Версия 2.0, подробнее на Хабре: https://habr.com/ru/articles/1022618/
🔥3⚡2

Channel
@skarodev
On this record: Topic · Growth · Engagement · Reactions · Stars · Posts · Cite this entry
29subscribers
+1 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1003820830185 |
|---|---|
| Type | Channel |
| Username | @skarodev |
| Created | 1 March 2026 — measured — dated from the channel’s first post |
| First recorded | 11 August 2026 |
| Last confirmed live | 6 October 2026 |
| Measurements held | 5 |
| Confirmed unchanged | 2 times, most recently 6 October 2026 |
| On Telegram | t.me/skarodev |
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 30 September 2026 and assigned it the closest of 31 fixed categories, at 98% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and why it has no browse page of its own yet.
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 25 Sept 2026, 07:18 | 29 | +1 |
| 13 Sept 2026, 10:39 | 28 | -1 |
| 22 Aug 2026, 13:56 | 29 | +1 |
| 11 Aug 2026, 06:31 | 28 | no change |
| 7 Aug 2026, 23:32 | 28 | first reading |
13 posts held, back to 1 March 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 13 posts for this entry, the most recent from 13 April 2026. An engagement rate over an empty window would be a number about nothing.
31 reactions across 7 posts, in 6 distinct kinds. The most used accounts for 38.7% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 12 | 38.7% | |
| 🔥 | 11 | 35.5% | |
| ⚡ | 3 | 9.68% | |
| ❤🔥 | 3 | 9.68% | |
| 🎉 | 1 | 3.23% | |
| 😎 | 1 | 3.23% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 10 of the 13 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 31 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 13 most recent posts we hold, published 1 March 2026 to 13 April 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @skarodev. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.
Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.
This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.
Counted over the 13 most recent posts we hold for this entry, published 1 March 2026 to 13 April 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.
Версия 2.0, подробнее на Хабре: https://habr.com/ru/articles/1022618/
🔥3⚡2
✨Фичи (Features) Новый раздел для планирования и отслеживания фич после завершения основного пайплайна проекта. Фича — первоклассная сущность со своим lifecycle: черновик → запланирована → в работе → завершена. Каждая фича имеет собственный чат с LLM, план и привязанные задачи/ADR. Пользователь создаёт фичу, описывает её в чате — LLM задаёт уточняющие вопросы, затем генерирует структурированное предложение: название,…
🔥2❤🔥1😎1
https://www.youtube.com/watch?v=lykzhNGKZnM&t=15s
🔥2
⚡️Custom Prompts — переопределение промптов фаз Теперь вы можете заменить встроенный промпт любой фазы Skaro своей версией. Достаточно создать файл в .skaro/prompts/ с тем же именем — Skaro подхватит его автоматически при следующем запуске фазы. Зачем это нужно. Встроенные промпты покрывают большинство сценариев, но иногда нужен полный контроль: изменить формат вывода, добавить доменные инструкции или перестроить ло…
👍3⚡1❤🔥1
🤩 Добавлена поддержка Skills Skaro теперь умеет обучать LLM паттернам вашего стека. Skills — это YAML-файлы с дополнительными инструкциями, которые Skaro инжектирует в промпт LLM при выполнении фаз. Конституция определяет что использует проект, а skills — как LLM должен писать код для этого стека. Что внутри 28 встроенных skills покрывают все 12 пресетов конституции: React, Vue, SvelteKit, Next.js, Angular, FastAPI,…
👍2🔥2❤🔥1
Добавлены провайдеры: OpenRouter, DeepSeek, Qwen, Z.ai, Google Полный список моделей поддерживаемых из коробки: Arcee Blitz Claude Haiku 4.5 Claude Opus 4.6 Claude Sonnet 4.5 Claude Sonnet 4.6 CodeLlama 34B Command R+ DeepSeek R1 DeepSeek R1 70B DeepSeek R1 8B DeepSeek V3 (free) DeepSeek V3.2 DeepSeek V3.2 (Chat) DeepSeek V3.2 (Reasoner) Devstral 2 Gemini 2.5 Flash Gemini 2.5 Flash Lite Gemini 2.5 Pro Gemini 3 Flash…
👍4🔥2🎉1
Posted without readable text
Release 1.3.0 Smart Context & Prompt Caching Added: AST-based project index: New context module extracts class, function, method, and type signatures from all project source files using tree-sitter. Supports Python, JavaScript, TypeScript, Go, Rust, Java, Ruby, HTML, CSS, Vue, and Svelte. Gives the LLM full visibility into the project's API surface at ~5-10% of the token cost of sending complete source files. Releva…
Release 1.2.0: 🚀 Autopilot mode for task execution has been added. With a single click, the LLM can handle the task autonomously: it answers clarifying questions, creates an execution plan, implements the steps, stages newly created files in git, and runs tests (skipping those that are not implemented). You can return to any stage later. Put it on autopilot and go grab a coffee :) Also in this release: - Improve…
👍3
Add manual LLM settings docs: https://docs.skaro.dev/settings/llm-and-roles
Channel photo updated
Start MVP https://habr.com/ru/articles/1007048/
Showing the 12 most recent of 13 posts we hold for @skarodev. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 25 September 2026 — this entry's latest reading, not the date you are reading this.
“Skaro” (@skarodev), 29 subscribers as measured 25 September 2026. Telegram Register, tgregister.com/channel/skarodev.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.