Skill

jarvis-status

Use when the user wants a quick health check on ServiceNow instances, data freshness, MCP connectivity, AI Assist status, and console health without the full startup briefing.

npx claudepluginhub chadronbryant/napa-cowork-plugins --plugin jarvis

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Provide a rapid health check without the full boot sequence.

SKILL.md

Similar Skills

cache-components

139.2k

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

canvas-design

124.2k

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

20 files

anthropics-skills-13

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 3, 2026

Actions

View Source View Plugin View on GitHub View README

Jarvis Quick Status

Provide a rapid health check without the full boot sequence.

Process

Step 1: Load State (in parallel)

Read from workspace root (use CLAUDE.md canonical root on Mac; in Cowork use mounted workspace at the path shown in your environment):

Jarvis/status.json - Instance health, MCP status, console version, data freshness
Jarvis/MOTD.md - System banner with capabilities and version info

Step 2: Present Status

JARVIS STATUS CHECK | [date]
─────────────────────────────────
SERVICENOW (napa-mcp v1.x, 388 tools, lazy mode)
  Test (napaanesthesiatest):  [active/offline]  Last pull: [date, X days ago]
  Dev  (napaanesthesiadev):   [active/not configured]
  Prod (napaanesthesia):      [active/read-only]  OAuth: svc_napa_mcp

MCP PROFILE
  Active:   [lite/full]
  Router:   jarvis-router [up/down]
  Tools loaded: [3 meta / 388 full]

CONSOLE (v[version])
  Backend:    Docker:8000  [running/stopped]
  Frontend:   Docker:3000  [running/stopped]
  AI Assist:  [available/unavailable]
  Features:   mcp_console, nl_interpreter, local_inference, agent_mesh, semantic_memory, scheduler

LOCAL AI / MESH
  jarvis-brain (Mac Mini):  [reachable/unreachable]  http://100.86.223.86:8000
  ai-mini-x1 (GPU node):   [reachable/unreachable]  http://100.79.119.60:8000
  Delegate:  [auto / forced model]

DATA FRESHNESS
  Tables:     [count] extracted
  Records:    [count] analyzed
  Last Pull:  [date] ([X days ago])
  [warning if > 7 days stale]

DELIVERABLES
  Completed:  [count] ([list names])

IMPROVEMENT CADENCE
  Last run:   [date or NEVER]  [current / ⚡ OVERDUE]
─────────────────────────────────
[One-liner assessment]

Step 3: Flag Issues

Data > 7 days old → recommend /jarvis:refresh
MCP disconnected → recommend /jarvis:setup
Console not running → recommend /jarvis:console + Docker rebuild
AI Assist unavailable → check Anthropic API key in backend .env
jarvis-brain unreachable → check Tailscale + Mac Mini power
Cadence overdue → run weekly improvement cadence before next work session