Chat SDK
databuddy-analytics/Databuddy
Build multi-platform chat bots with Chat SDK (chat npm package).
Send messages and rich content to Slack channels via webhooks or Bot API.
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenClaudia/openclaudia-skills slack-bot --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/slack-bot .claude/skills/slack-bot && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .claude/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-botType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenClaudia/openclaudia-skills slack-bot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/slack-bot .agents/skills/slack-bot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .agents/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenClaudia/openclaudia-skills slack-bot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/slack-bot .cursor/skills/slack-bot && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .cursor/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OpenClaudia/openclaudia-skills.git --path skills/slack-bot--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenClaudia/openclaudia-skills slack-bot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/slack-bot .gemini/skills/slack-bot && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .gemini/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OpenClaudia/openclaudia-skills slack-botInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/slack-bot .github/skills/slack-bot && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .github/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OpenClaudia/openclaudia-skills slack-bot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/slack-bot .opencode/skills/slack-bot && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "slack-bot" agent skill from https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/slack-bot into .opencode/skills/slack-bot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-bot", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
slack-botSend messages and rich content to Slack channels via webhooks or Bot API.
Slack Bot is an agent skill from OpenClaudia/openclaudia-skills. Send messages and rich content to Slack channels via webhooks or Bot API. Use Block Kit for formatted announcements, marketing reports, and community updates. Trigger phrases: "post to slack", "slack message", "slack webhook", "slack notification", "slack announcement", "send to slack", "slack marketing", "slack update", "slack channel".
Its SKILL.md is about 8.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering Webhooks and Chatbots and conversational support. It works with Slack. The repository describes itself as: 77 open-source marketing skills for Claude Code, Codex, and other AI coding agents. SEO, content, email, ads, analytics, and growth. The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 28bf209. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
BashWebFetchWebSearchFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlpython3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
slack.comhooks.slack.comtwitter.comlinkedin.comAlso links to:
api.slack.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SLACK_BOT_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Slack Bot loads about 8.7k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 1,564 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
EBHOOK_URL` or `SLACK_BOT_TOKEN` set in `.env`, `.env.local`, or`~/.claude/.env.global`.source ~/.claude/.env.global 2>/dev/nullsource .env 2>/dev/nullsource .env.local 2>/dev/nullks.slack.com/services/T.../B.../xxxx' >> .envSLACK_BOT_TOKEN=xoxb-your-token-here' >> .envho 'SLACK_DEFAULT_CHANNEL=#marketing' >> .envallowed-tools: Bash, WebFetch, WebSearchAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from OpenClaudia/openclaudia-skills at commit 28bf209, republished under its MIT licence (© OpenClaudia). 1,564 words, ~8,694 tokens.
.claude/skills/slack-bot/SKILL.md (or your agent's skills folder).Send messages and rich content to Slack channels using Incoming Webhooks or the Slack Web API. Build formatted announcements, marketing reports, metrics dashboards, and community updates with Block Kit.
Requires either SLACK_WEBHOOK_URL or SLACK_BOT_TOKEN set in .env, .env.local, or
~/.claude/.env.global.
source ~/.claude/.env.global 2>/dev/null
source .env 2>/dev/null
source .env.local 2>/dev/null
if [ -n "$SLACK_WEBHOOK_URL" ]; then
echo "SLACK_WEBHOOK_URL is set. Webhook mode available."
elif [ -n "$SLACK_BOT_TOKEN" ]; then
echo "SLACK_BOT_TOKEN is set. Web API mode available."
else
echo "Neither SLACK_WEBHOOK_URL nor SLACK_BOT_TOKEN is set."
echo "See the Setup Guide below to configure Slack credentials."
fiIf neither variable is set, instruct the user to follow the Setup Guide section below.
Incoming Webhooks are the fastest way to post messages. They require no OAuth scopes and are scoped to a single channel.
https://hooks.slack.com/services/...).echo 'SLACK_WEBHOOK_URL=https://hooks.slack.com/services/T.../B.../xxxx' >> .envLimitations: One webhook per channel. Cannot read messages, list channels, or reply to
threads programmatically (you must know the thread_ts from a prior API response).
Bot tokens give access to the full Slack Web API: post to any channel the bot is in, reply to threads, list channels, upload files, and more.
chat:write - Post messageschat:write.public - Post to channels without joiningchannels:read - List public channelsfiles:write - Upload files (optional, for images/reports)reactions:write - Add emoji reactions (optional)xoxb-).echo 'SLACK_BOT_TOKEN=xoxb-your-token-here' >> .env/invite @YourBotName in each channel.Optional: Set a default channel for convenience:
echo 'SLACK_DEFAULT_CHANNEL=#marketing' >> .envcurl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"text": "Hello from the marketing bot!"
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"text": "New blog post published!",
"username": "Marketing Bot",
"icon_emoji": ":mega:"
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": "New Product Launch"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*Product X* is now live! Check out the announcement."
}
},
{
"type": "divider"
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "Read the full announcement on our blog."
},
"accessory": {
"type": "button",
"text": {
"type": "plain_text",
"text": "Read More"
},
"url": "https://example.com/blog/launch"
}
}
]
}'The Web API provides full control over message delivery, threading, channel management, and more.
All requests go to https://slack.com/api/ with the header Authorization: Bearer {SLACK_BOT_TOKEN}.
curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"channel": "#marketing",
"text": "Weekly metrics report is ready!",
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": "Weekly Marketing Metrics"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "Here are the numbers for this week."
}
}
]
}'The response includes a ts (timestamp) field which identifies the message. Save this value
for threading replies:
# Post and capture the message timestamp for threading
RESPONSE=$(curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"channel": "#marketing",
"text": "Thread parent message"
}')
MESSAGE_TS=$(echo "$RESPONSE" | python3 -c "import json,sys; print(json.load(sys.stdin).get('ts',''))")
echo "Message timestamp: $MESSAGE_TS"Use the thread_ts parameter to reply inside an existing thread:
curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"channel\": \"#marketing\",
\"thread_ts\": \"${MESSAGE_TS}\",
\"text\": \"This is a threaded reply with additional details.\"
}"To also broadcast the reply to the channel (so it appears in the main conversation as well),
add "reply_broadcast": true.
curl -s -X POST "https://slack.com/api/chat.update" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"channel\": \"#marketing\",
\"ts\": \"${MESSAGE_TS}\",
\"text\": \"Updated message content.\",
\"blocks\": []
}"curl -s -X POST "https://slack.com/api/chat.delete" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"channel\": \"#marketing\",
\"ts\": \"${MESSAGE_TS}\"
}"Useful for discovering which channel to post to:
curl -s "https://slack.com/api/conversations.list?types=public_channel&limit=100" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" | \
python3 -c "
import json, sys
data = json.load(sys.stdin)
for ch in data.get('channels', []):
members = ch.get('num_members', 0)
print(f\"#{ch['name']} | Members: {members} | ID: {ch['id']}\")
"curl -s -X POST "https://slack.com/api/files.uploadV2" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-F "file=@report.pdf" \
-F "filename=weekly-report.pdf" \
-F "channel_id=C0123456789" \
-F "initial_comment=Here is this week's marketing report."curl -s -X POST "https://slack.com/api/reactions.add" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"channel\": \"C0123456789\",
\"timestamp\": \"${MESSAGE_TS}\",
\"name\": \"white_check_mark\"
}"Block Kit is Slack's UI framework for building rich, interactive messages. Messages are composed of an array of blocks, each with a specific type and structure.
| Block Type | Purpose | Supports mrkdwn |
|---|---|---|
header | Large bold title text | No (plain_text only) |
section | Primary content block with text and optional accessory | Yes |
divider | Horizontal line separator | N/A |
image | Full-width image with alt text | N/A |
context | Small, muted text and images (for metadata, timestamps) | Yes |
actions | Row of interactive elements (buttons, selects, date pickers) | N/A |
rich_text | Advanced formatted text (lists, quotes, code blocks) | N/A |
{
"type": "header",
"text": {
"type": "plain_text",
"text": "Weekly Marketing Report",
"emoji": true
}
}Plain text section:
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*Traffic is up 23%* this week compared to last week.\nOrganic search drove most of the growth."
}
}Section with fields (two-column layout):
{
"type": "section",
"fields": [
{
"type": "mrkdwn",
"text": "*Visitors*\n12,450"
},
{
"type": "mrkdwn",
"text": "*Signups*\n342"
},
{
"type": "mrkdwn",
"text": "*MRR*\n$28,500"
},
{
"type": "mrkdwn",
"text": "*Churn*\n1.2%"
}
]
}Section with a button accessory:
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "New blog post: *How We Grew 10x in 6 Months*"
},
"accessory": {
"type": "button",
"text": {
"type": "plain_text",
"text": "Read Post"
},
"url": "https://example.com/blog/growth-story",
"action_id": "read_blog_post"
}
}Section with an image accessory:
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*New Feature: Dark Mode*\nOur most requested feature is finally here."
},
"accessory": {
"type": "image",
"image_url": "https://example.com/images/dark-mode-preview.png",
"alt_text": "Dark mode preview"
}
}{
"type": "divider"
}{
"type": "image",
"image_url": "https://example.com/images/chart.png",
"alt_text": "Weekly traffic chart",
"title": {
"type": "plain_text",
"text": "Traffic Overview"
}
}{
"type": "context",
"elements": [
{
"type": "mrkdwn",
"text": "Posted by *Marketing Team* | Feb 10, 2026"
},
{
"type": "image",
"image_url": "https://example.com/logo-small.png",
"alt_text": "Company logo"
}
]
}{
"type": "actions",
"elements": [
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Approve"
},
"style": "primary",
"action_id": "approve_action",
"value": "approved"
},
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Reject"
},
"style": "danger",
"action_id": "reject_action",
"value": "rejected"
},
{
"type": "button",
"text": {
"type": "plain_text",
"text": "View Details"
},
"url": "https://example.com/details",
"action_id": "view_details"
}
]
}Button styles: "primary" (green), "danger" (red), or omit for default (gray).
Note on interactivity: Buttons with action_id (no url) require a Request URL configured
in your Slack App settings under Interactivity & Shortcuts to receive the button click
payload. Buttons with a url field open the link directly and do not require a backend.
| Limit | Value |
|---|---|
| Blocks per message | 50 |
| Characters per text block | 3,000 |
| Characters per header | 150 |
| Fields per section | 10 |
| Elements per actions block | 25 |
| Elements per context block | 10 |
Use the visual builder to design and preview messages before coding them: https://app.slack.com/block-kit-builder
Slack uses its own markdown variant called mrkdwn. It differs from standard Markdown in several ways.
| Formatting | Syntax | Example |
|---|---|---|
| Bold | *text* | bold text |
| Italic | _text_ | italic text |
| Strikethrough | ~text~ | |
| Code (inline) | `text` | inline code |
| Code block | ```text``` | Multi-line code block |
| Blockquote | >text | Quoted text |
| Link | <https://url|display text> | Clickable link |
| User mention | <@U0123456> | @username |
| Channel mention | <#C0123456> | #channel |
| Emoji | :emoji_name: | :rocket: |
| Bulleted list | Start line with - or * | Bullet point |
| Numbered list | Start line with 1. | Numbered item |
| Line break | \n in JSON string | New line |
Important differences from standard Markdown:
*bold*, not double **bold**._italic_, not single asterisks.<url|text> format with a pipe, not [text](url).header block type instead.image block or accessory instead.curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": ":rocket: New Feature: [Feature Name]",
"emoji": true
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "We just shipped *[Feature Name]* — here is what it does and why it matters.\n\n:point_right: *What it does:* [One-sentence description]\n:point_right: *Why it matters:* [Key benefit for users]\n:point_right: *How to try it:* [Quick instructions or link]"
}
},
{
"type": "image",
"image_url": "https://example.com/feature-screenshot.png",
"alt_text": "Feature screenshot"
},
{
"type": "divider"
},
{
"type": "actions",
"elements": [
{
"type": "button",
"text": {
"type": "plain_text",
"text": ":newspaper: Read Announcement",
"emoji": true
},
"url": "https://example.com/blog/feature-launch",
"action_id": "read_announcement"
},
{
"type": "button",
"text": {
"type": "plain_text",
"text": ":play_or_pause_button: Watch Demo",
"emoji": true
},
"url": "https://example.com/demo",
"action_id": "watch_demo"
}
]
},
{
"type": "context",
"elements": [
{
"type": "mrkdwn",
"text": "Posted by *Product Team* | :speech_balloon: Reply in thread with questions"
}
]
}
]
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": ":bar_chart: Weekly Marketing Metrics — Feb 3-9, 2026",
"emoji": true
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "Here is this week'\''s performance snapshot."
}
},
{
"type": "divider"
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":globe_with_meridians: *Website Traffic*"
},
"fields": [
{
"type": "mrkdwn",
"text": "*Sessions*\n45,230 (:arrow_up: 12%)"
},
{
"type": "mrkdwn",
"text": "*Unique Visitors*\n31,870 (:arrow_up: 8%)"
},
{
"type": "mrkdwn",
"text": "*Bounce Rate*\n42.3% (:arrow_down: 2.1%)"
},
{
"type": "mrkdwn",
"text": "*Avg. Session Duration*\n3m 42s (:arrow_up: 15s)"
}
]
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":money_with_wings: *Conversion Metrics*"
},
"fields": [
{
"type": "mrkdwn",
"text": "*Signups*\n487 (:arrow_up: 18%)"
},
{
"type": "mrkdwn",
"text": "*Trial-to-Paid*\n12.4% (:arrow_up: 1.2%)"
},
{
"type": "mrkdwn",
"text": "*MRR*\n$52,300 (:arrow_up: $3,200)"
},
{
"type": "mrkdwn",
"text": "*Churn*\n1.8% (:arrow_down: 0.3%)"
}
]
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":email: *Email Performance*"
},
"fields": [
{
"type": "mrkdwn",
"text": "*Emails Sent*\n12,400"
},
{
"type": "mrkdwn",
"text": "*Open Rate*\n34.2%"
},
{
"type": "mrkdwn",
"text": "*Click Rate*\n4.8%"
},
{
"type": "mrkdwn",
"text": "*Unsubscribes*\n23"
}
]
},
{
"type": "divider"
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*:bulb: Key Takeaways*\n- Organic traffic up 15% after publishing 3 new blog posts\n- Email welcome sequence A/B test: Variant B outperformed by 22%\n- Trial signup spike on Thursday correlated with Product Hunt feature"
}
},
{
"type": "actions",
"elements": [
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Full Dashboard",
"emoji": true
},
"url": "https://analytics.example.com/dashboard",
"action_id": "view_dashboard"
}
]
},
{
"type": "context",
"elements": [
{
"type": "mrkdwn",
"text": "Auto-generated by Marketing Bot | Data from Google Analytics + Stripe"
}
]
}
]
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": ":pencil: New Blog Post Published",
"emoji": true
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*<https://example.com/blog/post-slug|Blog Post Title Here>*\n\nA brief summary of what the post covers — keep it to 2-3 sentences that capture the key value and make people want to click through."
},
"accessory": {
"type": "image",
"image_url": "https://example.com/blog/post-og-image.png",
"alt_text": "Blog post cover image"
}
},
{
"type": "context",
"elements": [
{
"type": "mrkdwn",
"text": ":bust_in_silhouette: Author: *Jane Smith* | :clock1: 6 min read | :label: SEO, Growth"
}
]
},
{
"type": "divider"
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":mega: *Help us amplify!* Share this post on your socials. Here are ready-to-use snippets:\n\n*Twitter/X:* _Just published: [title]. [Key insight from the post]. Link in reply._\n\n*LinkedIn:* _We just published a deep dive on [topic]. Here is the #1 takeaway: [insight]._"
}
},
{
"type": "actions",
"elements": [
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Read the Post",
"emoji": true
},
"style": "primary",
"url": "https://example.com/blog/post-slug",
"action_id": "read_post"
},
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Share on Twitter",
"emoji": true
},
"url": "https://twitter.com/intent/tweet?text=Check%20out%20this%20post&url=https://example.com/blog/post-slug",
"action_id": "share_twitter"
},
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Share on LinkedIn",
"emoji": true
},
"url": "https://www.linkedin.com/sharing/share-offsite/?url=https://example.com/blog/post-slug",
"action_id": "share_linkedin"
}
]
}
]
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": ":clipboard: Marketing Team Update — Monday, Feb 10",
"emoji": true
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*:white_check_mark: Completed Last Week*\n- Launched email welcome sequence v2\n- Published 3 blog posts (SEO, product, case study)\n- Set up Google Ads remarketing campaign\n- Shipped landing page A/B test (Variant B live)"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*:construction: In Progress*\n- Content calendar for March (70% done)\n- Competitor analysis report (due Wednesday)\n- Social media campaign for Product Hunt launch"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*:dart: This Week'\''s Priorities*\n1. Finalize Product Hunt launch assets\n2. Send weekly newsletter (Thursday 9am)\n3. Review and approve Q1 ad spend budget\n4. Onboard new content writer"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*:warning: Blockers*\n- Waiting on design team for Product Hunt gallery images\n- Need legal review on new case study before publishing"
}
},
{
"type": "divider"
},
{
"type": "context",
"elements": [
{
"type": "mrkdwn",
"text": ":speech_balloon: Reply in thread with your own updates or questions"
}
]
}
]
}'curl -s -X POST "$SLACK_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": ":rotating_light: Marketing Alert",
"emoji": true
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*Issue:* [Brief description of the problem]\n*Impact:* [Who/what is affected]\n*Status:* :red_circle: Active\n*Owner:* <@U0123456>"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*Details:*\n[Longer explanation. What happened, when it started, what we know so far.]"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "*Next Steps:*\n1. [Action item 1]\n2. [Action item 2]\n3. [Action item 3]"
}
},
{
"type": "actions",
"elements": [
{
"type": "button",
"text": {
"type": "plain_text",
"text": "Status Page"
},
"url": "https://status.example.com",
"action_id": "status_page"
}
]
}
]
}'When the user asks to post an announcement, product update, or news to Slack:
ts for threading.When the user asks to send a metrics report or dashboard to Slack:
fields for the two-column metric layout.When a new blog post needs to be distributed to the team:
For managing Slack community channels (public communities, customer channels):
TITLE="Product X v2.0 Released"
DESCRIPTION="Version 2.0 includes dark mode, API improvements, and 3x faster performance."
LINK="https://example.com/changelog/v2"
IMAGE_URL="https://example.com/images/v2-banner.png"
CHANNEL="#announcements"
curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "$(python3 -c "
import json
payload = {
'channel': '${CHANNEL}',
'text': '${TITLE}',
'blocks': [
{
'type': 'header',
'text': {'type': 'plain_text', 'text': '${TITLE}', 'emoji': True}
},
{
'type': 'section',
'text': {'type': 'mrkdwn', 'text': '${DESCRIPTION}'}
},
{
'type': 'image',
'image_url': '${IMAGE_URL}',
'alt_text': '${TITLE}'
},
{
'type': 'actions',
'elements': [{
'type': 'button',
'text': {'type': 'plain_text', 'text': 'Learn More'},
'url': '${LINK}',
'style': 'primary',
'action_id': 'learn_more'
}]
}
]
}
print(json.dumps(payload))
")"For complex messages, write the payload to a file first:
# Write the payload
cat > /tmp/slack-message.json << 'PAYLOAD'
{
"channel": "#marketing",
"text": "Fallback text for notifications",
"blocks": [
{
"type": "header",
"text": {
"type": "plain_text",
"text": "Message Title"
}
},
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": "Message body with *bold* and _italic_ formatting."
}
}
]
}
PAYLOAD
# Send it
curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d @/tmp/slack-message.jsonPost a message at a specific future time using chat.scheduleMessage:
# Schedule a message for a specific Unix timestamp
# Use: date -d "2026-02-12 09:00:00" +%s (Linux) or date -j -f "%Y-%m-%d %H:%M:%S" "2026-02-12 09:00:00" +%s (macOS)
SEND_AT=$(date -j -f "%Y-%m-%d %H:%M:%S" "2026-02-12 09:00:00" +%s 2>/dev/null || date -d "2026-02-12 09:00:00" +%s)
curl -s -X POST "https://slack.com/api/chat.scheduleMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d "{
\"channel\": \"#marketing\",
\"post_at\": ${SEND_AT},
\"text\": \"Good morning team! Here is today's marketing agenda.\",
\"blocks\": []
}"List scheduled messages:
curl -s "https://slack.com/api/chat.scheduledMessages.list" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" | \
python3 -c "
import json, sys, datetime
data = json.load(sys.stdin)
for msg in data.get('scheduled_messages', []):
ts = datetime.datetime.fromtimestamp(msg['post_at']).strftime('%Y-%m-%d %H:%M')
print(f\"ID: {msg['id']} | Channel: {msg['channel_id']} | Scheduled: {ts}\")
"Delete a scheduled message:
curl -s -X POST "https://slack.com/api/chat.deleteScheduledMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d '{
"channel": "C0123456789",
"scheduled_message_id": "Q0123456789"
}'Post the same message to multiple channels:
CHANNELS=("#marketing" "#general" "#product")
MESSAGE='{"text":"Big announcement coming tomorrow!","blocks":[{"type":"section","text":{"type":"mrkdwn","text":":mega: *Big announcement coming tomorrow!* Stay tuned."}}]}'
for CHANNEL in "${CHANNELS[@]}"; do
echo "Posting to ${CHANNEL}..."
echo "$MESSAGE" | python3 -c "
import json, sys
msg = json.load(sys.stdin)
msg['channel'] = '${CHANNEL}'
print(json.dumps(msg))
" | curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d @- | python3 -c "
import json, sys
r = json.load(sys.stdin)
if r.get('ok'):
print(f' Sent. ts={r[\"ts\"]}')
else:
print(f' Error: {r.get(\"error\", \"unknown\")}')
"
done| Error | Cause | Fix |
|---|---|---|
invalid_auth | Bad or expired token | Regenerate the bot token in Slack App settings |
channel_not_found | Bot not in channel or wrong channel name | Invite bot with /invite @BotName or use channel ID |
not_in_channel | Bot needs to join the channel first | Invite the bot or use chat:write.public scope |
too_many_attachments | Over 50 blocks | Split the message into multiple posts or thread replies |
msg_too_long | Text exceeds 40,000 characters | Shorten the message or split into parts |
rate_limited | Too many requests | Wait the number of seconds in the Retry-After header |
missing_scope | Token lacks required permission | Add the scope in OAuth & Permissions and reinstall the app |
RESPONSE=$(curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d '{"channel":"#marketing","text":"Test message"}')
python3 -c "
import json, sys
r = json.loads('${RESPONSE}'.replace(\"'\", \"\"))
if r.get('ok'):
print(f'Message sent successfully. ts={r[\"ts\"]} channel={r[\"channel\"]}')
else:
print(f'Error: {r.get(\"error\", \"unknown\")}')
if r.get('response_metadata', {}).get('messages'):
for m in r['response_metadata']['messages']:
print(f' Detail: {m}')
" 2>/dev/null || echo "$RESPONSE"A more robust approach using a temp file:
RESPONSE_FILE=$(mktemp)
curl -s -X POST "https://slack.com/api/chat.postMessage" \
-H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
-H "Content-Type: application/json" \
-d '{"channel":"#marketing","text":"Test message"}' \
-o "$RESPONSE_FILE"
python3 -c "
import json
with open('${RESPONSE_FILE}') as f:
r = json.load(f)
if r.get('ok'):
print(f'Sent. ts={r[\"ts\"]}')
else:
print(f'Error: {r.get(\"error\")}')
"
rm -f "$RESPONSE_FILE"text field alongside blocks — it serves as the fallback for
notifications, accessibility readers, and clients that do not support Block Kit.chat.postMessage (Web API) over webhooks. It returns a
message ts you can use for threading, updating, and deleting.:emoji: codes in plain_text fields with "emoji": true to render emoji in headers
and button labels.& becomes &, < becomes <, > becomes >.fields for the two-column layout rather than trying to
format tables in mrkdwn (Slack does not support tables).© OpenClaudia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/slack-bot of OpenClaudia/openclaudia-skills.
Open the folder on GitHubat commit 28bf209
Slack Bot next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Slack Bot this skillOpenClaudia/openclaudia-skills | 711 | — | ~8.7k | Automated safety check: Notes | MIT | |
| Chat SDKdatabuddy-analytics/Databuddy | 1.2k | — | ~2.6k | Automated safety check: Pass | AGPL-3.0 | |
| Channel Debug Corevercel-labs/vercel-openclaw-archived | 117 | — | ~2k | Automated safety check: Notes | MIT | |
| Frontmcp Channelsagentfront/frontmcp | 146 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Add OAuth Integrationrome-os/rome | 725 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Telegram Development Guide2025Emma/vibe-coding-cn | 23k | 1 repos | ~3.7k | Automated safety check: Pass | MIT |
databuddy-analytics/Databuddy
Build multi-platform chat bots with Chat SDK (chat npm package).
vercel-labs/vercel-openclaw-archived
Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.
agentfront/frontmcp
A skill your agent uses when pushing real-time notifications or events into Claude Code (or another MCP client) sessions, or building two-way chat bridges.
rome-os/rome
Add a new Rome-managed OAuth integration for a third-party service so a user can delegate access by clicking Connect, and Rome can act on the service with the delegated token (the GitHub/Slack model…
2025Emma/vibe-coding-cn
Chinese-language guide to building on Telegram: bots through the Bot API, Mini Apps in JavaScript and custom clients through TDLib, with Python examples.
serejaris/personal-corp-os
A skill your agent uses when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway.
OpenClaudia/openclaudia-skills
Build an interactive competitive-traffic report for any company and its rivals — monthly visits (SimilarWeb), organic search traffic and Domain Rating (Ahrefs) — as one self-contained HTML page with…
OpenClaudia/openclaudia-skills
Score how hard a keyword is to rank for in the AI-search era — page-level URL Rating of real competitors (not just domain DR), Ahrefs keyword difficulty, and whether a given site already ranks or is…
OpenClaudia/openclaudia-skills
Audit EVERY Google Search Console property at once — rank all sites by clicks and impressions with period-over-period deltas, then diff keywords per site to surface what is newly ranking, rising…
OpenClaudia/openclaudia-skills
Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb.
OpenClaudia/openclaudia-skills
Manages Ahrefs API usage in Python using ahrefs-python library.
OpenClaudia/openclaudia-skills
Design, plan, and analyze A/B tests with statistical rigor. An agent skill from OpenClaudia/openclaudia-skills.
Works with
Categories
Send messages and rich content to Slack channels via webhooks or Bot API. Slack Bot is an agent skill from OpenClaudia/openclaudia-skills. Send messages and rich content to Slack channels via webhooks or Bot API.
Slack Bot fits situations like: phrases: post to slack; slack notification; slack announcement; slack marketing.
Run `npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a claude-code`. Or copy the skill folder (skills/slack-bot in OpenClaudia/openclaudia-skills) into .claude/skills/slack-bot in your project. Claude Code loads it when a task matches its description.
Run `npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a codex`. Or copy the skill folder (skills/slack-bot in OpenClaudia/openclaudia-skills) into .agents/skills/slack-bot in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenClaudia/openclaudia-skills --skill slack-bot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slack-bot, .gemini/skills/slack-bot, .github/skills/slack-bot and .opencode/skills/slack-bot in your project.
Going by SKILL.md and its folder, Slack Bot needs the command-line tools its instructions call (curl and python3) and credentials named SLACK_BOT_TOKEN. Our summary lists: Python 3; A credential in SLACK_BOT_TOKEN. Its frontmatter pre-approves these tools: Bash, WebFetch, WebSearch.
SKILL.md names 5 domains. In commands or code: slack.com, hooks.slack.com, twitter.com and linkedin.com; the agent is likely to contact these when it follows the instructions. As links in the text: api.slack.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Slack Bot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 8.7k tokens (SKILL.md is roughly 35k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Slack Bot: Chat SDK (databuddy-analytics/Databuddy, 1.2k stars), Channel Debug Core (vercel-labs/vercel-openclaw-archived, 117 stars), Frontmcp Channels (agentfront/frontmcp, 146 stars) and Add OAuth Integration (rome-os/rome, 725 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
OpenClaudia (a GitHub organization) maintains it in OpenClaudia/openclaudia-skills, which has 711 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on September 18, 2026.
Source: OpenClaudia/openclaudia-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.