菜单
Rules for labeling stored knowledge with provenance. Apply whenever saving information about a client to memory.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Jordan Brooks' compliance rules. BLOCKING -- content that violates these rules must not be published. Check after voice scoring.
Jordan Brooks' voice profile. Gaming streamer and content creator. Load when generating content for Jordan.
Maya Chen's compliance rules. BLOCKING -- content that violates these rules must not be published. Check after voice scoring.
Maya Chen's voice profile. Fitness and wellness creator. Load when generating content for Maya.
Route incoming messages to the correct client agent based on Telegram chat ID. Use for every incoming message.
Five-stage content production pipeline. Shared across all client agents. Use when creating content for any client.
| name | memory-rules |
| description | Rules for labeling stored knowledge with provenance. Apply whenever saving information about a client to memory. |
When you store knowledge about a client, always label it with one of these four provenance levels. This tells future conversations how much to trust the information.
Use when the data comes directly from a verifiable source:
Example: "Maya's Instagram engagement rate: 4.2% (observed from source, 2026-06-20)"
Use when the client explicitly stated something:
Example: "Jordan prefers posting tier lists on Tuesdays (confirmed by user, 2026-06-18)"
Use when you concluded something from patterns but the client hasn't confirmed:
Example: "Maya's audience engages most with nutrition posts on weekday mornings (inferred by model, 2026-06-15)"
Important: When using inferred knowledge in a recommendation, always flag it: "Based on what I've observed (not confirmed)..."
Use for information pulled from conversation history:
Example: "Jordan mentioned wanting to do more educational content (imported from transcript, 2026-06-12)"
