Setup
If ~/chat-rooom/ does not exist or is empty, read setup.md silently. Default to local-first coordination and keep persistence light until the user confirms they want a durable room workflow.
When to Use
User wants multiple agents to talk, coordinate, debate, or hand off work without copying terminal output around. Use when a task benefits from channels, mentions, lightweight ownership, or an auditable shared log inside the current workspace.
Architecture
Skill memory lives in ~/chat-rooom/. Active rooms live in the current workspace at .chat-rooom/. See memory-template.md for both templates.
~/chat-rooom/
|- memory.md # Activation defaults and durable preferences
|- rooms.md # Recent room names, roles, and conventions
`- patterns.md # Coordination patterns that repeatedly worked well
<workspace>/.chat-rooom/
`- rooms/<room>/
|- room.md # Purpose, roster, channels, status
|- summary.md # Snapshot, decisions, next actions
|- jobs.md # Work items with owner and state
|- claims.md # File, task, or test ownership
|- channels/general.md # Shared timeline
|- channels/review.md # Critique and approval requests
`- inbox/<agent>.md # Pending mentions and directed asks
Quick Reference
| Topic |
File |
| Setup process |
setup.md |
| Memory template |
memory-template.md |
| Room protocol |
protocol.md |
| Daily operations |
operations.md |
| Example room patterns |
patterns.md |
Core Rules
1. Start Coordination Inside a Named Room
- Create or join one named room before multi-agent work starts.
- Keep one room per objective, incident, or milestone so decisions stay discoverable.
- Do not scatter the same coordination across scratch files, comments, and terminal notes.
2. Make Every Message Addressable
- Each message should carry one primary intent: ask, update, proposal, decision, block, or handoff.
- Use
@agent mentions for directed work. Use @all only for blocking context changes or final checkpoints.
- Link exact paths, commands, or commits instead of pasting large blobs that bury the action item.
3. Claim Shared Surfaces Before Editing Them
- Update the claims table before touching the same file, test target, or subtask as another agent.
- Claim the smallest useful surface to reduce idle waiting.
- Refresh or release stale claims when work is done, blocked, or handed off.
4. Read the Summary First and Repair It Often
- On join, read the room summary before scrolling the whole channel history.
- When a thread pauses, update summary with status, decisions, open questions, and next owner.
- If summary and channel history diverge, trust the newer timestamp and fix the summary immediately.
5. Separate Channels by Intent
- Keep
general for status, review for critique, build for execution details, and incident for live recovery.
- Create a new channel when one topic would bury another.
- Once a task becomes active, avoid mixing debate and execution in the same channel.
6. Keep the Room Local and Auditable
- Prefer workspace files and local tools over a hosted chat backend unless the user explicitly asks for one.
- Treat the room as an operational log, not as private memory.
- Never store secrets, tokens, or unrelated personal data in room files.
Common Traps
- Starting a room without a clear objective or roster -> duplicate work and vague ownership.
- Posting long monologues instead of targeted asks -> agents miss the real action item.
- Editing shared files without a claim -> merge collisions and silent overwrites.
- Leaving a room without updating summary or jobs -> the next agent rereads everything.
- Using
@all for routine chatter -> noisy wakeups and wasted context.
Security & Privacy
Data that leaves your machine:
- None from this skill itself
Data that stays local:
- Room logs and defaults in
~/chat-rooom/ and .chat-rooom/ inside the active workspace
This skill does NOT:
- Require a hosted backend
- Access undeclared folders outside the active workspace and
~/chat-rooom/
- Store credentials or secrets in room logs
Scope
This skill ONLY:
- Sets up local chatroom coordination patterns for multiple agents
- Keeps channels, claims, jobs, and summaries consistent
- Helps agents talk through room files instead of terminal copy-paste
This skill NEVER:
- Promise real-time transport that is not available locally
- Replace version control or formal code review
- Treat room logs as a secret store
Related Skills
Install with clawhub install <slug> if user confirms:
chat - Communication preference memory for cleaner agent interactions.
agent - Agent behavior and prompting patterns for consistent roles.
agents - Multi-agent system design and safety boundaries.
agentic-engineering - Multi-agent operating patterns and coordination strategy.
delegate - Structured handoffs when work should move between agents.
Feedback
- If useful:
clawhub star chat-rooom
- Stay updated:
clawhub sync
1---2name: chat-rooom3description: Create local chat rooms for AI agents with channels, mentions, task claims, and durable summaries in the workspace.4---56## Setup78If `~/chat-rooom/` does not exist or is empty, read `setup.md` silently. Default to local-first coordination and keep persistence light until the user confirms they want a durable room workflow.910## When to Use1112User wants multiple agents to talk, coordinate, debate, or hand off work without copying terminal output around. Use when a task benefits from channels, mentions, lightweight ownership, or an auditable shared log inside the current workspace.1314## Architecture1516Skill memory lives in `~/chat-rooom/`. Active rooms live in the current workspace at `.chat-rooom/`. See `memory-template.md` for both templates.1718```text19~/chat-rooom/20|- memory.md # Activation defaults and durable preferences21|- rooms.md # Recent room names, roles, and conventions22`- patterns.md # Coordination patterns that repeatedly worked well2324<workspace>/.chat-rooom/25`- rooms/<room>/26 |- room.md # Purpose, roster, channels, status27 |- summary.md # Snapshot, decisions, next actions28 |- jobs.md # Work items with owner and state29 |- claims.md # File, task, or test ownership30 |- channels/general.md # Shared timeline31 |- channels/review.md # Critique and approval requests32 `- inbox/<agent>.md # Pending mentions and directed asks33```3435## Quick Reference3637| Topic | File |38|-------|------|39| Setup process | `setup.md` |40| Memory template | `memory-template.md` |41| Room protocol | `protocol.md` |42| Daily operations | `operations.md` |43| Example room patterns | `patterns.md` |4445## Core Rules4647### 1. Start Coordination Inside a Named Room48- Create or join one named room before multi-agent work starts.49- Keep one room per objective, incident, or milestone so decisions stay discoverable.50- Do not scatter the same coordination across scratch files, comments, and terminal notes.5152### 2. Make Every Message Addressable53- Each message should carry one primary intent: ask, update, proposal, decision, block, or handoff.54- Use `@agent` mentions for directed work. Use `@all` only for blocking context changes or final checkpoints.55- Link exact paths, commands, or commits instead of pasting large blobs that bury the action item.5657### 3. Claim Shared Surfaces Before Editing Them58- Update the claims table before touching the same file, test target, or subtask as another agent.59- Claim the smallest useful surface to reduce idle waiting.60- Refresh or release stale claims when work is done, blocked, or handed off.6162### 4. Read the Summary First and Repair It Often63- On join, read the room summary before scrolling the whole channel history.64- When a thread pauses, update summary with status, decisions, open questions, and next owner.65- If summary and channel history diverge, trust the newer timestamp and fix the summary immediately.6667### 5. Separate Channels by Intent68- Keep `general` for status, `review` for critique, `build` for execution details, and `incident` for live recovery.69- Create a new channel when one topic would bury another.70- Once a task becomes active, avoid mixing debate and execution in the same channel.7172### 6. Keep the Room Local and Auditable73- Prefer workspace files and local tools over a hosted chat backend unless the user explicitly asks for one.74- Treat the room as an operational log, not as private memory.75- Never store secrets, tokens, or unrelated personal data in room files.7677## Common Traps7879- Starting a room without a clear objective or roster -> duplicate work and vague ownership.80- Posting long monologues instead of targeted asks -> agents miss the real action item.81- Editing shared files without a claim -> merge collisions and silent overwrites.82- Leaving a room without updating summary or jobs -> the next agent rereads everything.83- Using `@all` for routine chatter -> noisy wakeups and wasted context.8485## Security & Privacy8687**Data that leaves your machine:**88- None from this skill itself8990**Data that stays local:**91- Room logs and defaults in `~/chat-rooom/` and `.chat-rooom/` inside the active workspace9293**This skill does NOT:**94- Require a hosted backend95- Access undeclared folders outside the active workspace and `~/chat-rooom/`96- Store credentials or secrets in room logs9798## Scope99100This skill ONLY:101- Sets up local chatroom coordination patterns for multiple agents102- Keeps channels, claims, jobs, and summaries consistent103- Helps agents talk through room files instead of terminal copy-paste104105This skill NEVER:106- Promise real-time transport that is not available locally107- Replace version control or formal code review108- Treat room logs as a secret store109110## Related Skills111Install with `clawhub install <slug>` if user confirms:112- `chat` - Communication preference memory for cleaner agent interactions.113- `agent` - Agent behavior and prompting patterns for consistent roles.114- `agents` - Multi-agent system design and safety boundaries.115- `agentic-engineering` - Multi-agent operating patterns and coordination strategy.116- `delegate` - Structured handoffs when work should move between agents.117118## Feedback119120- If useful: `clawhub star chat-rooom`121- Stay updated: `clawhub sync`