---
id: gh-knowledge-agent
name: "knowledge-agent"
url: https://skills.yangsir.net/skill/gh-knowledge-agent
author: thedotmack
domain: ai-agent-memory-knowledge
tags: ["knowledge-management", "information-retrieval", "ai-agent-memory", "context-management", "semantic-search"]
install_count: 5200
rating: 4.40 (120 reviews)
github: https://github.com/thedotmack/claude-mem/tree/main/plugin/skills/knowledge-agent
---

# knowledge-agent

> 该技能能从历史观察数据中构建并查询AI驱动的知识库，为AI智能体提供定制化的“大脑”。它允许用户根据项目、概念或时间范围筛选信息，快速创建专注于特定主题的知识集合，从而帮助智能体记住用户偏好、理解复杂情境并高效回答关于过去工作模式或专业领域的问题。

**Stats**: 5,200 installs · 4.4/5 (120 reviews)

## Before / After 对比

### 编译特定项目知识所需时间

**Before**:

在没有知识代理的情况下，手动筛选大量项目文档和历史观察记录，以收集特定信息或回答复杂问题。这通常需要数小时，且容易遗漏关键细节或获取过时信息。

**After**:

使用知识代理，通过快速构建一个专注于相关主题的知识库，并进行对话式查询，即时获得精确且上下文感知的答案，大大减少了信息检索的时间和精力。

| Metric | Before | After | Change |
|---|---|---|---|
| 时间 | 240分钟 | 15分钟 | -94% |

## Readme

# Knowledge Agent

Build and query AI-powered knowledge bases from claude-mem observations.

## What Are Knowledge Agents?

Knowledge agents are filtered corpora of observations compiled into a conversational AI session. Build a corpus from your observation history, prime it (loads the knowledge into an AI session), then ask it questions conversationally.

Think of them as custom "brains": "everything about hooks", "all decisions from the last month", "all bugfixes for the worker service".

## Workflow

### Step 1: Build a corpus

```text
build_corpus name="hooks-expertise" description="Everything about the hooks lifecycle" project="claude-mem" concepts="hooks" limit=500
```

Filter options:
- `project` — filter by project name
- `types` — comma-separated: decision, bugfix, feature, refactor, discovery, change
- `concepts` — comma-separated concept tags
- `files` — comma-separated file paths (prefix match)
- `query` — semantic search query
- `dateStart` / `dateEnd` — ISO date range
- `limit` — max observations (default 500)

### Step 2: Prime the corpus

```text
prime_corpus name="hooks-expertise"
```

This creates an AI session loaded with all the corpus knowledge. Takes a moment for large corpora.

### Step 3: Query

```text
query_corpus name="hooks-expertise" question="What are the 5 lifecycle hooks and when does each fire?"
```

The knowledge agent answers from its corpus. Follow-up questions maintain context.

### Step 4: List corpora

```text
list_corpora
```

Shows all corpora with stats and priming status.

## Tips

- **Focused corpora work best** — "hooks architecture" beats "everything ever"
- **Prime once, query many times** — the session persists across queries
- **Reprime for fresh context** — if the conversation drifts, reprime to reset
- **Rebuild to update** — when new observations are added, rebuild then reprime

## Maintenance

### Rebuild a corpus (refresh with new observations)

```text
rebuild_corpus name="hooks-expertise"
```

After rebuilding, reprime to load the updated knowledge:

### Reprime (fresh session)

```text
reprime_corpus name="hooks-expertise"
```

Clears prior Q&A context and reloads the corpus into a new session.


---
*Source: https://skills.yangsir.net/skill/gh-knowledge-agent*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-knowledge-agent/markdown*