kb-guide
Skill326 starsChanged 9 months agoMITView on GitHub
Search, read, create, and update knowledge base entries via MCP-connected KB tools. Use when the user asks to look up documentation, find existing articles, check if docs exist on a topic, create a new KB entry, update an existing document, or when domain questions should be answered from the knowledge base first.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/architecture-constraints.mdcCursor rule
- .cursor/rules/engine-internals.mdcCursor rule
- .cursor/rules/testing-conventions.mdcCursor rule
- escalationSkill
- generalSkill
- im-adapterSkill
- message-pushSkill
- multi-botSkill
- task-managerSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
When MCP knowledge base servers are configured, you can use their tools to search, read, create, and update knowledge entries.
- Distinctive: line 31
When a user asks "do we have docs on deployment?", search the KB first:
- Distinctive: line 42
Before answering domain questions: Search the KB first -- it may contain authoritative answers
- Distinctive: line 43
When the user asks "do we have docs on...": Search the KB and return results
- Distinctive: line 45
For onboarding/FAQ questions: Check if there's an existing KB article
- Distinctive: line 50
Call the appropriate MCP tool by name
- Distinctive: line 51
If a tool is not available, inform the user that no KB server is configured
- Distinctive: line 58
Always prefer searching the KB before generating answers from your own training data
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Knowledge Base Integration Guide
When MCP knowledge base servers are configured, you can use their tools to search, read, create, and update knowledge entries.
Common MCP Knowledge Base Tools
MCP KB servers typically expose tools with these patterns:
Search / Query
search_documents(query, limit?)-- full-text search across the knowledge basesearch_notes(query)-- search personal notes or wiki entriesquery_knowledge(query, filters?)-- filtered search with metadata constraints
Read
get_document(id)-- retrieve a document by IDread_page(path)-- read a wiki page by pathlist_documents(folder?, tag?)-- list documents in a folder or by tag
Create / Update
create_document(title, content, metadata?)-- create a new entryupdate_document(id, content)-- update an existing documentcreate_note(title, body)-- create a quick note
Example Tool Call
When a user asks "do we have docs on deployment?", search the KB first:
Tool: search_documents
Arguments: { "query": "deployment", "limit": 5 }Present matching results with titles and snippets. If no results are found, offer to create a new entry.
When to Use Knowledge Base
- Before answering domain questions: Search the KB first -- it may contain authoritative answers
- When the user asks "do we have docs on...": Search the KB and return results
- After resolving an issue: Suggest creating a KB entry to capture the solution
- For onboarding/FAQ questions: Check if there's an existing KB article
Usage Pattern
- Identify the user's intent (search, read, write)
- Call the appropriate MCP tool by name
- If a tool is not available, inform the user that no KB server is configured
- Present results clearly -- include titles, snippets, and links when available
Notes
- MCP server configuration is defined in
golem.yamlunder themcpkey - Available MCP tools depend on which servers are configured -- use tool discovery to check
- Always prefer searching the KB before generating answers from your own training data
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

