القائمة
Overall Equipment Effectiveness calculation skill with loss categorization and improvement analysis.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/a5c-ai/babysitter --skill oee-calculatorيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | oee-calculator |
| description | Overall Equipment Effectiveness calculation skill with loss categorization and improvement analysis. |
| allowed-tools | Bash(*) Read Write Edit Glob Grep WebFetch |
| metadata | {"author":"babysitter-sdk","version":"1.0.0","category":"production-planning","backlog-id":"SK-IE-031"} |
| graph | {"domains":["domain:industrial-engineering"],"skillAreas":["skill-area:statistical-analysis","skill-area:organizational-design","skill-area:data-analysis"],"roles":["role:operations-analyst","role:research-engineer"]} |
You are oee-calculator - a specialized skill for calculating Overall Equipment Effectiveness (OEE) and analyzing equipment losses.
This skill enables AI-powered OEE analysis including:
pandas pd
numpy np
datetime datetime, timedelta
():
planned_time = production_data[]
run_time = production_data[]
downtime = planned_time - run_time
availability = (run_time / planned_time) * planned_time >
ideal_cycle = production_data[]
total_count = production_data[]
ideal_run_time = total_count * ideal_cycle
performance = (ideal_run_time / run_time) * run_time >
performance = (performance, )
good_count = production_data[]
quality = (good_count / total_count) * total_count >
oee = (availability / ) * (performance / ) * (quality / ) *
{
: (oee, ),
: (availability, ),
: (performance, ),
: (quality, ),
: {
: planned_time,
: run_time,
: downtime,
: total_count,
: good_count,
: total_count - good_count
}
}
def analyze_six_big_losses(loss_data: dict):
"""
Categorize and analyze the Six Big Losses
loss_data:
- breakdowns: minutes
- setup_adjustments: minutes
- minor_stops: minutes
- reduced_speed: minutes (calculated from speed losses)
- startup_rejects: units
- production_rejects: units
- planned_time: minutes
- ideal_cycle_time: minutes/unit
"""
planned_time = loss_data['planned_time']
ideal_cycle = loss_data['ideal_cycle_time']
# Availability Losses
breakdowns = loss_data.get('breakdowns', 0)
setup_adjustments = loss_data.get('setup_adjustments', 0)
availability_losses = breakdowns + setup_adjustments
# Performance Losses
minor_stops = loss_data.get('minor_stops', 0)
reduced_speed = loss_data.get('reduced_speed', 0)
performance_losses = minor_stops + reduced_speed
# Quality Losses (convert to time equivalent)
startup_rejects = loss_data.get('startup_rejects', 0)
production_rejects = loss_data.get('production_rejects', 0)
quality_losses = (startup_rejects + production_rejects) * ideal_cycle
# Total losses
total_losses = availability_losses + performance_losses + quality_losses
losses = {
"availability_losses": {
"breakdowns": {"minutes": breakdowns, "percent": breakdowns / planned_time * 100},
"setup_adjustments": {"minutes": setup_adjustments, "percent": setup_adjustments / planned_time * 100},
"subtotal": availability_losses
},
"performance_losses": {
"minor_stops": {"minutes": minor_stops, "percent": minor_stops / planned_time * 100},
"reduced_speed": {"minutes": reduced_speed, "percent": reduced_speed / planned_time * 100},
"subtotal": performance_losses
},
"quality_losses": {
"startup_rejects": {"units": startup_rejects, "time_equivalent": startup_rejects * ideal_cycle},
"production_rejects": {"units": production_rejects, "time_equivalent": production_rejects * ideal_cycle},
"subtotal": quality_losses
},
"total_loss_time": total_losses,
"productive_time": planned_time - total_losses,
"loss_percent": total_losses / planned_time * 100
}
return losses
def calculate_teep(production_data: dict, calendar_time_hours: float = 24):
"""
Calculate Total Effective Equipment Performance
TEEP = OEE x Loading
Loading = Planned Production Time / Calendar Time
"""
# First calculate OEE
oee_result = calculate_oee(production_data)
# Calculate Loading
planned_time_hours = production_data['planned_production_time'] / 60
loading = (planned_time_hours / calendar_time_hours) * 100
# TEEP
teep = (oee_result['oee'] / 100) * (loading / 100) * 100
return {
"teep": round(teep, 1),
"oee": oee_result['oee'],
"loading": round(loading, 1),
"calendar_time_hours": calendar_time_hours,
"planned_time_hours": planned_time_hours,
"interpretation": interpret_teep(teep)
}
def interpret_teep(teep):
if teep >= 90:
return "World-class - exceptional asset utilization"
elif teep >= 70:
return "Good - some improvement opportunity"
elif teep >= 50:
return "Average - significant improvement potential"
else:
return "Low - major improvement needed"
def oee_trend_analysis(historical_data: pd.DataFrame):
"""
Analyze OEE trends over time
historical_data: DataFrame with columns ['date', 'oee', 'availability', 'performance', 'quality']
"""
historical_data = historical_data.sort_values('date')
# Calculate moving averages
historical_data['oee_ma7'] = historical_data['oee'].rolling(window=7).mean()
historical_data['oee_ma30'] = historical_data['oee'].rolling(window=30).mean()
# Calculate trend
if len(historical_data) >= 7:
recent = historical_data.tail(7)['oee'].mean()
previous = historical_data.tail(14).head(7)['oee'].mean() if len(historical_data) >= 14 else recent
trend = recent - previous
else:
trend = 0
# Find best and worst days
best_day = historical_data.loc[historical_data['oee'].idxmax()]
worst_day = historical_data.loc[historical_data['oee'].idxmin()]
# Identify limiting factor
means = {
'availability': historical_data['availability'].mean(),
'performance': historical_data['performance'].mean(),
'quality': historical_data['quality'].mean()
}
limiting_factor = min(means, key=means.get)
return {
"current_oee": round(historical_data['oee'].iloc[-1], 1),
"average_oee": round(historical_data['oee'].mean(), 1),
"trend": round(trend, 1),
"trend_direction": "improving" if trend > 0 else "declining" if trend < 0 else "stable",
"best_day": {"date": str(best_day['date']), "oee": best_day['oee']},
"worst_day": {"date": str(worst_day['date']), "oee": worst_day['oee']},
"limiting_factor": limiting_factor,
"component_averages": means
}
def create_loss_waterfall(planned_time: float, losses: dict):
"""
Create waterfall data showing progression from planned time to productive time
"""
waterfall = [
{"category": "Planned Time", "value": planned_time, "type": "total"},
{"category": "Breakdowns", "value": -losses['breakdowns'], "type": "loss"},
{"category": "Changeovers", "value": -losses['setup_adjustments'], "type": "loss"},
{"category": "Minor Stops", "value": -losses['minor_stops'], "type": "loss"},
{"category": "Speed Loss", "value": -losses['reduced_speed'], "type": "loss"},
{"category": "Startup Rejects", "value": -losses['startup_rejects_time'], "type": "loss"},
{"category": "Production Rejects", "value": -losses['production_rejects_time'], "type": "loss"}
]
running_total = planned_time
for item in waterfall[1:]:
running_total += item['value']
item['running_total'] = running_total
waterfall.append({
"category": "Productive Time",
"value": running_total,
"type": "result"
})
return {
"waterfall": waterfall,
"total_losses": planned_time - running_total,
"loss_percentage": (planned_time - running_total) / planned_time * 100
}
def identify_improvement_opportunities(oee_data: dict, losses: dict, benchmarks: dict = None):
"""
Identify and prioritize OEE improvement opportunities
"""
benchmarks = benchmarks or {
'world_class_oee': 85,
'world_class_availability': 90,
'world_class_performance': 95,
'world_class_quality': 99.9
}
opportunities = []
# Availability opportunities
avail_gap = benchmarks['world_class_availability'] - oee_data['availability']
if avail_gap > 0:
opportunities.append({
'component': 'Availability',
'current': oee_data['availability'],
'target': benchmarks['world_class_availability'],
'gap': avail_gap,
'primary_losses': ['breakdowns', 'setup_adjustments'],
'potential_oee_gain': calculate_oee_impact(oee_data, 'availability', avail_gap)
})
# Performance opportunities
perf_gap = benchmarks['world_class_performance'] - oee_data['performance']
if perf_gap > 0:
opportunities.append({
'component': 'Performance',
'current': oee_data['performance'],
'target': benchmarks['world_class_performance'],
'gap': perf_gap,
'primary_losses': ['minor_stops', 'reduced_speed'],
'potential_oee_gain': calculate_oee_impact(oee_data, 'performance', perf_gap)
})
# Quality opportunities
qual_gap = benchmarks['world_class_quality'] - oee_data['quality']
if qual_gap > 0:
opportunities.append({
'component': 'Quality',
'current': oee_data['quality'],
'target': benchmarks['world_class_quality'],
'gap': qual_gap,
'primary_losses': ['startup_rejects', 'production_rejects'],
'potential_oee_gain': calculate_oee_impact(oee_data, 'quality', qual_gap)
})
# Sort by potential gain
opportunities.sort(key=lambda x: x['potential_oee_gain'], reverse=True)
return {
"opportunities": opportunities,
"total_potential_gain": benchmarks['world_class_oee'] - oee_data['oee'],
"priority_focus": opportunities[0]['component'] if opportunities else None
}
def calculate_oee_impact(current: dict, component: str, improvement: float):
"""Calculate OEE impact of improving one component"""
a = current['availability'] + (improvement if component == 'availability' else 0)
p = current['performance'] + (improvement if component == 'performance' else 0)
q = current['quality'] + (improvement if component == 'quality' else 0)
new_oee = (a / 100) * (p / 100) * (q / 100) * 100
return new_oee - current['oee']
This skill integrates with the following processes:
equipment-effectiveness-analysis.jstpm-implementation.jscontinuous-improvement-program.js{
"oee_summary": {
"oee": 72.5,
"availability": 85.0,
"performance": 92.0,
"quality": 92.7
},
"losses": {
"availability_losses": {"breakdowns": 45, "changeovers": 30},
"performance_losses": {"minor_stops": 20, "speed_loss": 15},
"quality_losses": {"rejects": 150}
},
"improvement_opportunities": [
{"component": "Availability", "gap": 5.0, "potential_gain": 4.2}
],
"recommendations": [
"Focus on reducing breakdown frequency",
"Implement SMED for changeover reduction"
]
}