knowledge-agent

Name: knowledge-agent
Availability: InStock
Author: enigmaicon-eng

Build queryable knowledge bases from filtered observation history.

1|Updated May 16, 2026

Search Tags:#semantic search #knowledge base #observations #memory workflow #question answering #corpus building #context priming

Ready to run

npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill knowledge-agent-enigmaicon-eng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: knowledge-agent
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/claude-mem/plugin/skills/knowledge-agent
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill knowledge-agent-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of having large amounts of past observations stored somewhere you cannot efficiently search, summarize, or reuse during new conversations.

Core Features & Use Cases

Build focused corpora from observations: Filter your observation history by project, types, concepts, files, semantic query, and date ranges to create a compact knowledge base.
Prime a conversational session with knowledge: Load the selected corpus into a persistent AI session so answers are grounded in your historical work patterns.
Query and maintain continuity: Ask questions conversationally, then list, rebuild, or reprime to keep the knowledge current.
Use case: Create a “hooks lifecycle” expertise corpus from your observations, prime it, and repeatedly answer lifecycle questions such as what hooks exist and when each fires.

Quick Start

Build the corpus named hooks-expertise, prime it, and ask: What are the 5 lifecycle hooks and when does each fire?

Frequently Asked Questions about knowledge-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a queryable knowledge base from past observation history?▼

Semantic search over a filtered observation corpus works by priming a conversational session with your selected knowledge base. The session then retrieves and answers questions using the primed knowledge, ensuring responses are grounded in your historical work patterns rather than general data.

What is the best way to answer questions using a filtered set of past observations?▼

The best way to answer questions using a filtered set of past observations is to define a corpus with specific filter parameters, prime a session from that corpus, and then ask questions conversationally. This approach grounds answers in your historical work patterns for a chosen topic or time window.

Can I filter my observation history by project and date ranges to create focused expertise?▼

Yes, you can filter your observation history by project, types, concepts, files, semantic query, and date ranges. This filtering compiles focused expertise corpora, allowing you to create a compact knowledge base tailored to a specific topic, project, or time window for conversational Q&A.

How do I keep my primed knowledge base current when new observations are added?▼

To keep your primed knowledge base current when new observations are added, you use the supported corpus listing, rebuild, and reprime workflows. These workflows allow you to refresh the filtered observation corpus and re-prime your conversational session with the updated knowledge.

Does this question answering approach require defining a corpus before priming a session?▼

Yes, this question answering approach requires defining a corpus with filter parameters before priming a session. You must compile the knowledge base from prior observation history first, which then gets loaded into a persistent AI session to ground your conversational queries.