product-spec-bulk-fetch

Name: product-spec-bulk-fetch
Author: AlpacaLabsLLC

260stars54forks

How to install product-spec-bulk-fetch?

alpacalabsllc/skills-for-architects/product-spec-bulk-fetch

$npx -y skills add AlpacaLabsLLC/skills-for-architects --skill product-spec-bulk-fetch

Installs into the current project.

Summary

Fetch structured FF&E product specs from a list of URLs — extracts name, brand, dimensions, materials, price, and images into a standardized schedule. Use when the user provides product URLs and asks to "pull specs", scrape product pages, or bulk-import items by link.

Files · 1

View on GitHub

SKILL.md

1	# /product-spec-bulk-fetch — Bulk Product Spec Fetcher
2
3	Extract structured FF&E data from a list of product page URLs. Outputs a standardized schedule ready for design specs, procurement, or import into [Norma](https://norma.llc).
4
5	## Input
6
7	The user provides product URLs in one of these ways:
8
9	1. Inline list — URLs pasted directly in the message (one per line, or comma-separated)
10	2. File path — A `.txt`, `.csv`, or `.md` file containing URLs (one per line)
11	3. Google Sheet column — A spreadsheet ID + column containing URLs to re-fetch
12
13	If the input format is unclear, ask.
14
15	## Output Schema
16
17	Products are written to the master Google Sheet — the same 33-column schema used by all product skills. When writing to CSV, use the same column order.
18
19	Read `../../schema/product-schema.md` (relative to this SKILL.md) for the full column reference, field formats, and category vocabulary. Read `../../schema/sheet-conventions.md` for CRUD patterns with MCP tools.
20
21	Skill-specific column values:
22	- AF (Status): `saved`
23	- AG (Source): `bulk-fetch`
24	- AD (Tags): Blank (set by user later)
25	- AE (Notes): Blank
26	- T (Selected Color/Finish): Blank (unknown from URL)
27
28	## Extraction Process
29
30	For each URL:
31
32	1. Fetch the page using WebFetch with the prompt below
33	2. Parse the response into the schema fields
34	3. Flag issues — missing price, missing dimensions, non-product page
35	4. Continue to next URL — never stop the batch on a single failure
36
37	### WebFetch Extraction Prompt
38
39	Use this prompt (or close variant) for each URL:
40
41	```
42	Extract structured product/furniture specification data from this page. Return a JSON object with these exact fields:
43
44	- product_name: Full product name (Title Case)
45	- description: Short description or tagline (1-2 sentences), or null
46	- sku: Product ID, SKU, model number, or catalog number, or null
47	- brand: Manufacturer name (Title Case)
48	- designer: Designer or design studio name if attributed, or null
49	- vendor: The retailer/website selling the product (may differ from brand), or null
50	- collection: Product line or collection name, or null
51	- category: One of: Chair, Table, Sofa, Bed, Light, Storage, Desk, Shelving, Rug, Mirror, Accessory, Tabletop, Kitchen, Bath, Window, Door, Outdoor Furniture, Textile, Acoustic, Planter, Partition, Other
52	- width: Numeric width value only (no units), or null
53	- depth: Numeric depth value only (no units), or null
54	- height: Numeric height value only (no units), or null
55	- seat_height: Numeric seat height for seating products, or null
56	- unit: "in", "cm", or "mm" — whichever the page uses
57	- weight: Weight as stated with unit (e.g. "45 lbs"), or null
58	- materials: Comma-separated list of primary materials
59	- colors_finishes: Comma-separated list of ALL available colors or finish options
60	- list_price: Numeric price (no currency symbol, no commas), or null
61	- sale_price: Discounted/sale price if shown, or null
62	- currency: "USD", "EUR", "GBP", etc.
63	- lead_time: Delivery estimate as stated, or null
64	- warranty: Warranty info as stated, or null
65	- certifications: Comma-separated certifications (GREENGUARD, FSC, BIFMA, etc.), or null
66	- com_col: "COM", "COL", "COM/COL" if mentioned, or null
67	- indoor_outdoor: "Indoor", "Outdoor", or "Indoor/Outdoor" if specified, or null
68	- image_url: URL of the primary product image (largest/hero image)
69
70	If this is NOT a product page, return: {"error": "not_a_product_page"}
71	If dimensions use a combined format like "32 x 24 x 30 in", split them into W x D x H.
72	If price says "Contact for pricing" or similar, set price to null.
73	Return ONLY the JSON object, no other text.
74	```
75
76	## Workflow
77
78	### Step 1: Parse input
79	Extract all URLs from the user's input. Report count: "Found N product URLs."
80
81	### Step 2: Fetch in parallel
82	Process URLs using WebFetch. Use parallel tool calls — fetch up to 5 URLs simultaneously to maximize speed. Report progress after each batch.
83
84	### Step 3: Compile results
85	Build a results table. Group into:
86	- Successful — all key fields extracted
87	- Partial — some fields missing (still include in output)
88	- Failed — non-product page or fetch error
89
90	### Step 4: Present results
91	Show a summary table in markdown with all successful + partial results. Flag any issues:
92	- "Price not found" for trade/dealer sites
93	- "Dimensions not found" if missing
94	- "Failed to fetch" for errors
95
96	### Step 5: Ask about output format
97	Ask the user: "Where should I save this?"
98	Options:
99	- **Master

People who liked this also viewed

6 picks

Type

product-spec-bulk-fetch

260stars54forks

View on GitHub

How to install product-spec-bulk-fetch?

alpacalabsllc/skills-for-architects/product-spec-bulk-fetch

$npx -y skills add AlpacaLabsLLC/skills-for-architects --skill product-spec-bulk-fetch

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /product-spec-bulk-fetch — Bulk Product Spec Fetcher
2
3	Extract structured FF&E data from a list of product page URLs. Outputs a standardized schedule ready for design specs, procurement, or import into [Norma](https://norma.llc).
4
5	## Input
6
7	The user provides product URLs in one of these ways:
8
9	1. Inline list — URLs pasted directly in the message (one per line, or comma-separated)
10	2. File path — A `.txt`, `.csv`, or `.md` file containing URLs (one per line)
11	3. Google Sheet column — A spreadsheet ID + column containing URLs to re-fetch
12
13	If the input format is unclear, ask.
14
15	## Output Schema
16
17	Products are written to the master Google Sheet — the same 33-column schema used by all product skills. When writing to CSV, use the same column order.
18
19	Read `../../schema/product-schema.md` (relative to this SKILL.md) for the full column reference, field formats, and category vocabulary. Read `../../schema/sheet-conventions.md` for CRUD patterns with MCP tools.
20
21	Skill-specific column values:
22	- AF (Status): `saved`
23	- AG (Source): `bulk-fetch`
24	- AD (Tags): Blank (set by user later)
25	- AE (Notes): Blank
26	- T (Selected Color/Finish): Blank (unknown from URL)
27
28	## Extraction Process
29
30	For each URL:
31
32	1. Fetch the page using WebFetch with the prompt below
33	2. Parse the response into the schema fields
34	3. Flag issues — missing price, missing dimensions, non-product page
35	4. Continue to next URL — never stop the batch on a single failure
36
37	### WebFetch Extraction Prompt
38
39	Use this prompt (or close variant) for each URL:
40
41	```
42	Extract structured product/furniture specification data from this page. Return a JSON object with these exact fields:
43
44	- product_name: Full product name (Title Case)
45	- description: Short description or tagline (1-2 sentences), or null
46	- sku: Product ID, SKU, model number, or catalog number, or null
47	- brand: Manufacturer name (Title Case)
48	- designer: Designer or design studio name if attributed, or null
49	- vendor: The retailer/website selling the product (may differ from brand), or null
50	- collection: Product line or collection name, or null
51	- category: One of: Chair, Table, Sofa, Bed, Light, Storage, Desk, Shelving, Rug, Mirror, Accessory, Tabletop, Kitchen, Bath, Window, Door, Outdoor Furniture, Textile, Acoustic, Planter, Partition, Other
52	- width: Numeric width value only (no units), or null
53	- depth: Numeric depth value only (no units), or null
54	- height: Numeric height value only (no units), or null
55	- seat_height: Numeric seat height for seating products, or null
56	- unit: "in", "cm", or "mm" — whichever the page uses
57	- weight: Weight as stated with unit (e.g. "45 lbs"), or null
58	- materials: Comma-separated list of primary materials
59	- colors_finishes: Comma-separated list of ALL available colors or finish options
60	- list_price: Numeric price (no currency symbol, no commas), or null
61	- sale_price: Discounted/sale price if shown, or null
62	- currency: "USD", "EUR", "GBP", etc.
63	- lead_time: Delivery estimate as stated, or null
64	- warranty: Warranty info as stated, or null
65	- certifications: Comma-separated certifications (GREENGUARD, FSC, BIFMA, etc.), or null
66	- com_col: "COM", "COL", "COM/COL" if mentioned, or null
67	- indoor_outdoor: "Indoor", "Outdoor", or "Indoor/Outdoor" if specified, or null
68	- image_url: URL of the primary product image (largest/hero image)
69
70	If this is NOT a product page, return: {"error": "not_a_product_page"}
71	If dimensions use a combined format like "32 x 24 x 30 in", split them into W x D x H.
72	If price says "Contact for pricing" or similar, set price to null.
73	Return ONLY the JSON object, no other text.
74	```
75
76	## Workflow
77
78	### Step 1: Parse input
79	Extract all URLs from the user's input. Report count: "Found N product URLs."
80
81	### Step 2: Fetch in parallel
82	Process URLs using WebFetch. Use parallel tool calls — fetch up to 5 URLs simultaneously to maximize speed. Report progress after each batch.
83
84	### Step 3: Compile results
85	Build a results table. Group into:
86	- Successful — all key fields extracted
87	- Partial — some fields missing (still include in output)
88	- Failed — non-product page or fetch error
89
90	### Step 4: Present results
91	Show a summary table in markdown with all successful + partial results. Flag any issues:
92	- "Price not found" for trade/dealer sites
93	- "Dimensions not found" if missing
94	- "Failed to fetch" for errors
95
96	### Step 5: Ask about output format
97	Ask the user: "Where should I save this?"
98	Options:
99	- **Master

People who liked this also viewed

6 picks

Type