Treat NetBox as the source of truth for devices, prefixes, VLANs, and cables. Use when planning IP space, racking a leaf, or reconciling a drift between intent and running-config.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add gesh75/claude-skill-lint --skill netbox-source-of-truth --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Netbox Source Of Truth?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gesh75-netbox-source-of-truth)More formats (shields.io, HTML) on the badges page.
---
name: netbox-source-of-truth
description: Treat NetBox as the source of truth for devices, prefixes, VLANs, and cables. Use when planning IP space, racking a leaf, or reconciling a drift between intent and running-config.
argument-hint: "[site] [object]"
allowed-tools: Read Grep
license: MIT
---
# NetBox source of truth
Do not use as a monitoring tool or a substitute for a NMS. Not for flow records.
## Procedure
1. Nothing is real until it is in NetBox. A live device that is missing is drift, not inventory.
2. Allocate prefixes and IDs in NetBox first, then render config. Never the reverse.
3. Cables and rear/front ports are first-class. A "we'll document it later" patch is an incident waiting.
4. Reconcile weekly: NetBox vs CDP/LLDP vs IPAM utilization.
5. Verify the change ticket links the NetBox object IDs.
```python
prefix = nb.ipam.prefixes.create(prefix="2001:db8:24:1::/64", site="dc1", status="active", role="loopback")
```
## Anti-patterns
- Never hand-edit a loopback on a leaf and "catch up NetBox later".
- Do not store secrets in custom fields.
## Safety
NetBox writes are still reviewed. Device writes go through netops-change-guard.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
