telegram-post skill
✓ VerifiedCreate and schedule formatted posts, images, and videos to Telegram channels and groups using a bot via the Publora MCP server.
- GitHub stars
- 68
- Files
- 1
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the telegram-post skill do?
telegram-post creates and schedule formatted posts, images, and videos to Telegram channels and groups using a bot via the Publora MCP server.
Summary generated from the skill's SKILL.md.
About the telegram-post skill
Managing Telegram channels and groups through an AI agent is possible with this skill. It allows developers to create, schedule, and manage posts containing text, images, or videos using a Telegram bot via the Publora MCP server. The tool handles rich markdown formatting, including bold, italic, and blockquotes, specifically tailored to the Telegram markdown flavor.
Users can send immediate messages or schedule them for a future ISO 8601 UTC datetime. The skill provides specific tools like create_post for new content, list_connections to find platform IDs, and update_post to modify drafts or scheduled items. It also includes media management capabilities through get_upload_url and complete_media for more complex workflows.
When using media, users must respect specific Bot API constraints, such as a 1,024 character limit for captions and a 50 MB maximum file size for videos. The skill also supports advanced delivery settings like silent notifications, disabling link previews, and protecting content from being forwarded or saved.
What an agent can do with it
- 1Schedule formatted announcementsSend a scheduled post with bold headlines and hyperlinks to a specific Telegram channel.
- 2Post media with captionsUpload an image or video to a group with a descriptive text caption.
- 3Manage existing contentFix a typo in a scheduled post or delete a draft before it goes live.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the telegram-post skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the telegram-post skill in Plugin
/plugin marketplace add publora/skills /plugin install publora-skills@publora-skills
Install the telegram-post skill in Claude Code
~/.claude/skills/telegram-post/SKILL.md
$ npx degit publora/skills/skills/telegram-post ~/.claude/skills/telegram-postInstall the telegram-post skill in Claude Code (project)
.claude/skills/telegram-post/SKILL.md
$ npx degit publora/skills/skills/telegram-post .claude/skills/telegram-postInstall the telegram-post skill in Codex
~/.agents/skills/telegram-post/SKILL.md
$ npx degit publora/skills/skills/telegram-post ~/.agents/skills/telegram-postInstall the telegram-post skill in Gemini CLI
~/.gemini/skills/telegram-post/SKILL.md
$ npx degit publora/skills/skills/telegram-post ~/.gemini/skills/telegram-postInstall the telegram-post skill in Claude.ai
npx degit publora/skills/skills/telegram-post telegram-post && zip -r telegram-post.zip telegram-post # claude.ai → Customize → Skills → + → Create skill → Upload a skill → telegram-post.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablepublora/skills/skills/telegram-post is public and reachablegithub.com/publora/skills/tree/HEAD/skills/telegram-post ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-10github.com/publora/skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/publora/skills/blob/HEAD/skills/telegram-post/SKI ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/publora/skills/blob/HEAD/skills/telegram-post/SKI ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 229 linesgithub.com/publora/skills/blob/HEAD/skills/telegram-post/SKI ↗Pass
SKILL.md
View on GitHubTelegram Post
Create and schedule posts to Telegram channels and groups using the Publora MCP server. Supports rich markdown formatting, photos, videos, and message delivery options.
Prerequisites
Plans: Works on the free Starter plan. Current limits and pricing: publora.com/pricing.
Getting Started
- Create account at publora.com/register (free)
- Create Telegram bot:
- Message @BotFather on Telegram
- Send
/newbotand follow instructions - Save the bot token
- Add bot to your channel:
- Add the bot as administrator to your channel/group
- Grant
can_post_messagespermission
- Connect in Publora at Dashboard with the bot token and the channel:
- Public channel:
@usernameort.me/username - Private channel: its
-100…chat ID, or thet.me/c/…link of any message in it (Copy Link on the message) - Invite links (
t.me/+…) are rejected: the Bot API cannot identify a channel from them
- Public channel:
- Get an API key at app.publora.com/dashboard/api, only if your agent cannot sign in with OAuth or you will use the REST API fallback below
- Connect your agent to the MCP server at
https://mcp.publora.com/mcp:- Upgrading a manual connection without
/mcp: Claude treatshttps://mcp.publora.comas a different server from the bundled one. Change that existing connection tohttps://mcp.publora.com/mcpin its current scope, preserving its authentication and chosen account; sign in again if requested. Alternatively, verify the bundled connection uses the intended account, then remove only the old manual entry. Do not add a second entry or delete credentials automatically. - Publora tools already available (the
publora-skillsplugin or the Publora connector in Claude): nothing to set up. Claude asks you to sign in to Publora the first time a tool runs. - Agents that support OAuth (Claude Code, Cursor, and the Claude and ChatGPT apps): add the server by URL and sign in, no API key needed. In Claude Code, add it and then run
/mcpto sign in:
- Upgrading a manual connection without
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp
- Agents without OAuth: send the API key as
Authorization: Bearer sk_YOUR_API_KEY:
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp \
--header "Authorization: Bearer sk_YOUR_API_KEY"
Claude Desktop, Cursor, Codex, OpenClaw and the claude.ai connector each need a different config file or flow: see client setup for the exact path and snippet.
REST API Fallback
If the MCP server is unavailable or returns errors, use the REST API directly:
Base URL: https://api.publora.com/api/v1
Authentication: Use x-publora-key header (NOT Authorization: Bearer):
# Get your connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
-H "x-publora-key: sk_your_api_key"
# Create a post
curl -X POST "https://api.publora.com/api/v1/create-post" \
-H "x-publora-key: sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"platforms": ["telegram--1001234567890"],
"content": "*Announcement*\n\nYour message here",
"scheduledTime": "2026-03-25T10:00:00Z"
}'
Platform ID Format: telegram-{chat_id} where {chat_id} is the channel/group numeric ID from /platform-connections. A bot connection's chat ID is negative (-100…), so the ID has a double dash. Copy it verbatim; never rebuild it.
Example IDs: telegram--1001234567890, telegram--1002345678901
📖 Full API documentation: docs.publora.com
Platform Limits (Bot API)
| Feature | Limit |
|---|---|
| Text message | 4,096 characters |
| Media caption | 1,024 characters (critical limit!) |
| Images | 10 MB max, 10 per media group |
| Image formats | JPEG, PNG, GIF, BMP, WebP |
| Video size | 50 MB max (not 4 GB - that's for users!) |
| Video formats | MP4, MOV, AVI, MKV, WebM |
| Rate limit | 30 msg/sec global, 20 msg/min per group |
Critical: Bot API has much lower limits than regular Telegram users. Videos over 50 MB and captions over 1,024 characters will fail.
Markdown Formatting
Telegram uses its own markdown flavor with single asterisks for bold:
| Syntax | Result |
|---|---|
*bold* |
bold |
_italic_ |
italic |
`code` |
inline code |
code |
Code block |
[text](url) |
hyperlink |
> text |
Blockquote |
Note: This differs from standard Markdown where **double asterisks** make bold.
Available Tools
create_post
Create a new Telegram post.
Parameters:
platforms: Array with your Telegram connection ID (e.g.,["telegram--1001234567890"])content: Message text (supports markdown)scheduledTime: ISO 8601 UTC datetime. Optional: omit it and the post is created as a draft. Send a future time to schedule. A time five or more minutes in the past is rejected withSCHEDULED_TIME_IN_PAST, so for immediate posting use the current time plus a minute.mediaUrls: up to 10 public https image or video URLs. Publora downloads them server-side and attaches them before validation, so media and scheduling happen in one call. This is the one-shot alternative to the draft thenget_upload_urlthencomplete_mediaflow. Ingestion is rate-limited to 60 URLs per hour.
get_upload_url
Get presigned URL for media uploads.
complete_media
Finalize a file uploaded through get_upload_url, after the presigned PUT succeeds. Optional, because scheduling also finalizes pending media, but calling it early surfaces format and probe errors before publish. Not needed for media attached with mediaUrls.
Parameters:
mediaId: the id returned byget_upload_url
list_connections
List your connected accounts with their platform IDs. Call this first and copy the IDs verbatim; they are never guessable. A private channel has no public username: its username is null, so match it by displayName (the channel title).
list_posts / get_post / update_post / delete_post
Manage scheduled and draft posts. update_post also patches content and platforms on a draft or scheduled post, so fixing a typo or retargeting no longer means delete and recreate. delete_media and prune_media_reference clean up uploaded files.
Post Options (via REST API)
Telegram-specific options available via REST API platformSettings.telegram:
| Option | Description |
|---|---|
disableNotification |
Send silently (no sound) |
disableWebPagePreview |
No link preview cards |
protectContent |
Prevent forwarding/saving |
Caption-above-media is not settable: showCaptionAboveMedia is not an accepted key and sending it returns 400 PLATFORM_SETTING_UNKNOWN.
Note: platformSettings is accepted by the MCP create_post and update_post tools as well as over REST. The schema is strict: a mistyped platform or key is rejected with a validation error rather than silently dropped.
Examples
Simple Channel Post
Post this to my Telegram channel:
"*Product Update v2.5*
We have shipped the following improvements:
- _Faster API response times_ (avg 45ms)
- New `batch` endpoint for bulk operations
[Read the changelog](https://example.com/changelog)"
Formatted Announcement
Create a Telegram post with this formatting:
"*Important Update*
We're launching our new feature tomorrow at 10 AM UTC.
_What's new:_
- Feature A improvements
- Feature B release
[Read the full announcement](https://example.com/update)"
Post with Image
Post this image to my Telegram channel with caption:
"*New Dashboard Preview*
Here's a sneak peek at our redesigned analytics dashboard."
Important: Caption must be under 1,024 characters when posting with media.
Scheduled Post
Schedule this for tomorrow at 8 AM Moscow time:
"*Good morning!* Here's your daily market summary..."
Important Restrictions
-
Caption limit is 1,024 chars: When posting with media (images/videos), text is sent as a caption limited to 1,024 characters. Text-only messages allow 4,096 characters.
-
Video max 50 MB: Bot API limits videos to 50 MB (not 4 GB like regular users). Large videos will fail.
-
Bot must be admin: Your bot needs administrator role with
can_post_messagespermission. This is verified at connection time and re-checked byPOST /test-connection/{platformId}, not before each post. -
No mixed media: A single post cannot contain both images and videos.
-
Caption overflow: If caption exceeds 1,024 chars on a media post, it's sent as a separate reply message instead of being truncated.
Best Practices
Content
- Use formatting: Bold headlines, italic emphasis improves readability
- Link previews: Great for articles; disable for cleaner announcements
- Emoji usage: Common and expected on Telegram
- Post length: No penalty for longer posts on text-only messages
Timing
- Global audience: Telegram users are worldwide; consider timezone posts
- Best times: 8-10 AM, 12-2 PM, 7-9 PM in target regions
- Frequency: Channels can post more frequently (5-10/day)
Engagement
- Enable comments in channel settings for discussions
- Use polls for engagement
- Pin important announcements
Troubleshooting
| Error | Cause | Solution |
|---|---|---|
| "Bot not admin" | Bot missing admin permissions | Add bot as admin with can_post_messages |
| "Channel not found" | Wrong channel name/ID, or the bot is not in the channel | Verify @channelname or the -100… chat ID, and add the bot as an administrator |
| "Invite links cannot identify a channel for a bot" | A t.me/+… invite link was entered |
Use the channel's -100… chat ID or a t.me/c/… message link |
MEDIA_CAPTION_TOO_LONG |
Caption > 1,024 chars | Shorten caption or use text-only post |
| "Bad Request: file is too big" | File > 50 MB | Compress video/image to under 50 MB |
| "Mixed media not supported" | Images + video in same post | Use one media type per post |
Files in this skill
1telegram-post skill questions
How do I install the telegram-post skill in Claude Code?
Run npx degit publora/skills/skills/telegram-post ~/.claude/skills/telegram-post. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the telegram-post skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What are the limits for media captions and videos?
Media captions are limited to 1,024 characters and videos must be under 50 MB.
Can I post both images and videos in a single post?
No, a single post cannot contain a mix of both images and videos.
What should I do if my bot cannot identify a channel via an invite link?
Invite links (t.me/+...) are rejected; you must use the channel's numeric chat ID or a message link.