Run senior-network-engineer incident response from first page to RCA. Use when a SEV-1/2 hits BGP, WAN, DC fabric, or firewall and you need a timed, fail-closed playbook.
Scanned 9/5/2026
Install to Claude Code
npx -y skills add gesh75/claude-skill-lint --skill senior-ne-runbook --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Senior Ne Runbook?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gesh75-senior-ne-runbook)More formats (shields.io, HTML) on the badges page.
---
name: senior-ne-runbook
description: Run senior-network-engineer incident response from first page to RCA. Use when a SEV-1/2 hits BGP, WAN, DC fabric, or firewall and you need a timed, fail-closed playbook.
argument-hint: "[sev] [symptom]"
allowed-tools: Read Grep
license: MIT
---
# Senior NE runbook
Do not use for project design or CAB paperwork (use network-manager-cadence). Not for app-layer incidents.
## Procedure
1. Clock starts. Declare SEV, name an incident commander, open a war-room channel. No config yet.
2. Dual-signal: telemetry AND a human-reproducible symptom. One signal is not a change.
3. Scope: one site, one VRF, one prefix, or global. If global, page the manager.
4. Mitigate with the smallest reversible action (withdraw a prefix, fail over a color, shut a bad peer).
5. After restore: timeline, root cause, detection gap, and one prevention item. No blame.
```text
T+0 declare SEV-2 WAN site 2401 dual-color down
T+5 confirm BFD down both colors circuit IDs collected
T+12 LTE backup carrying 40% voice on-net degraded
T+25 ISP restores MPLS failback verify MOS
```
## Anti-patterns
- Never bounce BGP as the first step.
- Do not invite vendors before you have a packet capture or log excerpt.
## Safety
Mitigations are change-guarded unless the commander invokes emergency break-glass, which is logged.
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.