跳到正文
cccskills
免费在 GitHub 公开

launch-workshop

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.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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".

实测评分 未实测

查看安装方法

适用场景

  • Prepare desktop environments for a hands-on workshop
  • Distribute or resend attendee access links
  • Recover frozen seats or reset exercise data
  • Shut down workshop environments after a session

包含的文件(1)

  • SKILL.md2.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Launch a workshop

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.

Start ("start the workshop with N seats")

  1. Timing: 60–120 minutes before the session, never more than ~3 hours before (workplace OAuth approvals last about 8 hours).
  2. Confirm the size and cost in one line, then run in the foreground (~2 minutes per wave of ten seats, plus ~2.5 minutes for the Den):
    scripts/workshop/start.sh <seats 1-99> <lifetime-minutes, default 360> <stage, default event> <budget-usd, default 200>
    
    It refuses (before creating anything) if the estimate exceeds the budget, the team quota can't fit the seats, or the app commit isn't merged into dev. Report that message; don't work around it. A different <stage> name gives an independent second launch (its own Den; seats can't share skills across launches).
  3. Read 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.
  4. Spot-check: 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.
  5. scripts/workshop/links.sh <stage> prints one ready-to-paste message per seat; give it to the facilitator verbatim.

During the workshop

RequestCommand
Seat frozen / black screenseat.sh attendeeNN unlock <stage> (attendee reloads the page)
Task stuck / running foreverseat.sh attendeeNN stop <stage>
"My data is a mess"seat.sh attendeeNN reset <stage>
Model missing / no composerseat.sh attendeeNN prepare <stage>
Is this seat OK?seat.sh attendeeNN status <stage>
Resend a linkseat.sh attendeeNN link <stage>
More seatsa 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.

Stop

scripts/workshop/stop.sh <stage> for each stage the facilitator names. Only tear down stages you were asked to.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示英语简介。

  • Registering a feature before implementation
  • Releasing a feature to selected organizations
  • Separating cloud and self-hosted availability
different-ai/openwork2.4万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Connecting browser tools to a local Electron development app
  • Inspecting screen state during debugging
  • Entering a task in the composer and running it
different-ai/openwork2.4万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Checking changes for customer and partner identities
  • Reviewing documents and test data for identifying details
  • Reporting disclosure locations without repeating identities
different-ai/openwork2.4万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Connecting an AI client to OpenWork organization resources
  • Signing in and verifying available MCP tools
  • Switching organizations or troubleshooting authentication
different-ai/openwork2.4万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Screening an outside contributor’s pull request before execution
  • Checking encoded code and unexplained network calls
  • Reviewing dependency changes and installation scripts
different-ai/openwork2.4万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Adding custom tools to OpenWork
  • Creating a plugin to save and list notes
  • Running custom code before or after tool execution
different-ai/openwork2.4万2026年10月23日 更新

查看 different-ai 的全部技能

报告此技能的问题