skills/ai-bear-newsletter/SKILL.md
Use when creating AI-Bear newsletter articles for LinkedIn/Substack - triggered by requests to write, draft, or execute an article from Notion drafts, or when the user references the framework and workflow.
npx skillsauth add ai-mindset-org/pos-sprint ai-bear-newsletterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transforms raw Notion drafts into publication-ready LinkedIn/Substack articles following the AI-Bear Single-Article Newsletter Framework. One issue = one article. No invention, no expansion beyond the source.
Fetch the draft page by publishing date from the Drafts database.
fdf75999-5031-487b-877c-196d21e7061bSearch the web for each topic. Gather:
Write immediately — no review step in chat. Follow the framework below exactly.
Step 4a: Create new page in Scheduled database
248aa851-3792-43a6-a065-06ebb14ec81aMeeting name = article headline, Platform = ["LinkedIn/Substack"], Date for publishing = same date as draftStep 4b: Add full article content to the new page (body + Midjourney prompts + reference images)
Step 4c: Leave original draft untouched in Drafts database
Reply: "Done! Article ready in Scheduled at [URL]. Ready for your review."
[Date]. Inside this issue:
- 3-4 sharp bullets
- Each previews a core development
- No emojis, no fluff, no vague phrasing
Section emojis are permanent — never change them.
Factual core. Stay close to the source. Tighten language. No opinions, no invented data, no speculation unless clearly labelled. Every key claim links to its primary source inline. Link text = entity or document name, not "click here". Link to exact primary sources — never homepages. All abbreviations explained on first use. Short, direct sentences.
Practical interpretation. Answers: what does this mean? Focused on founders, operators, marketers. Analytical, calm, sharp. No philosophy, no grand predictions, no political/religious/sexual framing.
Exposure and risk mapping. Must cover: who is exposed, who benefits, what changes operationally, what action to consider. No fear tactics, no drama.
Two Midjourney prompts per article. Never change the baseline style:
#00e0c6 · Violet #6c63ff · Navy #0a1e3f--v 6, --q 2, no text, no logosVariant 1 — Mascot focus: Close-up AI-Bear + one key symbolic prop Variant 2 — Environment focus: AI-Bear in contextual scene + 2-3 minimal icons
Prompt template:
/imagine editorial-style flat vector illustration of the ai bear mascot, [scene context], [2-3 visual props], simple composition, white background, brand colors teal #00e0c6, violet #6c63ff, navy #0a1e3f --no text --ar 16:9 --v 6 --q 2
2-3 images per article. Official or open-access sources only (company blogs, research pages, arXiv, GitHub, product pages). Each image followed by a source attribution line.

Source: [Source name](source URL)
| Rule | Detail |
|------|--------|
| Punctuation | No em dashes — use - with spaces. Straight quotes only |
| Capitalisation | Sentence case everywhere. Only proper nouns capitalised |
| Emojis | Required in headline. Fixed in section headers only. Not in body text |
| Tone | Practical over clever. No sarcasm, no political/religious/sexual content |
| Language | British English throughout |
| Length | ~1,200 characters for article body (excluding prompts and images) |
| Database | ID | Purpose |
|----------|----|---------|
| Drafts | fdf75999-5031-487b-877c-196d21e7061b | Raw inputs — read only |
| Scheduled | 248aa851-3792-43a6-a065-06ebb14ec81a | Publication-ready output |
| Posted | b6c9ff9d-62c9-45f5-b62e-c725dff94fd5 | Archive (user moves manually after posting) |
| Ai-Bear articles | legacy | Do not use |
testing
# YT Transcribe — YouTube → Whisper → Obsidian Транскрибирует YouTube-видео через mlx-whisper (Apple Silicon, Metal-native) с параллельными чанками. Fallback на openai-whisper если mlx недоступен. ## Какую боль закрывает - **Потерянный контент видео**: Посмотрел лекцию/подкаст — через неделю забыл 90%. Нет текстовой базы для поиска. - **Нет транскриптов для русского**: YouTube auto-captions для русского языка — мусор. Whisper даёт quality транскрипцию. - **Ручная обработка**: Переслушивать 2-
development
Интерактивный процесс написания текстов для вайб-маркетинга на основе Julian Shapiro framework. **Новые возможности (v2.0):** - Research & Gap Analysis (Perplexity → WebSearch fallback) - Scoring 0-5 вместо binary (Novelty + Resonance + Hook + Clarity) - AI-Slop Detection на всех этапах (10 типов patterns) - 3 варианта intro с self-scoring - Markdown export всех промежуточных результатов **Русские triggers:** "напиши пост по шапиро", "написать статью по фреймворку шапиро", "создай текст в стиле julian shapiro", "помоги написать контент по методу shapiro", "контент по julian shapiro фреймворку", "пост по julian shapiro", "напиши в стиле шапиро" **English triggers:** "write content using julian shapiro framework", "create post with shapiro method", "write article shapiro style", "help with julian shapiro writing" **Generic triggers:** "напиши статью", "помоги написать контент", "создай текст", "начать писать", "хочу написать пост", "нужна помощь с текстом", "write content", "write article", "создай контент", "придумай идею для статьи", or requests help with content creation process.
tools
# /tg-saved v2 — Telegram Saved Messages → Deep Analysis → Obsidian ## Назначение Скилл извлекает сообщения из Telegram "Избранное" (Saved Messages) за последние N дней, автоматически парсит контент всех ссылок в сообщениях (requests + BeautifulSoup, до 5000 символов на URL), затем для каждого сообщения запускает глубокий анализ через Claude CLI subprocess (модель Sonnet). Результат — подробная структурированная заметка в Obsidian `00-inbox/` с YAML frontmatter, секциями анализа, ссылками и ор
documentation
Делает LLM-выжимку из комментариев менеджеров об одном или нескольких подрядчиках. Используй этот скилл когда нужно понять что говорят менеджеры о конкретном подрядчике, или получить JSON с выжимкой для дальнейшей обработки.