kiwi-receipts
NZ tax assistant for sole traders. Process receipt photos into IRD-ready GST reports, track sales income for GST Box 5, calculate IR3 annual income tax, provisional tax, asset depreciation, and export to Xero CSV. Use when: (1) user sends a receipt/invoice photo, (2) user asks about GST, income tax, or tax returns, (3) user wants to export receipts or generate reports, (4) user mentions IRD, GST, IR3, provisional tax, or depreciation.
What this skill does
# Kiwi Receipts
NZ tax assistant for sole trader builders and contractors. Process receipt photos into IRD-ready GST reports, track sales income, calculate annual income tax (IR3), provisional tax, and asset depreciation. Export to XLSX or Xero CSV.
This is a personal-use skill -- each user runs their own instance. No multi-tenant, no login.
## Data Paths
```
~/.openclaw/data/kiwi-receipts/
├── config.json # Business name, GST number, tax settings
├── receipts.json # All captured purchase receipts
├── income.json # Sales/invoice records
├── assets.json # Depreciable assets register
└── tax-history.json # Previous years' tax figures (for provisional tax)
```
## First-Time Setup
When user sends "setup", or on first use when `config.json` doesn't exist:
1. Ask for business name
2. Ask for GST/IRD number
3. Ask for vehicle business use % (default 80)
4. Ask for phone business use % (default 70)
5. Save to `~/.openclaw/data/kiwi-receipts/config.json`:
```json
{
"business_name": "My Construction Ltd",
"gst_number": "12-345-678",
"balance_date": "31-march",
"gst_filing_frequency": "2-monthly",
"depreciation_method": "DV",
"vehicle_business_percent": 80,
"phone_business_percent": 70,
"home_office_percent": 0
}
```
### income.json structure
Each entry represents an invoice or payment received:
```json
[
{
"id": "uuid-here",
"date": "2026-03-15",
"client": "ABC Homes Ltd",
"description": "Bathroom renovation - 42 Rimu St",
"amount_excl_gst": 8500.65,
"gst": 1274.35,
"amount_incl_gst": 9775.00,
"invoice_number": "INV-2026-015",
"status": "paid",
"created_at": "2026-03-15T14:30:00Z"
}
]
```
### assets.json structure
```json
[
{
"id": "uuid-here",
"name": "DeWalt DCS570 Circular Saw",
"category": "portable_power_tools",
"purchase_date": "2026-01-15",
"cost": 899.00,
"dv_rate": 0.40,
"sl_rate": 0.30,
"method": "DV",
"business_percent": 100,
"disposed": false,
"disposal_date": null,
"disposal_amount": null,
"created_at": "2026-01-15T10:00:00Z"
}
]
```
### tax-history.json structure
```json
{
"years": {
"2025": {
"tax_year_end": "2025-03-31",
"gross_income": 95000.00,
"total_expenses": 42000.00,
"depreciation": 3500.00,
"taxable_income": 49500.00,
"tax_on_income": 7582.50,
"acc_levy": 826.50,
"total_tax": 8409.00,
"tax_already_paid": 0,
"residual_income_tax": 8409.00
}
}
}
```
## Handling Receipt Photos
When the user sends an image (check for `MediaPaths` in context):
### Step 1: Analyze the image
Use your vision capabilities to analyze the receipt image. Extract:
```json
{
"merchant": "Bunnings Warehouse",
"date": "2026-03-15",
"items": [
{ "description": "Timber 2x4 3.6m", "quantity": 10, "unit_price": 12.50, "amount": 125.00 },
{ "description": "Concrete Mix 40kg", "quantity": 5, "unit_price": 9.80, "amount": 49.00 }
],
"subtotal": 174.00,
"gst": 22.57,
"total": 174.00,
"gst_number": "123-456-789",
"payment_method": "EFTPOS",
"category": "materials"
}
```
**Extraction rules:**
- NZ GST is 15%. If only total is visible, calculate GST as `total × 3/23`
- If GST is shown separately on the receipt, use that value
- Detect the GST number if printed on the receipt
- Classify into categories: `materials`, `tools`, `fuel`, `safety`, `subcontractor`, `office`, `vehicle`, `other`
- Dates: parse to ISO format (YYYY-MM-DD), assume current year if not shown
- All amounts in NZD
### Step 2: Confirm with user
Send back a summary:
```
Receipt captured:
Merchant: Bunnings Warehouse
Date: 2026-03-15
Total: $174.00 (GST: $22.57)
Items: Timber 2x4 3.6m x10, Concrete Mix 40kg x5
Category: materials
Reply to save, or correct any details.
```
### Step 3: Save receipt data
After confirmation, append to `~/.openclaw/data/kiwi-receipts/receipts.json`:
```bash
mkdir -p ~/.openclaw/data/kiwi-receipts
```
Read existing `receipts.json` (or start with `[]`), append the new receipt with a generated UUID as `id`, and write back. Each receipt object:
```json
{
"id": "uuid-here",
"merchant": "...",
"date": "2026-03-15",
"items": [...],
"subtotal": 174.00,
"gst": 22.57,
"total": 174.00,
"gst_number": "...",
"category": "materials",
"payment_method": "EFTPOS",
"created_at": "2026-03-15T10:30:00Z"
}
```
## Handling Text Commands
### "setup"
Create or update `config.json` with business name and GST number.
### "summary"
Read `receipts.json`, filter to current GST period, show:
```
GST Period: Mar-Apr 2026
Total purchases: $1,527.37
Total GST claimable: $199.13
Receipts: 5
By category:
Materials: $882.97 (GST: $115.17)
Tools: $114.00 (GST: $14.87)
Fuel: $131.40 (GST: $17.14)
Safety: $399.00 (GST: $51.95)
```
### "report" or "export"
Generate and send XLSX report:
```bash
python3 {baseDir}/scripts/generate_report.py \
--data ~/.openclaw/data/kiwi-receipts/receipts.json \
--income ~/.openclaw/data/kiwi-receipts/income.json \
--assets ~/.openclaw/data/kiwi-receipts/assets.json \
--tax-history ~/.openclaw/data/kiwi-receipts/tax-history.json \
--output /tmp/gst-report.xlsx \
--period current \
--business-name "from config.json" \
--gst-number "from config.json"
```
Then send the file back to user via message tool with `sendAttachment` action.
### "report YYYY-MM"
Generate report for a specific GST period (the 2-month period containing that month).
**XLSX report contains up to 7 sheets:**
1. **GST Summary** -- Business info, period, total purchases/GST
2. **All Receipts** -- Date, merchant, category, items, amounts
3. **By Category** -- materials/tools/fuel/safety/etc. subtotals
4. **IRD GST101A** -- Pre-filled with official box numbers (see below)
5. **Income** -- Sales/invoice records (if income.json has data)
6. **Depreciation** -- Asset depreciation schedule (if assets.json has data)
7. **IR3 Annual Tax** -- Annual income tax summary (when period=all or period=annual)
**GST101A auto-fill logic:**
If income.json has data for the period, BOTH sides are auto-filled:
- Box 5: Total sales and income (from income.json) -- AUTO-FILLED
- Box 6: Zero-rated supplies (default $0)
- Box 7: Box 5 - Box 6 -- auto-calculated
- Box 8: Box 7 x 3/23 -- auto-calculated
- Box 9: Adjustments (default $0)
- Box 10: Total GST collected (Box 8 + Box 9) -- auto-calculated
- Box 11: Total purchases incl GST (from receipts.json) -- auto-filled
- Box 12: Box 11 x 3/23 -- auto-calculated
- Box 13: Credit adjustments (default $0)
- Box 14: Total GST credit (Box 12 + Box 13) -- auto-calculated
- Box 15: Box 10 - Box 14 -- FULLY AUTO-CALCULATED
If no income data exists, Box 5 still shows "enter from accounts" as before.
### "delete last"
Remove the most recently added receipt from `receipts.json`.
### "list"
Show recent receipts (last 10) with date, merchant, total.
### "help"
```
Kiwi Receipts -- Commands:
RECEIPTS:
[Send photo] Capture a receipt
"summary" Current GST period overview
"report" Download GST report (XLSX)
"report 2026-03" Report for specific period
"list" Show recent receipts
"delete last" Remove last receipt
INCOME:
"income 9775 description" Record sales invoice
"income list" Show recent income
"income summary" Period income total
ASSETS:
"asset add name $cost" Register depreciable asset
"asset list" Show assets with book values
"asset dispose name $price" Record asset disposal
"depreciation" Calculate this year's depreciation
TAX:
"provisional" Calculate provisional tax
"set last year tax 8409" Set previous year RIT
"tax return" / "ir3" Annual tax summary
"export ir3" Annual XLSX report
EXPORT:
"xero export" Generate Xero-importable CSV
SETUP:
"setup" Configure business details
"heRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.