AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Run Diagnostics

skill-sumitaich1998-jarvisvr-run-diagnostics · by sumitaich1998

>-

No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-sumitaich1998-jarvisvr-run-diagnostics

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-sumitaich1998-jarvisvr-run-diagnostics)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Run Diagnostics? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Run Diagnostics

Produce a quick, honest health report and flag anything that needs attention.

Checks

  1. Connection: heartbeat health (client/server *.heartbeat every 5s),

protocol version, session id.

  1. Model/provider: active agent.model (from server.hello_ack) and provider

reachability (see configure-llm).

  1. Perception: perception.state — which streams are active, fps,

resolution, thermal (nominal|fair|serious|critical), battery.

  1. Capabilities/tools: advertised tools and client.hello.capabilities

(passthrough, mic, eye_tracking, depth).

  1. Stage: count of live holograms (clutter is a common "slow/laggy" cause).

Steps

  1. Gather the signals above.
  2. Render a data_table (or settings_panel) summarizing component → status.
  3. Diagnose the user's complaint (e.g. lag → high hologram count + serious

thermal → suggest declutter-space and lower vision fps).

  1. Raise a notification_toast (notify) for anything warning/error.

Output

data_table (show_data_table, props per registry.json):

{ "widget_type": "data_table",
  "props": { "title": "Diagnostics",
             "columns": [ { "key": "component", "label": "Component", "type": "string" },
                          { "key": "status", "label": "Status", "type": "string" },
                          { "key": "detail", "label": "Detail", "type": "string" } ],
             "rows": [
               { "component": "Connection", "status": "ok", "detail": "v1.2, heartbeat 5s" },
               { "component": "Model", "status": "ok", "detail": "gpt-4o" },
               { "component": "Vision", "status": "fair", "detail": "2 fps, thermal: fair" },
               { "component": "Battery", "status": "ok", "detail": "74%" },
               { "component": "Holograms", "status": "warn", "detail": "11 live — consider declutter" } ],
             "sortable": true } }

Issue alert (notifynotification_toast):

{ "widget_type": "notification_toast",
  "props": { "title": "Thermal: serious", "body": "Lowering vision to 1 fps to cool down.",
             "severity": "warning", "source": "Diagnostics" } }

agent.speech: { "text": "All green except the headset's warming up — I dropped the camera to 1 fps.", "final": true }

Edge cases

  • Disconnected → if heartbeats stopped, advise reconnect; queue the report.
  • Critical thermal/low battery → recommend pausing vision (manage-privacy)

and reducing holograms (declutter-space).

  • Provider unreachable → point to configure-llm; offer the offline mock.
  • Everything nominal → a one-line "all systems nominal" beats a wall of green.
  • Capability missing → report as "unavailable", not "failed".

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.