cyrus-setup-slack
Configure Slack integration for Cyrus — create a Slack app from manifest, then guide the user to save credentials.
What this skill does
**CRITICAL: Never use `Read`, `Edit`, or `Write` tools on `~/.cyrus/.env` or any file inside `~/.cyrus/`. Use only `Bash` commands (`grep`, `printf >>`, etc.) to interact with env files — secrets must never be read into the conversation context. Never scrape, extract, or read secret values from web pages — guide the user to copy them manually.**
# Setup Slack
Creates a Slack application from a pre-built manifest so Cyrus can respond to messages in Slack channels.
## Step 1: Check Existing Configuration
```bash
grep -E '^SLACK_BOT_TOKEN=' ~/.cyrus/.env 2>/dev/null
```
If `SLACK_BOT_TOKEN` is already set, inform the user:
> Slack is already configured. Skipping this step.
> To reconfigure, remove `SLACK_BOT_TOKEN` and `SLACK_SIGNING_SECRET` from `~/.cyrus/.env` and re-run.
Skip to completion.
## Step 2: Read Variables
Read the base URL (set by `setup-endpoint`):
```bash
grep '^CYRUS_BASE_URL=' ~/.cyrus/.env | cut -d= -f2-
```
You also need `AGENT_NAME` and `AGENT_DESCRIPTION` — these were collected in Step 0 of the orchestrator and should be available from the conversation context.
## Step 3: Build Manifest JSON
Construct the manifest, substituting `<AGENT_NAME>`, `<AGENT_DESCRIPTION>`, and `<CYRUS_BASE_URL>` with actual values.
**IMPORTANT: Use the manifest template EXACTLY as shown below.** The event subscription path MUST be `/slack-webhook` (not `/slack/events` or any other path). This matches the route registered by `SlackEventTransport` in the Cyrus codebase.
**NOTE: this list of 'scopes' must be kept in sync with the list of scopes in the skill defined at: [https://github.com/cyrusagents/cyrus-hosted/blob/main/.claude/skills/preview-init/SKILL.md](https://github.com/cyrusagents/cyrus-hosted/blob/main/.claude/skills/preview-init/SKILL.md) , as well as the list of scopes defined at [https://github.com/cyrusagents/cyrus-hosted/blob/main/apps/app/src/lib/slack/constants.ts](https://github.com/cyrusagents/cyrus-hosted/blob/main/apps/app/src/lib/slack/constants.ts). If you change here you must also propose changes in those locations.**
```json
{
"display_information": {
"name": "<AGENT_NAME>",
"description": "<AGENT_DESCRIPTION>",
"background_color": "#00240e"
},
"features": {
"bot_user": {
"display_name": "<AGENT_NAME>",
"always_online": true
}
},
"oauth_config": {
"redirect_urls": [
"<CYRUS_BASE_URL>/slack/oauth/callback"
],
"scopes": {
"user": [
"canvases:read",
"canvases:write",
"channels:history",
"chat:write",
"groups:history",
"im:history",
"mpim:history",
"users:read",
"users:read.email",
"reactions:write",
"search:read.public",
"search:read.private",
"search:read.mpim",
"search:read.im",
"search:read.files",
"search:read.users"
],
"bot": [
"groups:read",
"app_mentions:read",
"assistant:write",
"canvases:write",
"channels:history",
"channels:read",
"chat:write",
"chat:write.customize",
"groups:history",
"im:history",
"im:read",
"files:read",
"files:write",
"mpim:history",
"reactions:write",
"search:read.files",
"search:read.public",
"search:read.users",
"users:read",
"users:read.email",
"mpim:read"
]
},
"pkce_enabled": false
},
"settings": {
"event_subscriptions": {
"request_url": "<CYRUS_BASE_URL>/slack-webhook",
"bot_events": [
"app_mention",
"member_joined_channel",
"message.channels",
"message.groups",
"message.mpim",
"message.im"
]
},
"org_deploy_enabled": false,
"socket_mode_enabled": false,
"token_rotation_enabled": false
}
}
```
## Step 4: Create Slack App
**All paths use the "From a manifest" flow.** Never create the app "From scratch".
Determine which browser automation mode to use (see orchestrator rules):
1. If `claude-in-chrome` MCP tools are available → use **Path A-1** (claude-in-chrome)
2. If `agent-browser` is installed and a Chrome debug session is connected → use **Path A-2** (agent-browser)
3. Otherwise → use **Path B** (manual)
### Path A-1: claude-in-chrome Automation
Use the `mcp__claude-in-chrome__*` tools to navigate and interact with the user's existing Chrome browser.
1. Navigate to https://api.slack.com/apps
2. Click **Create New App**
3. Select **From a manifest** in the modal
4. Pick the workspace
5. Click **Next**
6. Select **JSON** tab and paste the manifest from Step 3 (fully substituted with real values)
7. Click **Next**, review, click **Create**
After creation, the app lands on the Basic Information page. **Do NOT take screenshots of credential pages.** Proceed to Step 5 (credential collection).
### Path A-2: agent-browser Automation
If `agent-browser` is connected to a Chrome debug session:
#### 4a. Navigate to Slack app creation
```bash
agent-browser navigate "https://api.slack.com/apps"
```
Take a screenshot to verify the page loaded and the user is logged in.
#### 4b. Click "Create New App"
```bash
agent-browser click "button:text('Create New App')"
```
#### 4c. Select "From a manifest" in the modal
```bash
agent-browser click "button:text('From a manifest')"
```
#### 4d. Select workspace
Take a screenshot to see the workspace picker. Click the appropriate workspace. If multiple are listed, ask the user which one.
```bash
agent-browser click "button:text('Next')"
```
#### 4e. Select JSON format and paste manifest
Click the **JSON** tab if not already selected:
```bash
agent-browser click "button:text('JSON')"
```
Paste the manifest using JavaScript:
```bash
agent-browser eval "var editor = document.querySelector('textarea, [role=\"textbox\"], .ace_editor textarea, .CodeMirror textarea'); if (editor) { var nativeInputValueSetter = Object.getOwnPropertyDescriptor(window.HTMLTextAreaElement.prototype, 'value').set; nativeInputValueSetter.call(editor, JSON.stringify(<MANIFEST_JSON>, null, 2)); editor.dispatchEvent(new Event('input', { bubbles: true })); 'pasted'; } else { 'editor not found'; }"
```
If that doesn't work, try:
```bash
agent-browser click "textarea"
agent-browser keyboard "Control+a"
agent-browser type '<MANIFEST_JSON_STRING>'
```
Take a screenshot to verify, then click **Next**:
```bash
agent-browser click "button:text('Next')"
```
#### 4f. Review and create
Take a screenshot to verify the summary, then click **Create**:
```bash
agent-browser click "button:text('Create')"
```
After creation, **do NOT screenshot credential pages or attempt to scrape secrets.** Proceed to Step 5.
### Path B: Manual Guided Setup
Guide the user through the manifest flow:
> ### Create a Slack App
>
> 1. Go to https://api.slack.com/apps
> 2. Click **Create New App**
> 3. In the modal, select **From a manifest**
> 4. Pick the **workspace** you want to associate the app with
> 5. Click **Next**
> 6. Select **JSON** format and paste the following manifest:
Print the fully-substituted manifest JSON for the user to copy.
> 7. Click **Next**, review the summary, then click **Create**
Proceed to Step 5.
## Step 5: Install App & Collect Credentials
After the app is created (via any path), guide the user through installation and credential collection. **The agent must NOT scrape, read, or extract secrets from the page.** TheRelated in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.