workspace/skills/gns3-snapshot-ops/SKILL.md
Manage GNS3 project snapshots - create, restore, delete for safe experimentation
npx skillsauth add automateyournetwork/netclaw gns3-snapshot-opsInstall 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.
Create and manage snapshots of GNS3 project state. Save checkpoints before risky changes and restore to known-good states.
python3 -u mcp-servers/gns3-mcp-server/gns3_mcp_server.py (stdio transport)GNS3_URL, GNS3_USER, GNS3_PASSWORD environment variables| Tool | Parameters | What It Does |
|------|------------|--------------|
| gns3_list_snapshots | project_id | List all snapshots for a project |
| gns3_create_snapshot | project_id, name | Create a snapshot of current state |
| gns3_restore_snapshot | project_id, snapshot_id | Restore project to snapshot state |
| gns3_delete_snapshot | project_id, snapshot_id | Delete a snapshot |
# Create baseline before changes
"Create a snapshot called baseline for routing-test"
# Make some changes...
# (configure OSPF, add new links, etc.)
# Something went wrong? Restore to baseline
"Restore routing-test to baseline snapshot"
# Save after initial topology setup
"Create a snapshot called topology-complete for routing-test"
# Save after basic configuration
"Create a snapshot called basic-config for routing-test"
# Save after full configuration
"Create a snapshot called full-config for routing-test"
# List all checkpoints
"List snapshots for routing-test"
# Create starting point for students
"Create a snapshot called student-starting-point for training-lab"
# After each session, restore to starting point
"Restore training-lab to student-starting-point"
# Remove snapshots no longer needed
"Delete the old-test snapshot from routing-test"
before-ospf-config not snap1| Error Code | Meaning | Resolution | |------------|---------|------------| | GNS3_NOT_FOUND | Project or snapshot doesn't exist | Check names/IDs | | GNS3_CONFLICT | Snapshot name already exists | Use unique names |
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.