lgdimaggio/predictive-maintenance-mcp/quick-screening

Claude Code and agent skill by lgdimaggio/predictive-maintenance-mcp

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Fast vibration health screening for industrial machinery using the predictive-maintenance-mcp server. Use this skill when the user says "quick check", "health screening", "vibration check", "is this machine healthy", "overall health", "quick diagnostic", "machine status", "condition monitoring", "health assessment", or wants a rapid overview of machine condition without full fault identification.

Install

npx vskill@latest install lgdimaggio/predictive-maintenance-mcp/quick-screening

SKILL.md

Quick Vibration Screening

Fast health status assessment for rotating machinery. Produces a screening card in under 30 seconds with clear next-step recommendations. Screening informs the engineer's decision — it is never a diagnosis by itself.

Prerequisite: The predictive-maintenance-mcp MCP server must be connected.

Workflow

Step 1 — Signal Selection

Call list_signals(scope="memory") to show loaded signal_ids, or list_signals(scope="disk") for loadable files. If the user has not specified one, ask. Load with load_signal(filepath="real_test/baseline_1.csv", signal_unit="g") if needed — declaring signal_unit up front makes the ISO step work without a re-load. For raw binary files (.bin/.raw/.dat), also declare sample_format and sampling_rate (or provide a companion <stem>_metadata.json) — see the signal-management skill.

Step 2 — Statistical Features

Call analyze_statistics(signal_id="<id>").

Report as bullet points:

  • RMS: energy level
  • Crest Factor: impulsiveness indicator
  • Kurtosis: excess kurtosis (Fisher convention)
  • Peak-to-Peak: overall vibration range
Step 3 — FFT Snapshot

Call analyze_fft(signal_id="<id>").

Report:

  • Peak frequency and magnitude
  • Top 3 spectral peaks (frequency + magnitude)
  • Any obvious harmonic patterns

A strongest line at 1x or 2x, or a harmonic series, names no fault on its own. If the user asks about unbalance, misalignment or looseness, the shaft-order-evidence skill gives an experimental evidence assessment that attributes no fault. It is optional and not part of the screening card.

Step 4 — ISO Severity Assessment

Call assess_severity(signal_id="<id>", machine_group=2, support_type="rigid").

Report:

  • RMS velocity in mm/s
  • Zone: A / B / C / D
  • Severity description

Notes:

  • Confirm machine_group (1 = large >300 kW, 2 = medium 15-300 kW) and

support_type with the user when known.

  • The verdict requires a DECLARED signal unit. If it is refused, re-load with

load_signal(filepath="<file>", signal_unit="g", overwrite=True) after confirming the unit with the user — units are never guessed.

  • If only a portable-instrument reading is available (no signal file), use

assess_severity(rms_velocity_mm_s=3.2, machine_group=2, support_type="rigid").

Step 5 — Summary Card

Format the output as a concise screening card:

VIBRATION HEALTH SCREENING
===========================
Signal: {signal_id}
Overall: {Healthy / Monitor / Suspicious / Critical}
Key Indicators:
RMS: {value} | CF: {value} | Kurt: {value}
ISO Zone: {zone} ({severity})
Recommendation:
{appropriate next step}

Decision logic:

ISO ZoneKurtosisVerdictRecommendation
A< 1HealthyNo immediate concerns. Schedule routine monitoring.
B1–3MonitorElevated indicators. Schedule follow-up in 2–4 weeks.
C3–6SuspiciousConsider detailed bearing analysis (bearing-diagnosis skill).
D> 6CriticalImmediate detailed analysis recommended.

Important Notes

  • This is a SCREENING tool, NOT a diagnostic tool
  • Never make definitive fault claims from screening alone
  • Always recommend targeted analysis for Suspicious/Critical results
  • Use cautious language: "indicators suggest", not "confirmed fault"; a line at

1x or 2x attributes no unbalance, misalignment or looseness; they may be named as possible explanations next to the others (Step 3)

  • The screening supports the engineer's judgment; it does not replace it
  • All processing happens locally — raw data never leaves the machine

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
77
Repository forks
25
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 22 Aug 2026, 2 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/lgdimaggio/predictive-maintenance-mcp/quick-screening/badge)](https://verified-skill.com/skills/lgdimaggio/predictive-maintenance-mcp/quick-screening)

Something wrong with this skill or its page? Tell us.