workspace/skills/msgraph-visio/SKILL.md
Generate and manage Visio network diagrams on SharePoint via Microsoft Graph API - create topology diagrams from CDP/LLDP discovery, update existing diagrams, export to PDF. Use when creating Visio topology diagrams, uploading network diagrams to SharePoint, or generating physical/logical topology views from discovery data
npx skillsauth add automateyournetwork/netclaw msgraph-visioInstall 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.
The Microsoft Graph MCP server is invoked via npx with Azure AD credentials:
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" <tool-name> '<arguments-json>'
Use pyats-topology to collect CDP/LLDP neighbor data from all devices:
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show cdp neighbors detail"}'
Collect from all devices via pCall for a complete topology view.
From discovery data, construct the topology as a Visio-compatible format. Use the OOXML structure that Visio .vsdx files use (ZIP archive containing XML).
For simpler workflows, generate the topology as Mermaid first, then use Draw.io for the editable diagram, and export the final version as .vsdx via the Draw.io editor.
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_upload_file '{"driveId":"<drive-id>","parentId":"<topology-folder-id>","fileName":"campus-topology-2026-02-22.vsdx","content":"<base64-vsdx-content>"}'
Create a sharing link for the team:
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_create_sharing_link '{"driveId":"<drive-id>","itemId":"<file-id>","type":"view","scope":"organization"}'
Generated from CDP/LLDP neighbor data. Shows:
Data sources:
show cdp neighbors detail — device names, platforms, interfaces, IPsshow lldp neighbors detail — same for LLDP-enabled devicesshow interfaces — link speeds, media types, error countersGenerated from routing protocol data. Shows:
Data sources:
show ip ospf neighbor + show ip ospf database — OSPF topologyshow bgp summary — BGP peering topologyshow vrf — VRF membershipColor-coded by NetBox reconciliation status:
Data source: netbox-reconcile skill output
ACI-specific topology showing:
Data source: aci-fabric-audit skill output
<site>-<diagram-type>-<date>.vsdx
Examples:
campus-physical-topology-2026-02-22.vsdx
dc-aci-fabric-2026-02-22.vsdx
wan-bgp-logical-2026-02-22.vsdx
site-a-reconciliation-2026-02-22.vsdx
SharePoint: Network Engineering/
└── Topology/
├── Physical/
│ ├── campus-physical-topology-2026-02-22.vsdx
│ └── dc-physical-topology-2026-02-22.vsdx
├── Logical/
│ ├── wan-bgp-logical-2026-02-22.vsdx
│ └── campus-ospf-logical-2026-02-22.vsdx
├── Reconciliation/
│ └── site-a-reconciliation-2026-02-22.vsdx
└── ACI/
└── dc-aci-fabric-2026-02-22.vsdx
Record diagram generation in GAIT:
python3 $MCP_CALL "python3 -u $GAIT_MCP_SCRIPT" gait_record_turn '{"input":{"role":"assistant","content":"Generated campus physical topology diagram from CDP/LLDP discovery (4 devices, 6 links). Uploaded to SharePoint Network Engineering/Topology/Physical/campus-physical-topology-2026-02-22.vsdx. Sharing link created for Network Engineering team.","artifacts":[]}}'
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.