Machine learning101k · #813

knowledge-agent

Creates and queries knowledge bases using AI. It allows asking questions about past work or compiling expertise on a topic.

What it does

This tool creates custom AI 'brains' from your past notes. You can gather information on a specific topic and then chat with this AI to get answers.

When to use it

✓When you want a summary about a specific project.
✓To recall past decisions or bug fixes.
✓When compiling knowledge on a subject for study.

Example of what to ask your AI

“Create a brain about 'hooks' and tell me the 5 types and when each one fires.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/thedotmack/claude-mem/blob/main/plugin/skills/knowledge-agent/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/thedotmack/claude-mem/blob/main/plugin/skills/knowledge-agent/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.

View on GitHub ↗Raw file

How it works

First, you tell the tool to build a collection of information (corpus) by filtering your notes. Then, you load this corpus into an AI session and can ask it questions.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add thedotmack/claude-mem --skill knowledge-agent

Or download just the file:

curl -L https://raw.githubusercontent.com/thedotmack/claude-mem/main/plugin/skills/knowledge-agent/SKILL.md -o SKILL.md

Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

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

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

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

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

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)

rebuild_corpus name="hooks-expertise"

After rebuilding, reprime to load the updated knowledge:

Reprime (fresh session)

reprime_corpus name="hooks-expertise"

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

FAQ

How do I create a 'brain'?

You use the `build_corpus` command to create the information collection and then `prime_corpus` to load it into an AI.

Can I update the 'brain' with new information?

Yes, use `rebuild_corpus` to update the collection and then `reprime_corpus` to reload the AI with the new information.

What are 'observations'?

These are records you've made previously, such as decisions, bug fixes, new features, etc.

Details

Original description by the author

Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.

repo: thedotmack/claude-mem

Popularity

GitHub stars: 101k
Ranking position: #813
License: Apache-2.0
Updated: 10/16/2026

Is this skill useful?

Comments

More skills from this repository

Documentation101k

Agent Cost Report

Has your agent generate detailed cost reports for its activities. Shows how much was spent on tokens and services.

thedotmack/claude-mem

Agents101k

claude-mem-install

Helps your agent set up Claude-Mem in different environments. Allows choosing between local or remote workers and configuring observation.

thedotmack/claude-mem

Agents101k

mem-search

Lets your agent search past memories. Useful for recalling previous solutions or work from old sessions.

thedotmack/claude-mem

Agents101k

host-observer

Helps your agent respond to Claude-Mem observer tasks. It should only reply with 'skip_summary' or a full XML observation.

thedotmack/claude-mem

Similar skills

Machine learning280k

pytorch-patterns

Helps your agent use PyTorch for machine learning models. It applies best practices for efficient model training and ensures reproducible results.

affaan-m/ECC

Machine learning280k

evm-token-decimals

Helps your agent avoid errors with decimal numbers across different blockchain networks. It ensures token values are accurate in transactions and calculations.

affaan-m/ECC

Machine learning77k

Snowflake Automation

Makes your agent interact with Snowflake. It can list data, run SQL commands, and manage data workflows.

ComposioHQ/awesome-claude-skills