Set up and manage an OpenWork workshop with 1–99 attendee desktops and fictional workplace data. Prepare seats, distribute access links, check readiness, resolve common session problems, reset exercise data, and shut down requested workshop environments.
Start, size, check, hand out, fix and stop a hands-on OpenWork workshop (one private Den + 1-99 Daytona desktops, fictional Outlook/Calendar/Drive/Jira/Confluence). Use when the user says "start the workshop", "give me N workshop desktops", "add seats", "send me the workshop links", "seat N is stuck", "reset the workshop" or "stop the workshop".
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Scripts live in scripts/workshop/ (run from the repo root); details and the
safety model are in worlds/WORKSHOP-FLEET.md. Private output (attendee links,
member test logins) goes to ~/.openwork/workshops/<stage>/. Never paste
viewer links anywhere except the facilitator's own conversation unless they ask:
each link controls one attendee's desktop.
scripts/workshop/start.sh <seats 1-99> <lifetime-minutes, default 360> <stage, default event> <budget-usd, default 200>
<stage> name gives
an independent second launch (its own Den; seats can't share skills across
launches).READY x/y. For each NOT READY seat run
scripts/workshop/seat.sh attendeeNN prepare <stage> once; if it still fails,
leave it out and say so.seat.sh attendee01 status <stage> and seat.sh attendee01 task <stage> must both print PASS; then seat.sh attendee01 prepare <stage> so
the seat starts on a fresh task.scripts/workshop/links.sh <stage> prints one ready-to-paste message per
seat; give it to the facilitator verbatim.| Request | Command |
|---|---|
| Seat frozen / black screen | seat.sh attendeeNN unlock <stage> (attendee reloads the page) |
| Task stuck / running forever | seat.sh attendeeNN stop <stage> |
| "My data is a mess" | seat.sh attendeeNN reset <stage> |
| Model missing / no composer | seat.sh attendeeNN prepare <stage> |
| Is this seat OK? | seat.sh attendeeNN status <stage> |
| Resend a link | seat.sh attendeeNN link <stage> |
| More seats | a new launch: start.sh <n> <minutes left> <new-stage> |
Reset restores the fictional data only; sign-in and connections stay, chats and desktop files remain.
scripts/workshop/stop.sh <stage> for each stage the facilitator names. Only
tear down stages you were asked to.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Manage OpenWork feature releases with feature flags, switches that control access to new behavior. Register features before coding, release them by organization and deployment, prepare a global shutdown option, and remove temporary flags after rollout.
Connect OpenCode browser tools to a locally running OpenWork Electron app to inspect its UI, enter a task, and check the response. This skill supports exploration and debugging through CDP, Chrome's remote control protocol.
Check added lines in a change for information identifying customers, prospects, partners, or outside individuals. Report locations and generic remediation without reproducing identities, and escalate cases where the information is already public.
Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.
Review an outside contributor’s pull request before running its code. Identify concealed behavior, obfuscated code, risky dependencies, and build hooks, with file locations and specific checks for maintainers to follow up.
Create an OpenCode plugin for OpenWork with custom tools and hooks, which run code at specific events. The skill builds the plugin file and adds its entry to the project configuration.