telegrab-fetch
Automated, reliable download of single videos from Telegram posts.
Install
mkdir -p .claude/skills/telegrab-fetch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13122" && unzip -o skill.zip -d .claude/skills/telegrab-fetch && rm skill.zipInstalls to .claude/skills/telegrab-fetch
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when the user needs to download one Telegram video from a post link through this repository's telegrab CLI with deterministic preflight checks and machine-readable result fields.Key capabilities
- →Download a single video from a Telegram post link
- →Perform preflight checks for credentials and authorization
- →Run CLI commands via bash script to ensure venv and PYTHONPATH
- →Return local file path and fetch metadata on success
- →Report specific error codes and messages on failure
How it works
The skill executes doctor, status, and fetch commands in JSON mode, performing preflight checks for credentials and authorization before attempting to download the video.
Inputs & outputs
When to use telegrab-fetch
- →Downloading specific videos from Telegram
- →Automating media extraction
About this skill
Telegrab Fetch
Use this skill for one practical task: download a single video from one Telegram post link and return the local file path plus fetch metadata.
When to use
- The user provides (or wants to provide) one
t.meortelegram.mepost link. - The user expects the agent to run the local
telegrabutility in this repository. - The user needs a predictable result that can be reused by another step.
Inputs
- Required:
telegram_link
- Optional:
output_dir(default./downloads)name_template(pass through to--name-template)overwrite(boolean, defaultfalse)
If the link is missing, ask only for the link. Do not ask extra questions when defaults are acceptable.
Required workflow
Always execute in this order, using JSON mode:
doctor --output jsonstatus --output jsonfetch <link> --output json(plus optional flags)
Run CLI commands via bash scripts/run_telegrab.sh to ensure the repository venv and PYTHONPATH=src are used.
Decision rules
- If
doctorreports missing credentials (credentials_present=false), stop and explain:- where config is expected (
config_pathfrom doctor), - that credentials must be set (
TELEGRAB_API_ID,TELEGRAB_API_HASH, or config file).
- where config is expected (
- If
statusreportsauthorized=false, stop and instruct the user to runtelegrab loginmanually. - Do not try to automate interactive login prompts.
- If preflight passes, run the real
fetchdirectly (no mandatory dry-run step).
Output contract
On success, return:
file_pathsource_urlmessage_idchat_idexit_code
On failure, return:
exit_codeerror_codeerror_message
Preserve telegrab semantics. Do not reinterpret or remap exit codes; treat CLI JSON as source of truth.
Error handling
For known failures, keep the message short and actionable:
2: invalid link/input3: credentials or authorization missing4: channel/message inaccessible5: message has no video6: content restriction7: Telegram/runtime error
When reporting an error, include original error_message from CLI output.
When not to use it
- →When the user needs to download multiple videos
- →When the user does not provide a t.me or telegram.me post link
- →When the user expects the agent to automate interactive login prompts
Limitations
- →The skill downloads only a single video from one Telegram post link
- →The skill does not automate interactive login prompts
- →The skill relies on the local telegrab utility in this repository
How it compares
This skill provides a deterministic and machine-readable way to download a single Telegram video with explicit preflight checks, unlike a manual download or a less structured script.
Compared to similar skills
telegrab-fetch side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| telegrab-fetch (this skill) | 0 | 4mo | Review | Beginner |
| youtube-downloader | 0 | 5mo | Review | Beginner |
| crawl4ai | 21 | 8mo | Review | Intermediate |
| firecrawl-scrape | 5 | 7mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
youtube-downloader
syavaYki
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
crawl4ai
basher83
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.
firecrawl-scrape
parcadei
Scrape web pages and extract content via Firecrawl MCP
douyin-scraper-skill
orange-suli
douyin-scraper-skill — an agent skill by orange-suli.
web-scraper
KevanPatira
Web scraping inteligente multi-estrategia. Extrai dados estruturados de paginas web (tabelas, listas, precos). Paginacao, monitoramento e export CSV/JSON.
wechat-batch-crawl
JourneytoNewland
| Intent | Supported Phrases | |--------|-------------------| | 爬取今天 | "爬取今天的微信文章" / "获取今天的文章" / "抓今天的公众号" | | 爬取昨天 | "爬取昨天的微信文章" / "获取昨天的文章" | | 爬取指定日期 | "爬取1月20号的文章" / "获取上周一的文章" | | 仅列出 | "今天有哪些文章" / "列出今天的文章" / "看看有啥新文章" | | 增量爬取 | "继续爬取" / "爬取新增的文章" |