← Back to Skills Marketplace
228
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install telegram-openapi-skill
Description
Operate Telegram Bot API through UXC with a curated OpenAPI schema, bot-token path auth, polling-based reads, and webhook management guardrails.
Usage Guidance
This skill looks like a genuine Telegram Bot API wrapper for uxc, but note two practical issues before installing: (1) you must provide a Telegram bot token (TELEGRAM_BOT_TOKEN) via your environment/uxc credential binding—registry metadata didn't declare that, so configure it manually; (2) the docs contradict each other about local multipart uploads—if you intend to use file uploads, assume the skill can read user-specified local files when you call sendPhoto/sendDocument, so avoid passing paths to sensitive files. Also ensure you trust the uxc tool and the raw.githubusercontent.com schema URL before creating links or bindings.
Capability Analysis
Type: OpenClaw Skill
Name: telegram-openapi-skill
Version: 1.0.1
The telegram-openapi-skill bundle provides a legitimate interface for interacting with the Telegram Bot API using the uxc tool. It includes a curated OpenAPI schema (references/telegram-bot.openapi.json), clear authentication setup instructions using environment variables, and explicit security guardrails in SKILL.md that require user confirmation for high-risk write operations. The validation script (scripts/validate.sh) and usage patterns are consistent with the stated purpose of bot management and message delivery.
Capability Assessment
Purpose & Capability
The skill's name/description match its behavior: it wraps Telegram Bot API calls via uxc and a curated OpenAPI schema. Requested capabilities (polling, webhook management, sendMessage/sendPhoto/sendDocument) are consistent with a Telegram bot integration. However, the registry metadata lists no required environment variables or primary credential even though the SKILL.md clearly instructs using a TELEGRAM_BOT_TOKEN credential—this metadata omission is an inconsistency.
Instruction Scope
SKILL.md confines runtime actions to calling api.telegram.org via uxc and local multipart uploads when explicitly requested. It does not instruct reading unrelated system secrets or exfiltrating data to third-party endpoints. Two documentation contradictions are present: one line states some media endpoints 'accept file_id or HTTP URL only; they do not upload new local files', and a nearby line states sendPhoto/sendDocument 'also support multipart/form-data local file uploads'. That is a documentation coherence issue that should be clarified because supporting local file uploads means the skill can access user-specified local files.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or written to disk by default. The only code file is a validation script; it is harmless and intended to run developer-side. The SKILL.md expects uxc on PATH but does not install any binaries itself.
Credentials
The runtime instructions require a single bot credential (TELEGRAM_BOT_TOKEN) configured via uxc auth binding, which is proportionate to the stated purpose. The registry metadata, however, declares no required env vars or primary credential—this mismatch should be corrected so installers know a secret is required. Aside from the bot token, the skill does not request unrelated credentials.
Persistence & Privilege
The skill is not marked always:true and does not request elevated/persistent platform privileges. It does not modify other skills or system-wide settings. Autonomous invocation remains possible (platform default) but is not combined with other concerning flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install telegram-openapi-skill - After installation, invoke the skill by name or use
/telegram-openapi-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Add support for `multipart/form-data` local file upload to `sendPhoto` and `sendDocument` (via local path strings).
- Update guardrails: clarify that `sendMediaGroup` is still JSON-only and does not use multipart file arrays.
- Expand documentation for multipart usage, including local photo/document file upload examples.
- `setWebhook` now supports multipart certificate uploads for self-signed certificates through the `certificate` file field.
- Update OpenAPI schema and usage references to reflect multipart and related behavior.
- Improve prerequisites, scope, and operation documentation for clarity.
v1.0.0
telegram-openapi-skill 1.0.0
- Initial release with OpenAPI-based Telegram Bot API operations via UXC integration.
- Supports core operations: bot identity, chat lookup, message and media sends (by file_id/URL), polling (getUpdates), and webhook configuration.
- Uses bot-token path authentication with credential binding and path-prefix templating.
- Webhook and polling management include built-in guardrails to prevent conflicts and guide correct usage.
- Explicitly excludes multipart file uploads, self-signed webhook certs, generic webhook ingestion, and unsupported Telegram API features.
- Provides detailed setup, validation, and runtime guidance for reliable bot workflows.
Metadata
Frequently Asked Questions
What is Telegram OpenAPI Skill?
Operate Telegram Bot API through UXC with a curated OpenAPI schema, bot-token path auth, polling-based reads, and webhook management guardrails. It is an AI Agent Skill for Claude Code / OpenClaw, with 228 downloads so far.
How do I install Telegram OpenAPI Skill?
Run "/install telegram-openapi-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Telegram OpenAPI Skill free?
Yes, Telegram OpenAPI Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Telegram OpenAPI Skill support?
Telegram OpenAPI Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Telegram OpenAPI Skill?
It is built and maintained by jolestar (@jolestar); the current version is v1.0.1.
More Skills