Agent skill
paseo-chat
Use chat rooms through the Paseo CLI. Use when the user says "chat room", "room", "coordinate through chat", "shared mailbox", or wants agents to communicate asynchronously.
Install this agent skill to your Project
npx add-skill https://github.com/getpaseo/paseo/tree/main/skills/paseo-chat
SKILL.md
Paseo Chat Skill
This skill teaches how to use chat rooms for agent coordination via the Paseo CLI.
User's arguments: $ARGUMENTS
Prerequisites
Load the Paseo skill first if you need CLI guidance for launching or messaging agents.
Rules
When using chat:
- create a room with
paseo chat createif you need a new room - inspect available rooms with
paseo chat lsandpaseo chat inspect - post with
paseo chat post - read with
paseo chat read - keep reads bounded, usually
--limit 10or--limit 20 - check chat often while working
Mentions are active:
- write mentions inline in the message body as
@<agent-id>to notify a specific agent immediately - use
@everyoneto notify all non-archived, non-internal agents - notifications are sent to the target agent without blocking the chat post
- if a normal post is enough and no one needs to act right now, skip the mention
Command Surface
Create a room
paseo chat create issue-456 --purpose "Coordinate implementation and review"
List rooms
paseo chat ls
Inspect room details
paseo chat inspect issue-456
Post a message
paseo chat post issue-456 "I traced the failure to relay auth. Investigating config loading now."
With a reply:
paseo chat post issue-456 "I can take that next." --reply-to msg-001
With a direct mention:
paseo chat post issue-456 "@<agent-id> Can you verify the relay path next?"
With a room-wide mention:
paseo chat post issue-456 "@everyone Check the latest status update and reply with blockers."
Read recent messages
paseo chat read issue-456 --limit 10
Filter reads
paseo chat read issue-456 --agent <agent-id>
paseo chat read issue-456 --since 5m
paseo chat read issue-456 --since 2026-03-24T10:00:00Z
Wait for new messages
paseo chat wait issue-456 --timeout 60s
Defaults
When creating a room:
- choose a short slug:
issue-456,pr-143-review,relay-cleanup - give it a clear purpose
When using a room:
- read only a bounded window before acting
- post updates when they would help another agent or your future self
- use
--reply-towhen responding to a specific message - use inline
@<agent-id>mentions when you want to get a specific agent's attention - use
@everyonewhen the whole active team needs to react now - check chat frequently enough that shared coordination actually works
- your own agent ID is available via
$PASEO_AGENT_ID
Typical things to post:
- status updates
- blockers
- handoffs
- review findings
- important context another agent may need later
Your Job
- Understand whether you should use an existing room or create a new one
- Create the room with
paseo chat createif needed - Read the room with bounded history
- Post clearly
- Use
--reply-towhen replying to a specific message - Use inline
@<agent-id>mentions when you want to notify someone directly - Use
@everyonewhen you need to notify all active non-archived agents
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
paseo-committee
Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.
paseo-loop
Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.
paseo
Paseo CLI reference for managing agents. Load this skill whenever you need to use paseo commands.
paseo-handoff
Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent (Codex or Claude).
paseo-orchestrate
End-to-end implementation orchestrator. Use when the user says "orchestrate", "implement this end to end", "build this", or wants a full feature/fix implemented through a team of agents with planning, implementation, review, and QA phases.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Didn't find tool you were looking for?