跳到正文
cccskills
免费在 GitHub 公开

set-up-openwork-slack

Set up the OpenWork assistant in Slack for an approved private-alpha organization using its existing app and individual account connections. Configure permissions and reply settings, link the requesting member, and verify completed answers in DMs and allowed channels.

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

Configure and verify the OpenWork Slack assistant for an approved private-alpha organization, using its existing Slack app and individual-account connector. Use when a user wants @openwork in Slack or needs help installing or linking it.

集成工具Slack
查看安装方法

适用场景

  • Setting up @openwork in a Slack workspace
  • Linking a member's Slack and OpenWork accounts
  • Configuring allowed channels and reply visibility
  • Verifying DM and channel mention responses

包含的文件(1)

  • SKILL.md4.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

OpenWork in Slack — private alpha

Guides: https://openworklabs.com/docs/slack/set-up-the-slack-app.md (administrator setup) and https://openworklabs.com/docs/slack/connect-your-account.md (member linking and verification)

Use browser/computer tools for the existing signed-in OpenWork and Slack administration sessions. Prefer supported setup tools if available. This skill does not grant alpha access or authorize actions beyond the user's request and your tools' permissions.

Establish the target

Identify the OpenWork organization, Slack workspace, existing Slack app, and connector. Do not create duplicates. In Connectors → Slack → OpenWork in Slack, check eligibility, platform rollout access, runtime access, installation, enabled state, signing-secret presence, and channel/reply settings. If alpha or runtime access is missing, report the exact missing prerequisite; do not change deployment settings unless requested.

Ask for the user's channel scope if unspecified: selected channel IDs or all channels. Blank channel IDs allows all channels but does not invite the bot. Private replies are a useful rollout default; honor the user's choice.

Configure the existing app

Read the generated manifest from this connector, then read the current manifest in that same Slack app. Merge without removing existing user scopes, optional user scopes, redirects, MCP configuration, or unrelated features. Keep a before/after comparison in memory. Never replace the entire manifest with only the generated fragment.

Required bot scopes: app_mentions:read, chat:write, im:history, im:read, im:write, assistant:write, commands. Required events: app_mention, message.im, app_home_opened, app_context_changed, agent_session_stopped, agent_session_title_changed, app_uninstalled, tokens_revoked.

Use the deployment's generated URLs, not guessed connector IDs: events, interactions, and commands under /v1/integrations/slack/<connectionId>/; bot redirect /v1/integrations/slack/oauth/callback. Bot display name is openwork. App Home Messages must permit messages and slash commands. Agent experience must be on.

If Slack rejects agent_view.enabled, preserve Slack's supported exported agent_view structure and confirm the Agents toggle. Fix validation errors before saving; do not drop required scopes or events.

Transfer the signing secret directly from Basic Information to the connector's signing-secret field. Never print it, put it in chat, save it in files, or rotate it merely to complete setup. If secure transfer is unavailable, let the user paste it directly.

Save the secret, start Add to Slack from OpenWork, and complete authorization within ten minutes in the intended workspace. Follow your tools' approval requirements. Reinstall in Slack confirms installation. Verify the Events URL challenge and save its Verified state. Turn on the connector assistant and requested reply/channel settings.

Link the invoking member

Installation does not link members. Each member must finish their own Slack OAuth flow in Your Connections. If an existing connection predates installation, explain the temporary interruption and obtain authorization to disconnect only that member's Slack connection, then reconnect it. Never use Sign everyone out. The human may need to complete login or authorization; do not impersonate another member.

The bot's /openwork command returns a link to Your Connections. Opening that link or seeing Connected as you on an older connection is not proof that the assistant identity binding exists. A real completed bot answer is the acceptance check.

Verify and report

Send a short DM test and wait for a finished answer, not just On it. In an authorized allowed test channel, invite @openwork, check mention autocomplete, and test a mention. Confirm delivery respects private/channel reply settings. Check setup metrics for completed, active, need-connection, and failed requests.

Do not test by exposing private data in a shared channel. Do not mark channel behavior verified from a DM-only test. If a step fails, inspect its concrete error, make a targeted correction, and retry; stop repeating an unchanged failing installation or authorization.

Report configuration saved, installation, event verification, member linking, DM result, channel result, reply mode, and remaining blockers without credentials. Do not claim success from manifest validation, installation, or an acknowledgement alone.

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19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19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19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19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19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19日 更新

查看 different-ai 的全部技能

报告此技能的问题