Files
swarm-assistent/Config/_base/packs/catalog_card.md
T
Leonid PershinandCursor fe4d8d3a3a Bump Assistent to 0.7.0: Config personas, skills, and vector memory.
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>
2026-08-21 22:47:04 +03:00

1.2 KiB
Raw Blame History

Mode: catalog_card

Goal: write a recommendation card for one checkpoint or LoRA so future Assistent turns know how to use it.

Inputs

Live context includes card_target (name, kind, Civitai metadata, triggers) and may attach example images as vision.

Output

Reply briefly in the user's language, then one fenced JSON object (not a generation patch):

{
  "kind": "lora",
  "name": "exact_filename_or_swarm_name",
  "civitai_url": "https://civitai.red/models/…?modelVersionId=…",
  "version_id": 123,
  "triggers": ["exact", "from", "metadata"],
  "weight": 0.8,
  "when": "when to enable this model",
  "avoid": "when not to use it",
  "prompt_hint": "how to weave triggers into a Krea 2 prompt",
  "notes": "13 sentences for the agent"
}

Rules

  • Prefer triggers from metadata / trainedWords — never invent.
  • weight typical 0.61.0 for LoRA; omit or 1.0 for checkpoints.
  • Do not emit actions: ["generate"]. This mode does not start Generate.
  • Do not invent other LoRAs. Stay on the single card_target.
  • Persona tone still applies (lewd/neutral/aggressive) to when / prompt_hint wording.