Perform Task
telegramdesktop/tdesktop
Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.
Парсинг публичных Telegram-каналов через веб-превью t.me/s/.
MITAuto-check: notes
Install Telegram Channel Parser
$ npx skills add artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install artwist-polyakov/polyakov-claude-skills telegram-channel-parser --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/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .claude/skills/telegram-channel-parser && 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 "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .claude/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parserType 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 artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install artwist-polyakov/polyakov-claude-skills telegram-channel-parser --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .agents/skills/telegram-channel-parser && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .agents/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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 artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install artwist-polyakov/polyakov-claude-skills telegram-channel-parser --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .cursor/skills/telegram-channel-parser && 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 "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .cursor/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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/artwist-polyakov/polyakov-claude-skills.git --path plugins/telegram-channel-parser/skills/telegram-channel-parser--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 artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install artwist-polyakov/polyakov-claude-skills telegram-channel-parser --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .gemini/skills/telegram-channel-parser && 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 "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .gemini/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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 artwist-polyakov/polyakov-claude-skills telegram-channel-parserInstalls 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 artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .github/skills/telegram-channel-parser && 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 "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .github/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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 artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install artwist-polyakov/polyakov-claude-skills telegram-channel-parser --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/artwist-polyakov/polyakov-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/telegram-channel-parser/skills/telegram-channel-parser .opencode/skills/telegram-channel-parser && 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 "telegram-channel-parser" agent skill from https://github.com/artwist-polyakov/polyakov-claude-skills/tree/main/plugins/telegram-channel-parser/skills/telegram-channel-parser into .opencode/skills/telegram-channel-parser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "telegram-channel-parser", 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.
Facts
- Skill name
telegram-channel-parser- GitHub stars
- 206
- Token cost
- ~2k tokens
- SKILL.md length
- 668 words
- Files
- 23 (incl. scripts, assets)
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Парсинг публичных Telegram-каналов через веб-превью t.me/s/.
- Works in 5 steps: Прочитать config/.env (если есть) → Распарсить TG_CATEGORIES — получить… → Для каждой категории: TG_CHANNELS_ =… → …
- SKILL.md covers Перед запуском, Config, Philosophy and Workflow, plus 5 more sections
- Runs Shell scripts from its folder; calls bash; reaches t.me
What it does
Telegram Channel Parser is an agent skill from artwist-polyakov/polyakov-claude-skills. Парсинг публичных Telegram-каналов через веб-превью t.me/s/. Посты, метрики, аналитика, дайджесты, конкурентный анализ. Cache-first подход для гигиены контекстного окна. Triggers: telegram канал, telegram channel, парсинг телеграм, дайджест каналов, telegram digest, анализ канала, шер-парад, telegram analytics, мониторинг каналов.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 25 other files, including scripts and assets (for example `config/README.md`, `scripts/channel_info.sh` and `scripts/common.sh`).
It works with Telegram. The repository describes itself as: Набор скиллов для Claude. The licence is MIT.
Example prompts
- “/telegram-channel-parser”
Requirements
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Прочитать config/.env (если есть)
- Распарсить TG_CATEGORIES — получить список доступных категорий
- Для каждой категории: TG_CHANNELS_ = каналы, TG_CHANNELS__LABEL = название
- Определить нужную категорию
- Передать каналы нужной категории через --channels
What it can do on your machine
Read from SKILL.md and the folder at commit 8bbeead. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 13 files in scripts/ (Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
t.me
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Telegram Channel Parser loads about 2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 668 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:25
.sh` копирует скилл и, если есть `config/.env`, нормализует его через `sed -i`: некавыченные значения с пробелами или ки - NoteMentions a .env fileSKILL.md:31
cp config/.env.example config/.env - NoteMentions a .env fileSKILL.md:34
**Без `.env`:** скилл работает, но каналы нужно передавать явно через `--channel` / `--channels`. - NoteMentions a .env fileSKILL.md:36
**С `.env`:** дайджест AI-каналов готов из коробки. Пользователь может добавить свои категории. - NoteMentions a .env fileSKILL.md:38
**Структура `.env` (категории дайджестов):** - NoteMentions a .env fileSKILL.md:51
1. Прочитать `config/.env` (если есть) - NoteMentions a .env fileSKILL.md:60
**Если `.env` нет** → спросить какие каналы парсить, предложить `cp config/.env.example config/.env`. - NoteMentions a .env fileSKILL.md:62
тет:** `--channels` явно > категория из `.env` > агент спрашивает. - NoteMentions a .env fileSKILL.md:172
| `--channels` | нет | из .env | Несколько каналов через запятую |
Automated 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); the scripts in this folder are not scanned.
SKILL.md
The full file from artwist-polyakov/polyakov-claude-skills at commit 8bbeead, republished under its MIT licence (© artwist-polyakov). 668 words, ~1,953 tokens.
Download SKILL.mdSave it as
.claude/skills/telegram-channel-parser/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.- name
- telegram-channel-parser
- description
- Парсинг публичных Telegram-каналов через веб-превью t.me/s/. Посты, метрики, аналитика, дайджесты, конкурентный анализ. Cache-first подход для гигиены контекстного окна. Triggers: telegram канал, telegram channel, парсинг телеграм, дайджест каналов, telegram digest, анализ канала, шер-парад, telegram analytics, мониторинг каналов.
telegram-channel-parser
Парсинг публичных Telegram-каналов через веб-превью (t.me/s/). Без API-ключей, без MTProto, zero config.
Перед запуском
Перед любым запуском скриптов создай рабочую копию скилла в /home/claude/telegram-channel-parser и работай уже из неё:
bash scripts/prepare_runtime.sh
cd /home/claude/telegram-channel-parserprepare_runtime.sh копирует скилл и, если есть config/.env, нормализует его через sed -i: некавыченные значения с пробелами или кириллицей оборачиваются в кавычки в рабочей копии.
Config
Никаких токенов не требуется. Для дайджестов — скопировать .env.example:
cp config/.env.example config/.envБез .env: скилл работает, но каналы нужно передавать явно через --channel / --channels.
С .env: дайджест AI-каналов готов из коробки. Пользователь может добавить свои категории.
Структура .env (категории дайджестов):
TG_CATEGORIES=ai,crypto # реестр доступных категорий
TG_DEFAULT_CATEGORY=ai # дефолтная при запросе "дайджест"
TG_CHANNELS_AI_LABEL="AI и технологии"
TG_CHANNELS_AI=countwithsasha,evilfreelancer,...
TG_CHANNELS_CRYPTO_LABEL="Криптовалюты"
TG_CHANNELS_CRYPTO=channel1,channel2Алгоритм агента при запросе дайджеста:
- Прочитать
config/.env(если есть) - Распарсить
TG_CATEGORIES— получить список доступных категорий - Для каждой категории:
TG_CHANNELS_<ID>= каналы,TG_CHANNELS_<ID>_LABEL= название - Определить нужную категорию:
- Пользователь назвал тему → сопоставить с
_LABEL - Не уточнил → использовать
TG_DEFAULT_CATEGORY - Несколько категорий подходят → предложить выбор
- Пользователь назвал тему → сопоставить с
- Передать каналы нужной категории через
--channels
Если .env нет → спросить какие каналы парсить, предложить cp config/.env.example config/.env.
Приоритет: --channels явно > категория из .env > агент спрашивает.
Подробности: config/README.md.
Philosophy
- Always fresh — данные запрашиваются в реальном времени при каждом вызове. Никогда не пропустишь свежий пост.
- Context window hygiene — stdout ограничен 30 строками. Полные данные в TSV/CSV. LLM работает с компактным форматом, а не с сырым HTML.
- Rate limit — между запросами к t.me пауза 1.5с. Не жадничаем.
- Чистый POSIX sh — никаких зависимостей кроме curl, sed, awk, grep.
В JSON-дайджесте и сравнении каналов последняя страница используется и для постов, и для сведений о канале, без повторной загрузки. При каждом запуске она загружается заново; страницы истории также запрашиваются заново по мере необходимости.
Workflow
Парсинг одного канала
Получи посты:
bash bash scripts/fetch_posts.sh --channel countwithsasha --limit 50Выведет последние 50 постов в TSV (id, date, views, reactions, fwd_from, fwd_link, text, media_url).
Инфо о канале:
bash bash scripts/channel_info.sh --channel countwithsashaПоиск по постам:
bash bash scripts/search_posts.sh --channel countwithsasha --query "скилл"Топ постов (шер-парад):
bash bash scripts/top_posts.sh --channel countwithsasha --limit 50 --sort reactionsРасписание публикаций:
bash bash scripts/posting_schedule.sh --channel countwithsasha --limit 100Экспорт:
bash bash scripts/export_csv.sh --channel countwithsasha --limit 100 --csv cache/export.csv
Дайджест по нескольким каналам
# Явный список каналов
bash scripts/digest.sh --channels "countwithsasha,evilfreelancer,aostrikov_ai_agents" --period today
# Дефолтный набор (без --channels)
bash scripts/digest.sh --period todayПериоды: today, yesterday, week, N (последние N дней).
Сравнение каналов
bash scripts/compare_channels.sh --channels "channel1,channel2,channel3" --limit 30Таблица: подписчики, средние просмотры, частота публикаций, engagement.
React-артифакт для дайджеста
При запросе дайджеста — отображай результаты как React-артифакт (лента карточек).
Алгоритм (4 шага):
- Запусти
digest_json.sh— он пишет JSON в файл (не stdout!) и возвращает путь:bash bash scripts/digest_json.sh --period today # → prints: cache/digest_today.json - Прочитай JSON-файл по выведенному пути
- Прочитай шаблон
assets/digest-feed.tsx - Замени
__DIGEST_DATA__в шаблоне на содержимое JSON, отрендери как React-артифакт
Важно: скрипт пишет в файл, а не в stdout, чтобы обойти лимит буфера sandbox (~200KB). Для 30-дневного дайджеста 15 каналов JSON может быть 500KB+.
Посты автоматически сортируются по дате (новые сверху), перемешаны между каналами. Пользователь фильтрует по периоду и каналу через UI.
Show full SKILL.md (261 more words)Show less
Scripts
Общий паттерн вызова:
bash scripts/<script>.sh --channel <username> [--limit N] [--before <post_id>] [--csv path]| Script | Description | Special params |
|---|---|---|
fetch_posts.sh | Посты канала → TSV | --limit, --before, --after-date YYYY-MM-DD |
channel_info.sh | Название, описание, подписчики | — |
search_posts.sh | Полнотекстовый поиск | --query "text" |
top_posts.sh | Ранжирование постов | --sort views|reactions, --limit |
posting_schedule.sh | Анализ времени публикаций | --limit |
export_csv.sh | Экспорт в CSV | --csv path |
digest.sh | Дайджест нескольких каналов | --channels "a,b,c", --period today|yesterday|week|N |
digest_json.sh | Дайджест → JSON файл (для React-артифакта) | --channels "a,b,c", --period today|yesterday|week|N |
compare_channels.sh | Сравнительная таблица | --channels "a,b,c", --limit N (положительное целое) |
Общие параметры
| Param | Required | Default | Description |
|---|---|---|---|
--channel | да* | — | Username канала (без @) |
--channels | нет | из .env | Несколько каналов через запятую |
--limit | нет | 20 | Сколько постов загрузить |
--before | нет | — | ID поста для пагинации |
--after-date | нет | — | Не загружать посты старше даты (YYYY-MM-DD) |
--csv | нет | — | Путь для экспорта |
*--channel для одного канала, --channels для мультиканальных команд.
Ввод канала
Скилл принимает канал в любом формате:
countwithsasha— просто username@countwithsasha— с собакойhttps://t.me/countwithsasha— прямая ссылкаhttps://t.me/s/countwithsasha— ссылка на веб-превьюt.me/countwithsasha?before=500— с параметрами
Всё автоматически нормализуется до голого username.
Ограничения
- Только публичные каналы (у которых есть t.me/s/ превью)
- Некоторые посты Telegram не отдаёт через веб-превью. Если вместо текста приходит предложение открыть Telegram, поле текста в TSV/JSON содержит
[Текст недоступен в веб-превью Telegram: https://t.me/<channel>/<id>]. Это пометка скилла, а не текст автора: сообщи о пропуске и дай ссылку, не пересказывай такой пост. Медиа без подписи остаётся с пустым текстом, если Telegram не пометил его как неподдерживаемое. - Счётчик пересылок (shares) недоступен — t.me/s/ его не отдаёт, только MTProto API
- Зато парсится откуда переслан пост (fwd_from + ссылка на оригинал)
- Реакции парсятся суммарно (общее количество по всем эмодзи)
- Пагинация: ~20 постов на страницу, для 100 постов = 5 запросов
- Rate limit: 1.5с между запросами к t.me
© artwist-polyakov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 22 other files (scripts, assets) in plugins/telegram-channel-parser/skills/telegram-channel-parser of artwist-polyakov/polyakov-claude-skills.
- SKILL.md
- .gitignore
- assets/digest-feed.tsx
- config/.env.example
- config/README.md
- scripts/channel_info.sh
- scripts/common.sh
- scripts/compare_channels.sh
- scripts/digest.sh
- scripts/digest_json.sh
- scripts/export_csv.sh
- scripts/fetch_posts.sh
- scripts/parse_tg_posts.awk
- scripts/posting_schedule.sh
- scripts/prepare_runtime.sh
- scripts/sanitize_env.sh
- scripts/search_posts.sh
- scripts/tests
- … and 5 more
Open the folder on GitHubat commit 8bbeead
Compare with similar skills
Telegram Channel Parser 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 |
|---|---|---|---|---|---|---|
| Telegram Channel Parser this skillartwist-polyakov/polyakov-claude-skills | 206 | — | ~2k | Automated safety check: Notes | MIT | |
| Perform Tasktelegramdesktop/tdesktop | 33k | 2 repos | ~3k | Automated safety check: Pass | GPL-3.0 | |
| Custom Mode Creator for claude-memthedotmack/claude-mem | 99k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Dependency Watchtelegramdesktop/tdesktop | 33k | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Continuetelegramdesktop/tdesktop | 33k | 2 repos | ~9.4k | Automated safety check: Pass | GPL-3.0 | |
| Process InboxTDesktop-x64/tdesktop | 3k | 1 repos | ~4.3k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Custom Mode Creator for claude-mem
thedotmack/claude-mem
Walks you through creating, installing and verifying a custom claude-mem mode, including note types, tags and optional Telegram alerts for chosen memories.
Dependency Watch
telegramdesktop/tdesktop
Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks.
Continue
telegramdesktop/tdesktop
Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.
Process Inbox
TDesktop-x64/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
Process Inbox
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
More from artwist-polyakov/polyakov-claude-skills
All 21 skills in this repoAgent Deck Sessions
artwist-polyakov/polyakov-claude-skills
Launches, monitors and collects results from child AI agent sessions with the agent-deck terminal session manager.
Crawl4AI SEO Site Crawler
artwist-polyakov/polyakov-claude-skills
Crawls a site with Crawl4AI to audit titles, meta tags, H1s, canonicals, navigation and internal links, and to compare landing pages and competitor sites.
GitHub Pages Publisher
artwist-polyakov/polyakov-claude-skills
Publishes already-built static pages to a GitHub Pages repo under a year, year-month and slug folder layout, optimizes large images and returns the public URL.
Perplexity Search and Research
artwist-polyakov/polyakov-claude-skills
Shell scripts for web search and research through the Perplexity API: raw results, cited answers, background deep research and page fetching, with results cached on disk.
Sourcecraft Publisher
artwist-polyakov/polyakov-claude-skills
Publish static page artifacts to SourceCraft Sites (Yandex infrastructure, works in Russia), with advisory image optimization and an original-image path.
X/Twitter Research via Grok
artwist-polyakov/polyakov-claude-skills
Searches X/Twitter through the xAI Grok API to build digests, trend reports and thread analysis, meant to surface post ideas for a Telegram channel.
Related
Works with
Questions about Telegram Channel Parser
What does Telegram Channel Parser do?
Парсинг публичных Telegram-каналов через веб-превью t.me/s/. Telegram Channel Parser is an agent skill from artwist-polyakov/polyakov-claude-skills.me/s/.
How do I install Telegram Channel Parser in Claude Code?
Run `npx skills add artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a claude-code`. Or copy the skill folder (plugins/telegram-channel-parser/skills/telegram-channel-parser in artwist-polyakov/polyakov-claude-skills) into .claude/skills/telegram-channel-parser in your project. Claude Code loads it when a task matches its description.
How do I install Telegram Channel Parser in Codex?
Run `npx skills add artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a codex`. Or copy the skill folder (plugins/telegram-channel-parser/skills/telegram-channel-parser in artwist-polyakov/polyakov-claude-skills) into .agents/skills/telegram-channel-parser in your project. Codex loads it when a task matches its description.
Can I use Telegram Channel Parser in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add artwist-polyakov/polyakov-claude-skills --skill telegram-channel-parser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/telegram-channel-parser, .gemini/skills/telegram-channel-parser, .github/skills/telegram-channel-parser and .opencode/skills/telegram-channel-parser in your project.
What does Telegram Channel Parser need to run?
Going by SKILL.md and its folder, Telegram Channel Parser needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: A Bash shell.
Does Telegram Channel Parser access the network?
SKILL.md names 1 domain. In commands or code: t.me; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Telegram Channel Parser safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Telegram Channel Parser use?
Telegram Channel Parser is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Telegram Channel Parser use?
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Telegram Channel Parser?
Skills that share tags, products or a category with Telegram Channel Parser: Perform Task (telegramdesktop/tdesktop, 33k stars), Custom Mode Creator for claude-mem (thedotmack/claude-mem, 99k stars), Dependency Watch (telegramdesktop/tdesktop, 33k stars) and Continue (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Telegram Channel Parser?
artwist-polyakov (a GitHub user) maintains it in artwist-polyakov/polyakov-claude-skills, which has 206 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.
Source: artwist-polyakov/polyakov-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.