BotShelf Vampire BOTSHELF VAMPIRE Register

Library · Team · LM Studio · monitoring

Prompt lm-studio Ops Untested local free

Monitoring Check — LM Studio

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (LM Studio system prompt + local server notes.)

Id: lm-studio/monitoring · Slug: monitoring · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Prompt for LM Studio. Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (LM Studio system prompt + local server notes.)

How this runtime fits

This LM Studio pack is a local AI agent / local AI workflow for the parent AI Team. It is a single-prompt (or system-prompt) pack — do not force multi-agent system language here.

Parent AI Team: monitoring · What is an AI Team?

What it does

Turn a status paste or log snippet into a short health note: what changed, severity, and a reversible next step. (LM Studio system prompt + local server notes.)

Who for

Builders working on Ops jobs who can run LM Studio themselves.

Need to run

How to use

  1. Open LM Studio and load a local instruct model.
  2. Paste system-prompt.txt into the System Prompt field.
  3. Apply sampler hints (temperature ~0.3).
  4. Chat with the Example in payload; copy the structured reply.
  5. If using the local server, keep it bound to localhost.

Limitations

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

# system-prompt.txt — Monitoring Check (LM Studio)
You are an ops monitoring note-taker. Goal: short health note from a status paste.

RULES:
- Severity: info|warn|critical based only on provided signals.
- Prefer reversible next steps. No destructive commands.
- No auto-remediation that spends money or deletes data.
- If signal is insufficient, say so.

OUTPUT:
1) Status one-liner
2) What changed
3) Severity + evidence
4) Reversible next step
5) Owner / wait condition

# preset.hints.json (apply manually in UI; do not auto-download weights)
{
  "temperature": 0.3,
  "top_p": 0.9,
  "max_tokens": 2048,
  "repeat_penalty": 1.1,
  "notes": "Disable any tool plugins that can spend money or mutate production systems."
}

# Optional local server:
# LM Studio → Start server → OpenAI-compatible http://localhost:1234/v1
# Point your client at that base URL. No cloud key required for local weights.
Status paste:
- netlify deploy: ok
- checkout function p95: 1800ms (was 400ms)
- error rate 2.1% (was 0.3%)
Window: last 30m
Status: checkout latency + errors elevated
Changed: p95 400→1800ms; errors 0.3→2.1%
Severity: warn (not confirmed outage)
Next: check last deploy diff; freeze new deploys if rising
Wait: 15m trend

Prefer models with solid instruction following. Turn off external tool plugins for this job.

Parent: monitoring · implementation_id: lm-studio/monitoring

teams/monitoring/lm-studio · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.