knowledge-agent
This skill builds and queries AI-powered knowledge bases from historical observation data, providing customized "brains" for AI agents. It allows users to filter information by project, concept, or date range, quickly creating focused knowledge collections on specific topics. This helps agents remember user preferences, understand complex situations, and efficiently answer questions about past work patterns or specialized domains.
npx skills add https://github.com/thedotmack/claude-mem --skill knowledge-agentBefore / After Comparison
1 组Manually sifting through extensive project documentation and past observations to gather specific information or answer complex questions without a knowledge agent. This often takes hours and is prone to missing details or retrieving outdated information.
Using the knowledge agent to quickly build a focused corpus on the relevant topic and instantly query it conversationally, obtaining precise, context-aware answers, significantly reducing time and effort for information retrieval.
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 nametypes— comma-separated: decision, bugfix, feature, refactor, discovery, changeconcepts— comma-separated concept tagsfiles— comma-separated file paths (prefix match)query— semantic search querydateStart/dateEnd— ISO date rangelimit— 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.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill