Entity Memory Extraction
Documentsentity-memory-extractionEntity Memory Extraction is an Agent Skill for documents published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Entity and fact extraction for user profiling and personalization
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/ai-agents-conversational/skills/entity-memory-extraction/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/entity-memory-extraction, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Entity Memory Extraction Skill
Capabilities
- Extract entities from conversations
- Build and update user profiles
- Track preferences and facts
- Implement entity disambiguation
- Design entity relationship graphs
- Configure extraction rules and schemas
Target Processes
- long-term-memory-management
- conversational-persona-design
Implementation Details
Extraction Types
- Named Entities: People, places, organizations
- User Preferences: Likes, dislikes, interests
- Facts: Stated information about user
- Temporal: Dates, events, schedules
- Relationships: Connections between entities
Configuration Options
- Extraction model selection
- Entity schema definition
- Confidence thresholds
- Update policies
- Storage backend
Best Practices
- Define clear entity schemas
- Handle entity conflicts
- Implement confidence scoring
- Regular profile validation
- Privacy considerations
Dependencies
- langchain
- spacy (optional)
- Custom extraction models