automateyournetwork/netclaw/claroty-ot-topology

Claude Code and agent skill by automateyournetwork/netclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Render Claroty xDome OT / IoT communication maps and zone segmentation as inline Canvas/A2UI topology, draw.io diagrams, and timeline summaries.

Install

npx vskill@latest install automateyournetwork/netclaw/claroty-ot-topology

SKILL.md

The same SKILL.md was published earlier as automateyournetwork/netclaw/claroty-ot-topology.

Claroty OT Topology

Visualise the OT / IoT communication fabric observed by Claroty xDome — device-to-device edges, organisation zones, and OT activity timelines — using Canvas / A2UI for inline chat rendering and draw.io for exportable diagrams.

When to Use

  • Visualising how OT devices communicate (PLC ↔ HMI, RTU ↔ historian, etc.)
  • Reviewing network segmentation zones and verifying Purdue-layer separation
  • Producing an OT topology diagram for a CR or QBR deck
  • Walking an activity timeline for a specific device during incident review
  • Sanity-checking that newly deployed zones are reflected in observed traffic

MCP Server

  • Server: claroty-mcp
  • Command: python3 -u mcp-servers/claroty-mcp/claroty_mcp_server.py (stdio transport)
  • Auth: Bearer token via CLAROTY_API_TOKEN
  • ITSM: This is a read-only skill — no ITSM gate required.

Available Tools

ToolParametersWhat It Does
get_device_communication_mapdevice_id?, site_id?, limit?, offset?Device-to-device edges (src, dst, protocol, port, byte counts)
list_organization_zoneslimit?, offset?Network segmentation zones (id, name, device count)
list_ot_activity_eventsdevice_id?, site_id?, event_type?, start?, end?, limit?, offset?, max_items?OT activity / protocol observations
list_devices(see claroty-asset-inventory)Resolve device IDs ↔ human-friendly names for diagram labels

Compose with:

  • canvas-network-viz skill for inline Canvas / A2UI topology rendering
  • drawio- skill for exportable .drawio / SVG diagrams
  • uml- skill for nwdiag-style topology

Workflow Examples

Inline topology for a device
"Show me the communication map for device 7a2c... as an inline topology"
  1. get_device_communication_map(device_id="7a2c...") → edges.
  2. list_devices(...) to resolve neighbour device IDs to names.
  3. Hand-off to canvas-network-viz to render the topology in chat with health-coloured nodes.
Zone segmentation audit
"List all xDome zones and show their device counts"

Calls list_organization_zones(). The agent then optionally calls list_devices per zone to surface devices that should be in a stricter zone but aren't.

Site-wide topology export
"Render a draw.io diagram of the OT topology at site warehouse-east"
  1. list_devices(site_id="warehouse-east") → nodes.
  2. get_device_communication_map(site_id="warehouse-east") → edges.
  3. Hand off to the draw.io skill to produce an exportable .drawio file.
OT activity timeline during incident review
"Show me OT activity events for device 7a2c between 09:00 and 11:00 today"

Calls list_ot_activity_events(device_id="7a2c...", start="2026-06-08T09:00:00Z", end="2026-06-08T11:00:00Z"). Optionally renders as a Canvas A2UI timeline.

Rendering hand-offs

This skill is intentionally a data + composition skill — it does not own the rendering layer. For visual output:

  • Inline chat: canvas-network-viz (topology map A2UI primitive)
  • Exportable diagram: drawio- skill or uml- skill (nwdiag)
  • Timeline: canvas-network-viz (timeline A2UI primitive)

This keeps Principle VII (Skill Modularity) intact — Claroty-specific knowledge stays here, generic rendering lives in the visualisation skills.

Failure Behavior

  • On a tool error (timeout, unreachable host, malformed response), report the failure and its error message directly to the user rather than fabricating or guessing at results.
  • For a confirmed read-only call, check connectivity and retry once if appropriate. For any call that changes state or sends a message, a timeout does not prove the action failed: inspect current state or delivery status before retrying, preserve the required approval/change gates, and do not repeat an action whose outcome is unknown.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
674
Repository forks
189
7-day trend score
33

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/automateyournetwork/netclaw/claroty-ot-topology/badge)](https://verified-skill.com/skills/automateyournetwork/netclaw/claroty-ot-topology)

Something wrong with this skill or its page? Tell us.