メニュー
Search long-term memories that have moved to the archive tier (> 90 days old, low-activity). Returns ranked results by semantic relevance.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build, install, and manage complete NekoCore OS apps — HTML payload, installer contract, window registration, start menu category. Produces installer-managed, reversible app packages.
Create and register new MA task blueprints, task types, and classification rules
Extract characters from a book and create them as NekoCore OS entities with POV-isolated memories. Supports main-only, all, or specific character selection.
Production code author — write, edit, debug, and scaffold real code projects. Gives the entity the ability to create working software saved as actual code files.
Create structured courses, curricula, lesson plans, and exam prep materials from topics or books
Build, run, and manage D&D campaigns with session prep, world lore, and narrative arcs
| name | search-archive |
| description | Search long-term memories that have moved to the archive tier (> 90 days old, low-activity). Returns ranked results by semantic relevance. |
| trigger | search-archive |
This skill enables searching the entity's long-term memory archive — memories older than 90 days that are no longer in the hot working-memory index.
Use this skill when:
Do not use this for recent memories — those are retrieved automatically.
[TOOL:search_archive query="your search terms here"]
With optional year range filter:
[TOOL:search_archive query="pipeline orchestration" yearRange='{"start":"2024-01-01T00:00:00.000Z","end":"2025-01-01T00:00:00.000Z"}' limit="10"]
query (required): Natural language search terms describing what you're looking foryearRange (optional): JSON object with "start" and/or "end" as ISO date strings to filter by archive datelimit (optional): Number of results to return (default 5, max 20)Results include:
id: Memory identifiersummary: Extracted text content from the archived memoryarchivedAt: When the memory was moved to the archivetopics: Topic keywords associated with the memorytype: Memory type (episodic, doc, or semantic_knowledge)score: Relevance score (higher = more relevant)