메뉴
Warehouse slotting and layout optimization skill for pick path minimization and space utilization.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/a5c-ai/babysitter --skill warehouse-slotting-optimizer명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
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/.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | warehouse-slotting-optimizer |
| description | Warehouse slotting and layout optimization skill for pick path minimization and space utilization. |
| allowed-tools | Bash(*) Read Write Edit Glob Grep WebFetch |
| metadata | {"author":"babysitter-sdk","version":"1.0.0","category":"supply-chain","backlog-id":"SK-IE-026"} |
| 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 warehouse-slotting-optimizer - a specialized skill for optimizing warehouse slotting and layout to minimize pick paths and maximize space utilization.
This skill enables AI-powered warehouse optimization including:
pandas pd
numpy np
():
sku_picks = order_data.groupby().agg({
: ,
:
}).rename(columns={: })
sku_picks = sku_picks.sort_values(, ascending=)
total_picks = sku_picks[].()
sku_picks[] = sku_picks[].cumsum()
sku_picks[] = sku_picks[] / total_picks *
():
pct <= :
pct <= :
:
sku_picks[] = sku_picks[].apply(assign_velocity)
{
: sku_picks,
: {
: (sku_picks),
: (sku_picks[sku_picks[] == ]),
: (sku_picks[sku_picks[] == ]),
: (sku_picks[sku_picks[] == ])
}
}
def optimize_golden_zone(skus: pd.DataFrame, warehouse_config: dict):
"""
Optimize placement in golden zone (ergonomic prime picking zone)
Golden zone: waist to shoulder height, immediate reach
"""
golden_zone = warehouse_config.get('golden_zone', {
'height_min': 24, # inches from floor
'height_max': 54,
'reach_max': 24 # inches from aisle
})
# Calculate golden zone capacity
rack_config = warehouse_config.get('rack', {
'bays': 100,
'levels': 5,
'positions_per_bay': 3
})
# Levels in golden zone (typically levels 2-3 of 5)
golden_levels = [2, 3] # Assuming 5 levels
golden_positions = (rack_config['bays'] *
len(golden_levels) *
rack_config['positions_per_bay'])
# Sort SKUs by pick frequency
fast_skus = skus[skus['velocity_class'] == 'Fast'].copy()
fast_skus = fast_skus.sort_values('pick_count', ascending=False)
# Assign to golden zone
assignments = []
position_count = 0
for idx, row in fast_skus.iterrows():
if position_count < golden_positions:
assignments.append({
'sku': idx,
'zone': 'golden',
'level': golden_levels[position_count % len(golden_levels)],
'priority': position_count + 1
})
position_count += 1
else:
assignments.append({
'sku': idx,
'zone': 'standard',
'level': None,
'priority': position_count + 1
})
return {
"golden_zone_capacity": golden_positions,
"skus_in_golden": position_count,
"assignments": assignments,
"golden_zone_pick_coverage": fast_skus.head(golden_positions)['pick_count'].sum() /
skus['pick_count'].sum() * 100
}
def optimize_pick_path(picks: list, warehouse_layout: dict):
"""
Optimize pick path through warehouse
Uses traveling salesman heuristic
"""
from scipy.spatial.distance import cdist
import itertools
# Get location coordinates for picks
locations = []
for pick in picks:
loc = warehouse_layout['locations'].get(pick['location'])
if loc:
locations.append((pick['location'], loc['x'], loc['y']))
# Calculate distance matrix
coords = np.array([(l[1], l[2]) for l in locations])
dist_matrix = cdist(coords, coords)
# Nearest neighbor heuristic
n = len(locations)
visited = [False] * n
path = [0] # Start at first location
visited[0] = True
for _ in range(n - 1):
current = path[-1]
nearest = None
nearest_dist = float('inf')
for j in range(n):
if not visited[j] and dist_matrix[current][j] < nearest_dist:
nearest = j
nearest_dist = dist_matrix[current][j]
if nearest is not None:
path.append(nearest)
visited[nearest] = True
# Calculate total distance
total_distance = sum(dist_matrix[path[i]][path[i+1]]
for i in range(len(path)-1))
# Return optimized sequence
optimized_picks = [picks[i] for i in path]
return {
"optimized_sequence": optimized_picks,
"total_distance": total_distance,
"locations_count": n,
"estimated_time_minutes": total_distance / warehouse_layout.get('walk_speed', 100) * 60
}
def size_forward_pick_area(sku_data: pd.DataFrame, replenishment_cost: float,
space_cost_per_unit: float):
"""
Determine optimal forward pick area size
Balance replenishment cost vs. space cost
"""
# Sort by velocity
sku_data = sku_data.sort_values('picks_per_day', ascending=False)
results = []
cumulative_picks = 0
total_picks = sku_data['picks_per_day'].sum()
for i, (idx, row) in enumerate(sku_data.iterrows()):
cumulative_picks += row['picks_per_day']
pick_coverage = cumulative_picks / total_picks
# Estimate costs
forward_skus = i + 1
space_cost = forward_skus * row.get('cube', 1) * space_cost_per_unit
replen_trips = sku_data.head(forward_skus)['picks_per_day'].sum() / \
sku_data.head(forward_skus)['case_qty'].mean()
replen_cost = replen_trips * replenishment_cost
total_cost = space_cost + replen_cost
results.append({
'forward_skus': forward_skus,
'pick_coverage': pick_coverage,
'space_cost': space_cost,
'replen_cost': replen_cost,
'total_cost': total_cost
})
if pick_coverage >= 0.95:
break
# Find optimal
optimal = min(results, key=lambda x: x['total_cost'])
return {
"analysis": results,
"optimal_forward_skus": optimal['forward_skus'],
"pick_coverage": optimal['pick_coverage'],
"total_cost": optimal['total_cost']
}
def slot_assignment(skus: pd.DataFrame, locations: pd.DataFrame,
constraints: dict = None):
"""
Assign SKUs to warehouse locations
Considers:
- Velocity (fast movers to best locations)
- Cube (size compatibility)
- Weight (heavy items at floor level)
- Family grouping (related items together)
"""
constraints = constraints or {}
# Score each location
def score_location(loc):
score = 0
# Distance from shipping (lower is better)
score -= loc.get('distance_to_ship', 0) * 0.01
# Ergonomic zone bonus
if 24 <= loc.get('height', 0) <= 54:
score += 10
# Ground level for heavy
if loc.get('level', 0) == 1:
score += 5
return score
locations['score'] = locations.apply(score_location, axis=1)
locations = locations.sort_values('score', ascending=False)
# Sort SKUs by assignment priority
skus['priority'] = skus['picks_per_day'] * 100 - skus.get('cube', 1)
skus = skus.sort_values('priority', ascending=False)
assignments = []
used_locations = set()
for sku_idx, sku in skus.iterrows():
for loc_idx, loc in locations.iterrows():
if loc_idx in used_locations:
continue
# Check constraints
if sku.get('cube', 1) > loc.get('capacity', float('inf')):
continue
if sku.get('weight', 0) > loc.get('weight_limit', float('inf')):
continue
# Assign
assignments.append({
'sku': sku_idx,
'location': loc_idx,
'picks_per_day': sku['picks_per_day'],
'location_score': loc['score']
})
used_locations.add(loc_idx)
break
return {
"assignments": assignments,
"assigned_count": len(assignments),
"unassigned_skus": len(skus) - len(assignments)
}
def calculate_slotting_metrics(current_slotting: pd.DataFrame,
order_history: pd.DataFrame,
warehouse_config: dict):
"""
Calculate slotting performance metrics
"""
metrics = {}
# Pick density (picks per foot traveled)
total_picks = len(order_history)
# Estimate travel based on current slotting
travel_estimate = estimate_total_travel(current_slotting, order_history, warehouse_config)
metrics['pick_density'] = total_picks / travel_estimate if travel_estimate > 0 else 0
# Golden zone utilization
golden_picks = order_history.merge(current_slotting, on='sku')
golden_picks = golden_picks[golden_picks['zone'] == 'golden']
metrics['golden_zone_pick_pct'] = len(golden_picks) / total_picks * 100
# Slot utilization
total_slots = len(current_slotting)
active_slots = current_slotting[current_slotting['picks_per_day'] > 0]
metrics['slot_utilization'] = len(active_slots) / total_slots * 100
# Velocity alignment score (are fast movers in best spots?)
current_slotting = current_slotting.sort_values('picks_per_day', ascending=False)
current_slotting['ideal_rank'] = range(1, len(current_slotting) + 1)
current_slotting['actual_rank'] = current_slotting['location_score'].rank(ascending=False)
correlation = current_slotting['ideal_rank'].corr(current_slotting['actual_rank'])
metrics['velocity_alignment'] = correlation
return metrics
def estimate_total_travel(slotting, orders, config):
# Simplified travel estimation
avg_picks_per_order = len(orders) / orders['order_id'].nunique()
avg_travel_per_pick = config.get('avg_aisle_length', 100) / 2
return len(orders) * avg_travel_per_pick
This skill integrates with the following processes:
warehouse-layout-slotting-optimization.jsinventory-optimization-analysis.js{
"velocity_analysis": {
"fast_movers": 150,
"medium_movers": 450,
"slow_movers": 2400
},
"golden_zone": {
"capacity": 300,
"pick_coverage": 72.5
},
"slotting_metrics": {
"pick_density": 2.3,
"velocity_alignment": 0.85
},
"recommendations": [
"Move top 50 SKUs to golden zone",
"Consider forward pick area for 200 SKUs"
]
}