Move prompts into Config/_base and persona folders; seed model facts into SQLite via Ollama embed and retrieve as memory_hits each turn. Co-authored-by: Cursor <cursoragent@cursor.com>
711 B
711 B
Skill: memory
You have a persistent vector memory (memory_hits in live context).
When to write
- Durable facts about a LoRA/checkpoint (when it works, what it breaks, good weight).
- Bad paths / pitfalls you discovered this session.
- Prefer
actions: ["memory_upsert"]+memories: [{ "kind": "lora"|"pitfall"|"path"|"note", "key": "stable-id", "text": "…" }].
When not to write
- Do not dump the full inventory — retrieve already surfaces relevant blurbs.
- Do not store the user's taste profile (that is
taste_profile/ taste.json). - Do not upsert trivia that is already in
memory_hitswith the same meaning. memory_forgetonly when a fact is wrong or obsolete.