> Auto-categorize uncategorized transactions using vendor pattern matching.
npx skills add https://github.com/openaccountant/skills --skill smart-categorize
Automatically categorize uncategorized transactions by matching vendor/description patterns against known rules. Uses existing categorization rules first, then suggests new rules for unmatched transactions based on common vendor names.
categorize — apply pattern-based categorization rules to transactionstransaction_search — find uncategorized transactionstransaction_search to find all transactions where category is null or empty.categorize to apply existing categorization rules (pattern matching on description field).You can categorize transactions manually in a spreadsheet:
Pattern and Category.| Pattern | Category |
|---------|----------|
| AMAZON | Shopping |
| WHOLE FOODS | Groceries |
| SHELL | Transportation |
| NETFLIX | Entertainment |
| STARBUCKS | Dining |
=IFERROR(INDEX(Rules!B:B,MATCH("*"&"AMAZON"&"*",Rules!A:A,0)),"Uncategorized") — but this only works for exact matches.=SUMPRODUCT or VBA macro to do partial matching.=IFERROR(VLOOKUP("*"&A2&"*",Rules!A:B,2,FALSE),"Uncategorized") does not support wildcards in VLOOKUP. =IF(REGEXMATCH(A2,"(?i)amazon"),"Shopping",
IF(REGEXMATCH(A2,"(?i)whole foods|trader joe"),"Groceries",
IF(REGEXMATCH(A2,"(?i)shell|chevron|exxon"),"Transportation",
"Uncategorized")))
| Vendor Pattern | Suggested Category |
|---|---|
| AMAZON, TARGET, WALMART | Shopping |
| WHOLE FOODS, TRADER JOE, KROGER, SAFEWAY | Groceries |
| UBER EATS, DOORDASH, GRUBHUB | Dining |
| NETFLIX, SPOTIFY, HULU, DISNEY+ | Entertainment |
| SHELL, CHEVRON, BP, EXXON | Transportation |
| AT&T, VERIZON, T-MOBILE, COMCAST | Utilities |
| CVS, WALGREENS, PHARMACY | Healthcare |
| VENMO, ZELLE, PAYPAL (person-to-person) | Transfers |
categorization_rules table so they persist across sessions and apply to future imports automatically.Use when you have a written implementation plan to execute in a separate session with review checkpoints
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take openaccountant/smart-categorize from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.