Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Communication & Collaboration
Ai Collab
Multi-agent autonomous collaboration system for two OpenClaw agents working in parallel. Use when setting up agent-to-agent communication, running a daemon a...
skill openclawclawhub Free
Multi-agent autonomous collaboration system for two OpenClaw agents working in parallel. Use when setting up agent-to-agent communication, running a daemon a...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, _meta.json, examples/claude-claude.md, examples/claude-gpt.md, examples/jim-workflow-prompt.md, references/protocol.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 2.0.0
Provenance
- Publisher
- jeremysommerfeld8910-cpu
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
ai-collab โ Autonomous Multi-Agent Collaboration
Two OpenClaw agents working in parallel on shared tasks, coordinated via a structured chat log and daemon inbox protocol.
Architecture Overview
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ User (Jeremy) โ โ Telegram / Direct Message โ โโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ โโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโ โผ โผ โโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ โ AGENT A โ โ AGENT B โ โ (Jim / main) โโโโโโโโโโบโ (Clawdy / daemon)โ โ claude code โ โ claude --print โ โ port: main โ โ inbox: filesystem โ โโโโโโโโโโฌโโโโโโโโโ โโโโโโโโโโฌโโโโโโโโโโ โ โ โโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโ โผ โโโโโโโโโโโโโโโโโโโโ โ chat.log โ โ THE shared record โ collab/inbox/ โ โ AโB messages โโโโโโโโโโโโโโโโโโโโ Agent A (Primary): Interactive Claude Code session. Handles browser, complex tasks, user-facing responses. Agent B (Daemon): claude --print subprocess. Handles background tasks, monitoring, quick lookups. Triggered by messages dropped in inbox.
Configuration
All settings via environment variables โ no hardcoded values: # ~/.openclaw/workspace/collab/.ai-collab.env export AGENT_A_NAME=Jim export AGENT_B_NAME=Clawdy export AGENT_B_MODEL=claude-haiku-4-5-20251001 # Any claude --print compatible model export AGENT_B_SESSION=clawdy-session # tmux session name export COLLAB_INBOX=$HOME/.openclaw/workspace/collab/inbox export COLLAB_LOG=$HOME/.openclaw/workspace/collab/chat.log Supported models for AGENT_B_MODEL: claude-haiku-4-5-20251001 โ fastest, cheapest (recommended for daemon) claude-sonnet-4-6 โ more capable, higher cost Any OpenAI model if using the GPT daemon variant (see examples/claude-gpt.md)
Quick Setup
# 1. Source config source ~/.openclaw/workspace/collab/.ai-collab.env # 2. Create the collab workspace mkdir -p "$COLLAB_INBOX" # 3. Start Agent B daemon (in a tmux session) tmux new-session -d -s "$AGENT_B_SESSION" \ "source ~/.openclaw/workspace/collab/.ai-collab.env && \ bash ~/.openclaw/workspace/skills/ai-collab/scripts/daemon.sh" # 4. Start message polling (Agent B โ Agent A routing, runs every 60s via cron) bash ~/.openclaw/workspace/skills/ai-collab/scripts/poll_chatlog.sh & # 5. Test the link bash ~/.openclaw/workspace/skills/ai-collab/scripts/send.sh "Hello from Agent A"
Communication Protocol
Every message between agents follows this format. No open loops. TagDirectionMeaning[TASK:name]AโB or BโAAssign a task[ACK:name]receiverAcknowledged, starting work[DONE:name]executorTask complete + one-line result[BLOCKED:name]executorCan't complete + reason[HANDOFF:name]either"Do X, reply [DONE:name] when finished"[STATUS:update]eitherAsync update on long-running task[QUESTION:topic]eitherNeeds info before proceeding Rules: Answer questions before asking new ones Close tasks before starting new ones Every message moves work forward or closes a loop Never: "let me know", "ready when you are", "standing by" Example exchange: A โ B: [TASK:price-check] Get BTC price from CoinGecko B โ A: [ACK:price-check] Checking now. B โ A: [DONE:price-check] BTC $94,230 as of 03:15 UTC
Daemon Script (Agent B)
scripts/daemon.sh โ drop in your collab directory: #!/bin/bash PIDFILE="/tmp/agentb_daemon.pid" if [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null; then echo "Daemon already running (PID $(cat $PIDFILE)). Exiting." >&2 exit 1 fi echo $$ > "$PIDFILE" trap "rm -f $PIDFILE" EXIT # Required: unset so nested claude --print works unset CLAUDECODE INBOX="$HOME/.openclaw/workspace/collab/inbox" LOG="$HOME/.openclaw/workspace/collab/chat.log" mkdir -p "$INBOX" logline() { printf "%s %s\n" "$(date '+%Y-%m-%d %H:%M:%S')" "$1" >> "$LOG" } logline "SYSTEM: Agent B daemon started" inotifywait -m -e moved_to "$INBOX" 2>/dev/null | while read dir event file; do FULLPATH="$INBOX/$file" [ ! -f "$FULLPATH" ] && continue MSG=$(cat "$FULLPATH") rm "$FULLPATH" logline "A -> B: $MSG" # Run Agent B (claude --print) RESPONSE=$(claude --print --model claude-haiku-4-5-20251001 \ "You are Agent B. Agent A says: $MSG Respond in under 100 words. Use [DONE:taskname] or [BLOCKED:taskname] to close loops. Context: shared collab system. Chat log: $LOG" 2>/dev/null) logline "B -> A: $RESPONSE" # Route response back to Agent A openclaw agent --agent main -m "[AgentB]: $RESPONSE" --json > /dev/null 2>&1 done
Sending Messages (A โ B)
# From Agent A, send to Agent B daemon inbox bash ~/.openclaw/workspace/skills/ai-collab/scripts/send.sh "your message" Atomic write pattern (prevents partial reads): INBOX="$HOME/.openclaw/workspace/collab/inbox" TMPFILE=$(mktemp "$INBOX/.msg.XXXXXX") echo "$*" > "$TMPFILE" mv "$TMPFILE" "$INBOX/msg_$(date +%s%N).txt" Always use mktemp + mv โ never write directly to inbox. inotifywait fires on moved_to, not close_write.
Chat Log Polling (B โ A)
scripts/poll_chatlog.sh โ run via cron every 60s: #!/bin/bash LOG="$HOME/.openclaw/workspace/collab/chat.log" PTR_FILE="/tmp/chatlog_ptr" [ ! -f "$LOG" ] && exit 0 TOTAL=$(wc -l < "$LOG") LAST=$(cat "$PTR_FILE" 2>/dev/null || echo "0") [ "$TOTAL" -le "$LAST" ] && echo "$TOTAL" > "$PTR_FILE" && exit 0 NEW=$(tail -n +"$((LAST + 1))" "$LOG" | grep "B -> A:" | sed 's/.*B -> A: //') echo "$TOTAL" > "$PTR_FILE" [ -z "$NEW" ] && exit 0 while IFS= read -r line; do [ -z "$line" ] && continue openclaw agent --agent main -m "[AgentB]: $line" --json > /dev/null 2>&1 done <<< "$NEW" Add to crontab: * * * * * /bin/bash ~/.openclaw/workspace/collab/poll_chatlog.sh
Shared Filesystem Conventions
~/.openclaw/workspace/collab/ chat.log # THE shared record โ all messages logged here inbox/ # AโB message queue (atomic mv only) .env # Shared secrets (chmod 600, never log) task_queue.md # Optional: structured task backlog status_tracker.md # Optional: current task status per agent Logging to chat.log: printf "%s %s\n" "$(date '+%Y-%m-%d %H:%M:%S')" "A -> B: [TASK:name] Description" >> "$LOG" Rules: Never log secrets from .env Always timestamp every line Prefix with sender: A -> B: or B -> A: or SYSTEM: or JEREMY ->
Telegram Bridge (Optional)
Route user Telegram messages into Agent B's inbox. Full setup guide: references/telegram-bridge.md Quick summary: Create a bot via @BotFather โ get BOT_TOKEN Add bot to your group โ get GROUP_ID (negative number, e.g. -1001234567890) Disable Group Privacy Mode in BotFather so bot can read all messages Get your Telegram USER_ID from @userinfobot Set in ~/.openclaw/.env: TELEGRAM_BOT_TOKEN, TELEGRAM_GROUP_ID, TELEGRAM_USER_ID Run the bridge in tmux: tmux new-session -d -s tg-bridge "bash references/telegram-bridge.md" # Minimal bridge loop (inline version): source ~/.openclaw/.env OFFSET_FILE="/tmp/tg_offset" while true; do OFFSET=$(cat "$OFFSET_FILE" 2>/dev/null || echo "0") UPDATES=$(curl -s "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getUpdates?offset=$((OFFSET+1))&timeout=20") # Parse updates, drop user messages into inbox with USER: prefix # See references/telegram-bridge.md for full parsing implementation sleep 1 done See references/telegram-bridge.md for the complete production-ready implementation with message parsing, offset tracking, and error handling.
Agent Configurations
See examples/ for full configs:
Claude โ Claude (Jim + Clawdy)
Agent A: claude code (interactive, full tool access) Agent B: claude --print claude-haiku-4-5-20251001 (fast, scripting-optimized) Best for: heavy task parallelism, one agent researches while other implements
Claude โ GPT
Agent A: Claude Code (full tool use) Agent B: openai api chat.completions.create via script Best for: cross-model verification, Claude builds โ GPT reviews
GPT โ GPT
Agent A: GPT-4o via openai CLI Agent B: GPT-4o-mini for fast background checks Best for: speed + cost optimization when all context is OpenAI
Task Handoff Pattern
When Agent A needs Agent B to own a task completely: A โ B: [HANDOFF:data-fetch] Fetch all BTC trades from Kraken API last 7 days. Save to ~/.openclaw/workspace/collab/kraken_trades.json. Reply [DONE:data-fetch] when finished. B โ A: [ACK:data-fetch] Fetching now. B โ A: [DONE:data-fetch] 847 trades saved to kraken_trades.json. Date range: 2026-02-15 to 2026-02-22. Agent A does not check on progress โ waits for DONE or BLOCKED.
Approval Pattern
When Agent B's daemon needs user approval for a terminal command: # From Agent A / user terminal: bash ~/.openclaw/workspace/skills/ai-collab/scripts/approve.sh "Yes" # or for numbered selections: bash ~/.openclaw/workspace/skills/ai-collab/scripts/approve.sh "2" approve.sh sends keystrokes to the tmux session running Agent B: SESSION=$(tmux ls | grep agentb-session | head -1 | cut -d: -f1) tmux send-keys -t "$SESSION" "$1" Enter
Rate Limiting
Agent B should implement a rate governor to prevent runaway API calls: # In daemon loop, before calling claude --print: CALLS_FILE="/tmp/agentb_calls" WINDOW=60 # seconds MAX_CALLS=10 # Count calls in last window RECENT=$(awk -v cutoff="$(($(date +%s) - WINDOW))" '$1 > cutoff' "$CALLS_FILE" 2>/dev/null | wc -l) if [ "$RECENT" -ge "$MAX_CALLS" ]; then logline "SYSTEM: Rate limited โ $RECENT calls in ${WINDOW}s" sleep 10 continue fi date +%s >> "$CALLS_FILE"
Financial Gate Protocol (TIERED โ updated 2026-02-22)
Three tiers based on amount: TierAmountRule1Under $20Either agent acts independently โ no approval needed2$20โ$50Both agents PROPOSE + APPROVE before acting3Over $50Requires [AUTHORIZED:financial:amount:timestamp:Jeremy] tag # Tier 3 tag format (Jeremy must write to chat.log): [AUTHORIZED:financial:buy:BTC:$100:2026-02-22:Jeremy] # Tier 2 example flow: # Clawdy proposes: "PROPOSE: buy $35 of SOL for DePIN gas โ approve?" # Jim approves: "APPROVED: buy $35 SOL" # Then Clawdy acts. Daemon tiered gate logic: # <$20: proceed. $20-50: flag as tier2. >$50: block without AUTHORIZED tag. AMOUNT=$(echo "$MSG" | grep -oP '[$]?\d+' | head -1 | tr -d '$') if [ -n "$AMOUNT" ] && [ "$AMOUNT" -gt 50 ] && ! echo "$MSG" | grep -q "\[AUTHORIZED:financial:"; then logline "BLOCKED:financial-gate:tier3 โ amount>$50, no AUTHORIZED tag"; continue elif [ -n "$AMOUNT" ] && [ "$AMOUNT" -ge 20 ]; then logline "FINANCIAL:tier2 โ propose before acting" fi If Tier 3 blocked: log [BLOCKED:financial-gate:tier3], send Telegram alert, do NOT execute.
Daemon Watchdog Pattern
Check daemon health every 15 minutes. If silent >15 min, restart: # check_daemon.sh (add to crontab: */15 * * * *) PIDFILE="/tmp/agentb_daemon.pid" LOG="$HOME/.openclaw/workspace/collab/chat.log" # Check PID alive pid_alive=0 [ -f "$PIDFILE" ] && kill -0 "$(cat $PIDFILE)" 2>/dev/null && pid_alive=1 # Check last activity within 15 min last_ts=$(grep -oP '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}' "$LOG" 2>/dev/null | tail -1) recent=0 if [ -n "$last_ts" ]; then age=$(( ($(date +%s) - $(date -d "$last_ts" +%s 2>/dev/null || echo 0)) / 60 )) [ "$age" -lt 15 ] && recent=1 fi if [ "$pid_alive" = "0" ] || [ "$recent" = "0" ]; then tmux send-keys -t agentb-session "bash daemon.sh" Enter fi
Task Takeover Threshold
If Agent A (Jim) blocks on the same task twice, Agent B (Clawdy) takes it over: B โ A: [TASK:fetch-data] Fetch X. Reply [DONE:fetch-data]. # 10 min timer... A โ B: [BLOCKED:fetch-data] Can't access endpoint. B โ A: [RETRY:fetch-data] Try alternate: curl -s https://backup-endpoint.com/x # Another 10 min... A โ B: [BLOCKED:fetch-data] Still failing. # Clawdy takes over immediately: B: *executes task directly, logs [DONE:fetch-data] to chat.log* Rule: Blocked 2x on same task โ take it over, don't reassign.
Daemon Error Diagnosis
When daemon produces blank/error responses: Check /tmp/clawdy_last_err โ contains last stderr from claude --print Check ANSI-stripped chat.log for CLAWDY_ERR: lines Verify RESPONSE trimming line not corrupted (common issue: accidentally set to RESPONSE="") Restart daemon: kill $(cat /tmp/clawdy_daemon.pid) && sleep 1 && bash clawdy_daemon.sh Auto-approve: Use Bash(*) in ~/.claude/settings.local.json. NEVER use tmux send-keys cron โ it sends keypresses blindly to the wrong sessions.
Category context
Messaging, meetings, inboxes, CRM, and teammate communication surfaces.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
5 Docs1 Config
- SKILL.md
- examples/claude-claude.md
- examples/claude-gpt.md
- examples/jim-workflow-prompt.md
- references/protocol.md
- _meta.json