Apple Reminders Processing - Smart Research System

v3 Evolution: Custom instructions + auto-processing + result tracking

🎯 Three Generations

Gen 1 (Manual - deprecated)

code

Title: 🔍 Pesquise tarot no livro
Notes: (empty)
→ Manual emoji trigger

Gen 2 (Auto - current baseline)

code

Title: Stacker bag
Notes: (empty)
→ Auto-detect empty notes
→ List-based behavior (shopping/claw/generic)

Gen 3 (Custom - NEW)

code

Title: Bitcoin ETF regulation
Notes: "Procure no livro de David Graeber sobre anarchism + web search SEC rulings 2024"
→ Follow custom instructions
→ Output: "💎 [resultado da pesquisa]"

🔑 Signifiers

💎 = RESULT (already processed)

•For Nicholas: "Read the report, it's done"
•For Claw: "Skip this, already researched"

No 💎 = NEEDS PROCESSING

•Empty notes → list-based default behavior
•Notes with instructions → follow custom research path

📋 Processing Logic

Detection

bash

process-reminders.sh

Output types:

code

NO_REMINDERS_TO_PROCESS          # Nothing to do
CLAW_ITEM|<id>|<title>            # System improvement (empty notes)
SHOPPING_ITEM|<id>|<title>        # Product search (empty notes)
GENERIC_ITEM|<id>|<list>|<title>  # Generic research (empty notes)
CUSTOM_ITEM|<id>|<list>|<title>|<instructions>  # Custom instructions (Gen 3)

AI Processing

For CUSTOM_ITEM:

•Parse custom instructions from notes
•
Execute multi-source research:
- •If mentions "livro/book" → use librarian skill
- •If mentions "web search" → use web_search
- •If mentions specific sources → prioritize those
•Combine findings
•Update notes: 💎 [research findings]

For CLAW_ITEM:

•Run memory_search for similar past issues
•Analyze pattern (frequency, context, impact)
•Propose solutions (tech/process/system)
•Update notes: 💎 [analysis + solutions]

For SHOPPING_ITEM:

•Web search: product + "buy" + "price"
•Priority sites: Temu, Shop.app, AliExpress (avoid Amazon)
•Extract: links, prices, ratings
•Update notes: 💎 [shopping findings]

For GENERIC_ITEM:

•Web search: title + context from list name
•Find: tutorials, how-to, documentation
•Summarize key findings
•Update notes: 💎 [research summary]

💎 Result Format

Start with 💎 signifier:

code

💎 RESEARCH RESULTS

**Sources:**
- Book: "Debt: The First 5000 Years" by David Graeber, Chapter 7
- Web: SEC ruling 2024-08 (Bitcoin ETF approval)

**Summary:**
[Key findings organized by source]

**Next steps:**
[Actionable recommendations if applicable]

📊 List-Based Behavior (Gen 2)

List	Action	Output Format
🛒 Groceries	SKIP	(no processing)
claw	System analysis	💎 Pattern + solutions
Shopping	Product search	💎 Links + prices
Others	Generic research	💎 Summary + sources

🎨 Custom Instructions (Gen 3)

Example prompts in notes:

Multi-source research:

code

Procure no livro de finance + web search "mortgage prepayment calculator"

Specific constraints:

code

Web search only (no books). Focus on 2024 data. Avoid crypto sites.

Librarian focus:

code

Pesquise nos livros de tarot + I Ching. Compare interpretations.

Shopping with constraints:

code

Where to buy. Budget under $50. Avoid Amazon.

🔄 Heartbeat Integration

Runs 2x/day (morning + evening):

bash

RESULT=$(~/.openclaw/skills/reminders/process-reminders.sh)

if [ "$RESULT" != "NO_REMINDERS_TO_PROCESS" ]; then
  # Parse each item type
  # Execute appropriate research
  # Update notes with 💎 result
  # Notify Telegram when batch complete
fi

📝 Update Reminder Notes

bash

remindctl edit <id> --notes "💎 [your research findings here]"

🎯 Use Cases

System debugging:

code

List: claw
Title: Messages disappear after reindexing
Notes: (empty)
→ Auto: Pattern analysis + 4 solution tiers
→ Result: "💎 ANALYSIS: [pattern] SOLUTIONS: [1-4]"

Product research:

code

List: Shopping
Title: iPad mini 6, second hand
Notes: (empty)
→ Auto: Web search eBay/Swappa/Facebook Marketplace
→ Result: "💎 FOUND: eBay $350, Swappa $380..."

Custom deep research:

code

List: TODO
Title: Bitcoin regulation impact
Notes: "Procure no livro 'Debt' by Graeber (debt history) + web search 'SEC Bitcoin ETF 2024 ruling'"
→ Custom: Librarian search + web search
→ Result: "💎 RESEARCH RESULTS\n\nBook: Graeber argues...\n\nWeb: SEC approved..."

Follow-up instructions:

code

List: Creative Code
Title: Vertical slider library
Notes: "Find React examples on GitHub. Check if any use Framer Motion. Budget: MIT license only."
→ Custom: GitHub code search with constraints
→ Result: "💎 FOUND: 3 MIT-licensed libs using Framer..."

🚫 What NOT to Process

•✅ Notes start with 💎 → already processed, skip
•✅ List = 🛒 Groceries → no research needed
•✅ Completed reminders → ignored

Dependencies

•remindctl (Apple Reminders CLI)
•jq (JSON processing)
•OpenClaw web_search tool
•OpenClaw memory_search tool (for claw items)
•Librarian skill (for book research)