dayour/scout-deployer/cowork-chat
Claude Code and agent skill by dayour/scout-deployer
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Launch and manage the interactive `cowork chat` REPL in a persistent PowerShell session for streaming multi-turn chat.
Install
npx vskill@latest install dayour/scout-deployer/cowork-chatSKILL.md
The same SKILL.md was published earlier as darbotlabs/scout-deployer/cowork-chat.
Use this skill when the user wants an interactive Cowork chat REPL rather than the full TUI or one-shot send.
Command surface:
cowork chat [OPTIONS]- Useful options include
--island/-i,--user/-u,--model/-m,--profile/-p,--container-type,--resume,--resume-latest/-R,--auto-approve,--mock-mode,--poll, and repeated--flag key=value. - Slash commands inside chat include
/help,/new,/ref email:<subject>,/ref onedrive:<url>,/ref meeting:<title>,/upload <path>,/files,/download 1,/trace,/raw,/island <name>,/model <name>,/id, and/quit.
Workflow:
- Check whether a
cowork-chatPowerShell session is already active withlist_powershell. - If active, use
read_powershellfor current output andwrite_powershellfor user messages or slash commands. - If not active, verify
coworkexists and startcowork chatusingpowershellwithmode: "async",shellId: "cowork-chat", and an initial wait around 10 seconds. - Include user-requested command flags when starting, such as model, profile, island, or resume latest.
- Do not start duplicate chat sessions unless the user asks for a fresh session.
- Stop only when the user asks, preferably by sending
/quitwithwrite_powershell; usestop_powershellonly if needed.
Operational notes:
- Use async mode so the REPL stays interactive.
- Do not use detached mode unless the user explicitly wants a process that survives Clawpilot shutdown.
- Avoid name-based process termination.
- Keep responses concise: running, already active, message sent, or stopped.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/cowork-chat/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/dayour/scout-deployer/cowork-chat)