product-data-cleanup

Name: product-data-cleanup
Author: AlpacaLabsLLC

260stars54forks

How to install product-data-cleanup?

alpacalabsllc/skills-for-architects/product-data-cleanup

$npx -y skills add AlpacaLabsLLC/skills-for-architects --skill product-data-cleanup

Installs into the current project.

Summary

Clean up an FF&E schedule — normalize casing, dimensions, units, language, materials, and formatting for consistency. Use when the user asks to "clean up the schedule", fix inconsistent product data, or standardize an FF&E sheet.

Files · 1

View on GitHub

SKILL.md

1	# /product-data-cleanup — Product Data Normalizer
2
3	Takes a messy FF&E schedule and normalizes everything: casing, dimensions, units, language, materials vocabulary, currency formatting, and duplicates. Outputs a clean, consistent, spec-ready schedule.
4
5	Operates on the master Google Sheet — the same 33-column schema used by all product skills. Also works on standalone CSV files and pasted tables.
6
7	## Input
8
9	The user provides a schedule in one of these ways:
10
11	1. Master Google Sheet — the shared product library. Provide spreadsheet ID or URL.
12	2. File path — a `.csv`, `.tsv`, `.xlsx` export, or `.md` file
13	3. Pasted table — markdown or tab-separated data in the message
14
15	If the input format is unclear, ask.
16
17	## Cleanup Rules
18
19	### 1. Casing
20
21	\| Field \| Rule \| Example \|
22	\|-------\|------\|---------\|
23	\| Product Name \| Title Case \| `eames lounge chair` → `Eames Lounge Chair` \|
24	\| Brand \| Title Case, preserve known abbreviations \| `HERMAN MILLER` → `Herman Miller`, `HAY` → `HAY` \|
25	\| Collection \| Title Case \| `cosm` → `Cosm` \|
26	\| Category \| Title Case, singular \| `chairs` → `Chair`, `TABLES` → `Table` \|
27	\| Materials \| Sentence case, lowercase after first word \| `MOLDED PLYWOOD, FULL GRAIN LEATHER` → `Molded plywood, full grain leather` \|
28	\| Colors/Finishes \| Title Case per item \| `walnut/black leather` → `Walnut / Black Leather` \|
29
30	Known brand abbreviations to preserve: HAY, USM, B&B, DWR, CB2, HBF, OFS, SitOnIt, 3form, ICF
31
32	### 2. Category Normalization
33
34	Map free-text categories to the canonical vocabulary and alias table defined in `../../schema/product-schema.md`. Read that file for the full mapping of variations (English, Spanish, legacy terms) to canonical category names.
35
36	If a category is ambiguous, keep the closest match and add a `[?]` flag for the user to review.
37
38	### 3. Dimensions
39
40	Splitting combined dimensions:
41	\| Input \| → W \| → D \| → H \| → Unit \|
42	\|-------\|-----\|-----\|-----\|--------\|
43	\| `32 x 24 x 30 in` \| 32 \| 24 \| 30 \| in \|
44	\| `80 × 60 × 75 cm` \| 80 \| 60 \| 75 \| cm \|
45	\| `W32 D24 H30` \| 32 \| 24 \| 30 \| (infer) \|
46	\| `32"W x 24"D x 30"H` \| 32 \| 24 \| 30 \| in \|
47	\| `Ancho: 80, Prof: 60, Alto: 75 cm` \| 80 \| 60 \| 75 \| cm \|
48
49	Dimension rules:
50	- Always store as separate W, D, H columns with a Unit column
51	- If dimensions are already split, validate they're numeric (strip any unit text from the number)
52	- Interpret `"` as inches, `'` as feet (convert to inches: `2'6"` → `30`)
53	- Accept `×`, `x`, `X`, `by`, `por` as separators
54	- Convention: W × D × H (width × depth × height). If only 2 values, ask which is missing.
55	- Round to 2 decimal places max
56	- If unit is missing but values suggest inches (all < 100 for furniture), assume `in`. If values suggest cm (> 100 or explicit), use `cm`. If truly ambiguous, flag with `[?]`.
57
58	Do NOT convert units. Keep the original unit. Designers need the manufacturer's spec for ordering.
59
60	### 4. Language Normalization
61
62	Detect the language of each field value and normalize to English unless the user specifies otherwise.
63
64	\| Spanish (common in UY sources) \| → English \|
65	\|-------------------------------\|-----------\|
66	\| Silla \| Chair (category) \|
67	\| Mesa \| Table (category) \|
68	\| Escritorio \| Desk (category) \|
69	\| Madera \| Wood (material) \|
70	\| Cuero \| Leather (material) \|
71	\| Acero \| Steel (material) \|
72	\| Vidrio \| Glass (material) \|
73	\| Tela \| Fabric (material) \|
74	\| Mármol \| Marble (material) \|
75	\| Roble \| Oak (material) \|
76	\| Nogal \| Walnut (material) \|
77	\| Blanco \| White (color) \|
78	\| Negro \| Black (color) \|
79	\| Natural \| Natural (keep as-is) \|
80	\| Cromado \| Chrome (finish) \|
81
82	Rule: Translate category, material, and color/finish fields. Leave Product Name and Brand as-is (proper nouns).
83
84	If the user says "keep in Spanish" or specifies a target language, respect that.
85
86	### 5. Materials & Finishes Vocabulary
87
88	Standardize common material terms:
89
90	\| Variations \| → Standard \|
91	\|-----------\|------------\|
92	\| SS, Stainless, S/S \| Stainless steel \|
93	\| Ply, Plywood, Mold ply \| Molded plywood \|
94	\| MDF, Medium density \| MDF \|
95	\| HPL, High pressure laminate \| HPL \|
96	\| Lam, Laminate \| Laminate \|
97	\| Fab, Textile \| Fabric \|
98	\| COM, C.O.M. \| COM (Customer's Own Material) \|
99	\| COL, C.O.L. \| COL (Customer's Own Leather) \|
100	\| Powder coat, PC, Pwdr \| Powder-coated \|
101	\| Chrm, Chrome plated \| Chrome \|
102	\| Anodized alum, Anod. \| Anodized aluminum \|
103	\| Ven, Veneer \| Veneer \|
104	\| Sol. wood, Solid \| Solid wood \|
105
106	### 6. Price & Currency
107
108	- Strip currency symbols (`$`, `€`, `£`, `¥`) — store symbol as currency code in separate column
109	- Remove thousands separators

People who liked this also viewed

6 picks

Type

product-data-cleanup

260stars54forks

View on GitHub

How to install product-data-cleanup?

alpacalabsllc/skills-for-architects/product-data-cleanup

$npx -y skills add AlpacaLabsLLC/skills-for-architects --skill product-data-cleanup

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /product-data-cleanup — Product Data Normalizer
2
3	Takes a messy FF&E schedule and normalizes everything: casing, dimensions, units, language, materials vocabulary, currency formatting, and duplicates. Outputs a clean, consistent, spec-ready schedule.
4
5	Operates on the master Google Sheet — the same 33-column schema used by all product skills. Also works on standalone CSV files and pasted tables.
6
7	## Input
8
9	The user provides a schedule in one of these ways:
10
11	1. Master Google Sheet — the shared product library. Provide spreadsheet ID or URL.
12	2. File path — a `.csv`, `.tsv`, `.xlsx` export, or `.md` file
13	3. Pasted table — markdown or tab-separated data in the message
14
15	If the input format is unclear, ask.
16
17	## Cleanup Rules
18
19	### 1. Casing
20
21	\| Field \| Rule \| Example \|
22	\|-------\|------\|---------\|
23	\| Product Name \| Title Case \| `eames lounge chair` → `Eames Lounge Chair` \|
24	\| Brand \| Title Case, preserve known abbreviations \| `HERMAN MILLER` → `Herman Miller`, `HAY` → `HAY` \|
25	\| Collection \| Title Case \| `cosm` → `Cosm` \|
26	\| Category \| Title Case, singular \| `chairs` → `Chair`, `TABLES` → `Table` \|
27	\| Materials \| Sentence case, lowercase after first word \| `MOLDED PLYWOOD, FULL GRAIN LEATHER` → `Molded plywood, full grain leather` \|
28	\| Colors/Finishes \| Title Case per item \| `walnut/black leather` → `Walnut / Black Leather` \|
29
30	Known brand abbreviations to preserve: HAY, USM, B&B, DWR, CB2, HBF, OFS, SitOnIt, 3form, ICF
31
32	### 2. Category Normalization
33
34	Map free-text categories to the canonical vocabulary and alias table defined in `../../schema/product-schema.md`. Read that file for the full mapping of variations (English, Spanish, legacy terms) to canonical category names.
35
36	If a category is ambiguous, keep the closest match and add a `[?]` flag for the user to review.
37
38	### 3. Dimensions
39
40	Splitting combined dimensions:
41	\| Input \| → W \| → D \| → H \| → Unit \|
42	\|-------\|-----\|-----\|-----\|--------\|
43	\| `32 x 24 x 30 in` \| 32 \| 24 \| 30 \| in \|
44	\| `80 × 60 × 75 cm` \| 80 \| 60 \| 75 \| cm \|
45	\| `W32 D24 H30` \| 32 \| 24 \| 30 \| (infer) \|
46	\| `32"W x 24"D x 30"H` \| 32 \| 24 \| 30 \| in \|
47	\| `Ancho: 80, Prof: 60, Alto: 75 cm` \| 80 \| 60 \| 75 \| cm \|
48
49	Dimension rules:
50	- Always store as separate W, D, H columns with a Unit column
51	- If dimensions are already split, validate they're numeric (strip any unit text from the number)
52	- Interpret `"` as inches, `'` as feet (convert to inches: `2'6"` → `30`)
53	- Accept `×`, `x`, `X`, `by`, `por` as separators
54	- Convention: W × D × H (width × depth × height). If only 2 values, ask which is missing.
55	- Round to 2 decimal places max
56	- If unit is missing but values suggest inches (all < 100 for furniture), assume `in`. If values suggest cm (> 100 or explicit), use `cm`. If truly ambiguous, flag with `[?]`.
57
58	Do NOT convert units. Keep the original unit. Designers need the manufacturer's spec for ordering.
59
60	### 4. Language Normalization
61
62	Detect the language of each field value and normalize to English unless the user specifies otherwise.
63
64	\| Spanish (common in UY sources) \| → English \|
65	\|-------------------------------\|-----------\|
66	\| Silla \| Chair (category) \|
67	\| Mesa \| Table (category) \|
68	\| Escritorio \| Desk (category) \|
69	\| Madera \| Wood (material) \|
70	\| Cuero \| Leather (material) \|
71	\| Acero \| Steel (material) \|
72	\| Vidrio \| Glass (material) \|
73	\| Tela \| Fabric (material) \|
74	\| Mármol \| Marble (material) \|
75	\| Roble \| Oak (material) \|
76	\| Nogal \| Walnut (material) \|
77	\| Blanco \| White (color) \|
78	\| Negro \| Black (color) \|
79	\| Natural \| Natural (keep as-is) \|
80	\| Cromado \| Chrome (finish) \|
81
82	Rule: Translate category, material, and color/finish fields. Leave Product Name and Brand as-is (proper nouns).
83
84	If the user says "keep in Spanish" or specifies a target language, respect that.
85
86	### 5. Materials & Finishes Vocabulary
87
88	Standardize common material terms:
89
90	\| Variations \| → Standard \|
91	\|-----------\|------------\|
92	\| SS, Stainless, S/S \| Stainless steel \|
93	\| Ply, Plywood, Mold ply \| Molded plywood \|
94	\| MDF, Medium density \| MDF \|
95	\| HPL, High pressure laminate \| HPL \|
96	\| Lam, Laminate \| Laminate \|
97	\| Fab, Textile \| Fabric \|
98	\| COM, C.O.M. \| COM (Customer's Own Material) \|
99	\| COL, C.O.L. \| COL (Customer's Own Leather) \|
100	\| Powder coat, PC, Pwdr \| Powder-coated \|
101	\| Chrm, Chrome plated \| Chrome \|
102	\| Anodized alum, Anod. \| Anodized aluminum \|
103	\| Ven, Veneer \| Veneer \|
104	\| Sol. wood, Solid \| Solid wood \|
105
106	### 6. Price & Currency
107
108	- Strip currency symbols (`$`, `€`, `£`, `¥`) — store symbol as currency code in separate column
109	- Remove thousands separators

People who liked this also viewed

6 picks

Type