mcpbeat Sign in

CSV To Sif Agent Skill

Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.

3k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
302
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AlpacaLabsLLC/skills-for-architects --skill csv-to-sif

What comes with it

1 987 bytes besides the instruction
README.md

The instruction itself

18 sections, as written by the author

/as:csv-to-sif — CSV to SIF Converter

Converts the nearest project's product-library.csv into a SIF output file for dealer and procurement systems such as Hedberg, CAP, CET, Cyncly Worksheet, ProjectMatrix, Studio Webware, and Design Manager.

When to Use

  • Sending a specification to a dealer for quoting
  • Importing product data into a dealer management system
  • Sharing a standardized product list with procurement
  • Converting an FF&E schedule into a format dealers expect

SIF Format Reference

SIF is a text-based key-value format. Each line is CODE=VALUE, terminated by CRLF. Products are separated by records starting with PN=.

Core fields

| Code | Name | Required | Description |

|------|------|----------|-------------|

| SF | Specification File | No | Project reference (header, once per file) |

| ST | Specification Title | No | Display title (header, once per file) |

| PN | Product Number | Yes | SKU or model number. Marks the start of a new record. |

| PD | Product Description | Yes | Product name and description |

| MC | Manufacturer Code | Yes | 3-5 character code (HMI, KNL, STC) |

| MN | Manufacturer Name | No | Full manufacturer name |

| QT | Quantity | Yes | Integer quantity |

| NT | Quantity (alt) | No | Some systems use NT instead of QT |

| GC | Category / Group Code | No | Product category |

| G0 | Vendor / Group ID | No | Vendor or dealer identifier |

Pricing fields

| Code | Name | Description |

|------|------|-------------|

| PL | List Price | Unit list price (numeric, no currency symbol) |

| P1 | Price Tier 1 | Primary price (some systems use P1 instead of PL) |

| P2 | Price Tier 2 | Alternate price tier |

| P4 | Price Tier 4 | Alternate price tier |

| P5 | Price Tier 5 | Alternate price tier |

| I1 | Unit List Price (Cyncly) | Used by Cyncly Worksheet |

| I2 | Purchase Price (Cyncly) | Used by Cyncly Worksheet |

| S- / S% | Sell Discount % | Sell = PL - (PL × S- × 0.01) |

| P% / B% | Purchase/Buy % | Cost = PL × (P% × 0.01) |

Product detail fields

| Code | Name | Description |

|------|------|-------------|

| TG | Side Mark / Tag | Room name, area code, or project tag |

| ON | Option Number | Must pair with OD |

| OD | Option Description | Finish, fabric, color selection |

| AN | Attribute Number | Must pair with AD |

| AD | Attribute Description | Dimension, weight, or other attribute |

| WT | Weight | Product weight |

| VO | Volume | Product volume |

| PRC | Product Category (Cyncly) | Category for Cyncly Worksheet |

| Code | Name | Description |

|------|------|-------------|

| ProductURL | Product Page URL | Link to manufacturer product page |

| ImageURL | Product Image URL | Link to product image |

| PV | Picture Path | Windows bitmap or TIF file path |

Alternate manufacturer codes (by system)

| System | Code | Purpose |

|--------|------|---------|

| Standard | MC | 3-5 char manufacturer code |

| Cyncly Worksheet | MG | Manufacturer code (replaces MC) |

| Cyncly Worksheet | MN | Full manufacturer name |

| CET / Configura | EC | Manufacturer code (alt) |

File structure example

SF=Project Alpha - FF&E Specification
ST=FF&E Schedule — March 2026
PN=670
PD=Eames Lounge Chair and Ottoman
MC=HMI
MN=Herman Miller
GC=Seating
QT=3
PL=5695.00
WT=92
TG=Executive Lounge
OD=Santos Palisander / Black MCL Leather
AN=DIM
AD=32.75W x 32.5D x 33.5H in
ProductURL=https://www.hermanmiller.com/products/seating/lounge-seating/eames-lounge-chair-and-ottoman/
ImageURL=https://www.hermanmiller.com/content/dam/hmicom/page_assets/products/eames_lounge_chair_and_ottoman/mh_prd_ovw_eames_lounge_chair_and_ottoman.jpg

PN=164-500
PD=Saarinen Round Dining Table 54"
MC=KNL
MN=Knoll
GC=Tables
QT=1
PL=4750.00
TG=Dining Area
OD=Arabescato Marble Top / White Base
AN=DIM
AD=54dia x 28.5H in

Rules

  • Each line is one field: CODE=VALUE
  • Lines terminated by CRLF
  • Blank line between records
  • PN starts a new record — must come first in each record
  • ON/OD and AN/AD pairs must stay together
  • No embedded line breaks within a field value
  • Empty values use CODE= with nothing after the equals sign

Step 1: Accept Input

Read ../../schema/product-schema.md and ../../schema/csv-conventions.md. Default to the nearest ancestor containing PROJECT.md and validate its product-library.csv with python3 "${CLAUDE_PLUGIN_ROOT}/skills/master-schedule/scripts/csv-library.py" validate product --project <project-root> before conversion. This skill is read-only with respect to the CSV; its structured output remains SIF.

CSV file:

/as:csv-to-sif ./product-data-import.csv

Pasted CSV:

/as:csv-to-sif
Product,Brand,SKU,Qty,Price,Finish,Room
Eames Lounge Chair,Herman Miller,670,3,5695,Walnut/Black Leather,Executive Lounge
Saarinen Table 54,Knoll,164-500,1,4750,Arabescato/White,Dining

Step 2: Choose Target System

Ask which dealer system the SIF file is for (affects which field codes to use):

Target system:
1. Standard (Hedberg, CAP, ProjectMatrix) — default
2. CET / Configura (SPEC)
3. Cyncly Worksheet (CAPSIF)
4. Design Manager

Default to Standard if not specified. The main differences:

  • Standard: MC for manufacturer, PL for price, QT for quantity
  • CET: EC for manufacturer, standard pricing
  • Cyncly: MG/MN for manufacturer, I1/I2 for pricing, PRC for category
  • Design Manager: Standard + DXSC, DXBD, DXLC, DXLN extensions

Step 3: Map Columns

Auto-detect column mappings from header names:

| CSV Column (common names) | SIF Field |

|---------------------------|-----------|

| Product Name, Name, Description, Product | PD |

| SKU, Model, Part Number, Product Number | PN |

| Brand, Manufacturer | MC + MN |

| Qty, Quantity, Count | QT |

| Price, List Price, Unit Price | PL |

| Finish, Color, Configuration | OD |

| Room, Location, Area, Tag, Side Mark | TG |

| Category | GC |

| Weight | WT |

| Discount, Discount % | S- |

| URL, Product URL, Link | ProductURL |

| Image, Image URL | ImageURL |

| W, D, H (dimensions) | AD (with AN=DIM) |

If using the master 33-column schema (defined in ../../schema/product-schema.md):

See ../../schema/sif-crosswalk.md for the full column-to-SIF mapping. Key fields:

| Column | SIF Field |

|--------|-----------|

| A (Category) | GC |

| B (Brand) | MC + MN |

| E (Product Name) | PD |

| I (SKU) | PN |

| J (Link) | ProductURL |

| L-P (W, D, H, Seat H, Unit) | AD (with AN=DIM) |

| Q (Weight) | WT |

| R (Materials) | AD (with AN=MAT) |

| S (Colors/Finishes) | OD (with ON=FIN) |

| T (Selected Color/Finish) | OD (primary, replaces S if present) |

| U (List Price) | PL |

| AC (Image URL) | ImageURL |

| AD (Tags) | TG |

If the mapping is ambiguous, ask the user to confirm.

Manufacturer code lookup

Convert full brand names to standard 3-5 character codes:

| Brand | MC Code | Brand | MC Code |

|-------|---------|-------|---------|

| Herman Miller | HMI | Blu Dot | BLU |

| MillerKnoll | MKN | Design Within Reach | DWR |

| Knoll | KNL | Fritz Hansen | FRH |

| Steelcase | STC | Vitra | VIT |

| Haworth | HAW | Arper | ARP |

| Teknion | TEK | Muuto | MUU |

| Humanscale | HUM | HAY | HAY |

| Kimball | KIM | Flos | FLS |

| National | NAT | Louis Poulsen | LPO |

| OFS | OFS | Artemide | ART |

| HBF | HBF | Restoration Hardware | RHB |

| Bernhardt | BRN | West Elm | WEL |

| Geiger | GEI | CB2 | CB2 |

For unknown brands, use first 3-5 characters uppercased. Flag for the user to verify.

Step 4: Preview

Show a preview of the first 3 records before generating the file:

## SIF Preview (first 3 of 12 records)

Record 1:
  PN=670
  PD=Eames Lounge Chair and Ottoman
  MC=HMI
  MN=Herman Miller
  GC=Seating
  QT=3
  PL=5695.00
  WT=92
  TG=Executive Lounge
  OD=Santos Palisander / Black MCL Leather
  AN=DIM
  AD=32.75W x 32.5D x 33.5H in

...

12 records total. Generate SIF file? (y/n)

Step 5: Generate SIF File

Write the .sif file with CRLF line endings:

# Output path: same directory as input, or specified path
{input-dir}/{input-name}.sif

Step 6: Summary

✓ Generated product-data-import.sif
  Target: Standard (Hedberg/CAP/ProjectMatrix)
  12 records · 8 fields per record avg
  Manufacturers: HMI (5), KNL (3), STC (2), BLU (2)
  Total list value: $47,830.00
  Saved to: ./product-data-import.sif

Pairs With

  • /as:product-data-import — generate a schedule first, then convert to SIF
  • /as:sif-to-csv — round-trip: CSV → SIF → send to dealer → receive updated SIF → back to CSV
  • /as:product-data-cleanup — clean up the CSV before converting

Other skills for the same job

different authors, same section of the catalogue
XLSX
by anthropics
vendor ×15

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

5k tokens scripts
XLSX
by w95
×7

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

3k tokens
Raffle Winner Picker
by frostant
×5

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

949 tokens
Fda Database
by christophacham
×4

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

32k tokens scripts
Matlab
by christophacham
×4

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.

25k tokens
Umap Learn
by ComeOnOliver
×4

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

14k tokens
D3 Viz
by chrisvoncsefalvay
×3

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.

20k tokens
Alphafold Database
by christophacham
×3

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

7k tokens

How to use it

Copy the folder

Take alpacalabsllc/csv-to-sif from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.