multi-bot
Skill326 starsChanged 9 months agoMITView on GitHub
Coordinates responses between multiple GolemBot instances in a shared fleet. Use when the bot operates in a group chat with other bots, needs to decide whether to respond or pass, or must call a peer bot's API to fetch cross-domain data.
- Sends data out
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
- kb-guideSkill
- message-pushSkill
- task-managerSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
When you see [Peers: 小忆 (user research), 小舟 (content creation)] in the prompt:
- Distinctive: line 22
Respond: if the message falls within your domain/role
- Distinctive: line 23
Respond: if you are directly @mentioned
- Distinctive: line 24
[PASS]: if the message clearly belongs to another peer's domain
- Distinctive: line 25
Respond: if the topic spans multiple domains — focus on YOUR area of expertise only, don't duplicate what peers would cover
- Distinctive: line 26
Respond: if no peer is better suited (don't let messages go unanswered)
- Very specific: line 30
Check the conversation history for [bot:PeerName] entries
- Distinctive: line 31
If a peer already covered a topic, don't repeat it — add new information or skip
- Distinctive: line 32
When a topic spans multiple domains, scope your response to your own expertise
- Distinctive: line 92
Use these labels to understand the conversation context and avoid repeating what peers have already said.
≈ “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
Multi-Bot Collaboration
You may be one of several GolemBot instances running in the same fleet. The gateway injects [Peers: ...] into your group chat context so you know who else is present.
Peer Awareness
When you see [Peers: 小忆 (user research), 小舟 (content creation)] in the prompt:
- These are other GolemBot instances in the fleet
- Each has its own specialization (shown in parentheses)
- They may or may not be active in this specific group chat
When to Respond vs [PASS]
In group chats with peers, follow these rules:
- Respond if the message falls within your domain/role
- Respond if you are directly @mentioned
- [PASS] if the message clearly belongs to another peer's domain
- Respond if the topic spans multiple domains — focus on YOUR area of expertise only, don't duplicate what peers would cover
- Respond if no peer is better suited (don't let messages go unanswered)
Avoiding Redundancy
- Check the conversation history for
[bot:PeerName]entries - If a peer already covered a topic, don't repeat it — add new information or skip
- When a topic spans multiple domains, scope your response to your own expertise
Calling Peer Bots
You can call other GolemBot instances directly via their HTTP API when you need their capabilities:
# Ask a peer bot a question
curl -s -X POST http://<peer-url>/chat \
-H 'Content-Type: application/json' \
-d '{"message": "your question here", "sessionKey": "cross-bot-<context>"}'
# Check a peer's status
curl -s http://<peer-url>/healthError Handling for Peer Calls
Peer bots may be temporarily unavailable. Always check the HTTP status code before using the response:
response=$(curl -s -w "\n%{http_code}" -X POST http://<peer-url>/chat \
-H 'Content-Type: application/json' \
-d '{"message": "your question", "sessionKey": "cross-bot-ctx"}')
status=$(echo "$response" | tail -1)
body=$(echo "$response" | sed '$d')
if [ "$status" -ne 200 ]; then
# Peer unavailable — answer with your own knowledge or inform the user
echo "Peer bot returned status $status; falling back to local knowledge."
fiWhen to Call a Peer
- You need data or analysis from another domain (e.g., you're the product bot and need user feedback data from the user-research bot)
- A user asks you something outside your expertise — call the appropriate peer, then synthesize the response
- You want to verify or cross-reference information
When NOT to Call a Peer
- The question is within your own domain
- The peer is likely to respond on their own in the group chat (redundant)
- Simple factual questions you can answer yourself
Discovering Peers
Peer information is automatically injected by the gateway from fleet discovery. You can also check:
# List all running GolemBot instances
curl -s http://localhost:4000/api/fleetConversation History Labels
In group chat history, messages are labeled:
[username]— human message[bot:BotName]— message from a peer bot
Use these labels to understand the conversation context and avoid repeating what peers have already said.
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.

