Single-skill wrapper for the 4-layer recall (durable memory → semantic DB → PostgreSQL → daily notes). Use BEFORE saying "I don't have context". Triggers: "search memory", "what do we know about X", "deep recall", "I don't remember".
Scanned 9/11/2026
Install to Claude Code
npx -y skills add netanel-abergel/pa-skills --skill memory-archaeologist --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Memory Archaeologist?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/netanel-abergel-memory-archaeologist)More formats (shields.io, HTML) on the badges page.
---
name: memory-archaeologist
description: |-
Single-skill wrapper for the 4-layer recall (durable memory → semantic DB → PostgreSQL → daily notes).
Use BEFORE saying "I don't have context".
Triggers: "search memory", "what do we know about X", "deep recall", "I don't remember".
---
# Memory Archaeologist
Run before ever claiming "no context" or "I don't remember".
## When to use
- Before answering any "what do we know about X" question
- Before responding "no context" / "I don't remember"
- When piecing together a thread that spans WhatsApp + daily notes + project memory
## Procedure (DO NOT SKIP STEPS)
1. **Durable memory + wiki**
```bash
grep -rin "<query>" MEMORY.md HOT.md AGENTS.md wiki/ 2>/dev/null
```
2. **Semantic DB**
```bash
python tools/session_search.py "<query>"
```
3. **PostgreSQL WhatsApp history**
```sql
SELECT body, ts, chat_id FROM messages
WHERE body ILIKE '%<query>%'
ORDER BY ts DESC LIMIT 20;
```
4. **Daily notes**
```bash
grep -lir "<query>" memory/daily/ 2>/dev/null
```
## Output rules
- Report findings only — do not narrate the search
- If all 4 layers return empty, then (and only then) escalate to "no context"
- Cache the answer in the relevant durable file if it's a recurring question
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
MySQL development best practices for schema design, query optimization, and database administration
基于Supabase最佳实践的PostgreSQL数据库模式,用于查询优化、架构设计、索引和安全。
Spring Boot中的JPA/Hibernate实体设计、关系、查询优化、事务、审计、索引、分页和连接池模式。
ClickHouse数据库模式、查询优化、分析和数据工程最佳实践,适用于高性能分析工作负载。
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).