logs for hybrid path analysis |
| fmc-firewall-ops | ThousandEyes path vis shows traffic traversing FTD + FMC rule analysis |
| servicenow-change-workflow | Outage events trigger ServiceNow incidents with ThousandEyes evidence |
| gait-session-tracking | Record all path analysis and troubleshooting in GAIT |
TE_TOKEN — ThousandEyes API v7 OAuth bearer token (shared with te-network-monitoring)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
Manage EVE-NG node lifecycle. Use when listing nodes, checking runtime state, creating or deleting nodes, starting or stopping nodes or whole labs, verifying node details, or wiping node NVRAM back to factory defaults.
development
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives, checking EVE-NG health or auth, or verifying available node images before build work.
tools
Execute live CLI commands on running EVE-NG nodes over telnet console. Use when running show commands, making live config changes, verifying protocol state, testing connectivity, checking console readiness, or interacting with IOS, Junos, VPCS, EOS, or NX-OS nodes.