Foundation skill for global personal brand cluster. Creates `.agents/personal-brand-context-global.md` with region-specific personal brand context plus visual identity and visual asset inventory (style refs, face refs, logo, palette, background). 4 region variants (US/EU/SEA/LATAM); each covers founder/coach/creator inside. Reads BEFORE other PB skills (23-28 global). Trigger: 'global personal brand', 'international personal brand', 'US founder brand', 'EU coach brand', 'creator economy global', 'personal brand reference image', 'personal visual identity'.
npx skills add https://github.com/minhnv0807/ai-business-skills --skill 22-personal-brand-context-global
> Foundation skill for the GLOBAL personal brand cluster — runs BEFORE every other global PB skill (23-28). Creates .agents/personal-brand-context-global.md with personal positioning, niche, story arc, content pillars, audience, voice, monetization tuned to a specific region.
>
> Parallel to product-marketing-context-global: That one serves PRODUCTS; this one serves PEOPLE — founders, coaches, creators going international.
| Audience | Concrete example |
|----------|------------------|
| Founder / CEO going global | Building thought leadership outside home market |
| Coach / Consultant selling internationally | English-speaking course buyers, global cohorts |
| Creator / KOL with global audience | Targeting US/EU viewers, brand deals in USD/EUR |
| Agency onboarding international personal brand client | Need region-tagged context once, reuse everywhere |
22-personal-brand-context (VN foundation) insteadproduct-marketing-context-global05-ad-copy-global or 04-script-video-global directlyThis skill produces ONE region-tagged file (.agents/personal-brand-context-global.md) with 13+ sections describing WHO YOU ARE in marketing terms, including which images/assets are style refs, face refs, logos, palettes, and backgrounds. Pick 1 of 4 region variants (US/EU/SEA/LATAM) — the variant tunes currency, primary platforms, regulations, cultural defaults, and gives examples for ALL THREE audience types (founder/coach/creator) inside ONE file. Every other PB skill (23-28) reads this file before working — like a medical chart every doctor reads first.
Without this file, every PB skill has to re-ask: Who are you? What region? What audience? What voice? What story? Repetitive, slow, inconsistent across skills.
With .agents/personal-brand-context-global.md:
Step 1: Check existing file
|-- exists -> ask which section to update
|-- missing -> Step 2
Step 2: Choose region variant (US / EU / SEA / LATAM)
Step 3: Declare primary role (Founder / Coach / Creator)
Step 4: Collect info per variant (13+ sections, role-specific defaults)
Step 5: Create file `.agents/personal-brand-context-global.md`
Check whether .agents/personal-brand-context-global.md already exists.
Ask the user one question: "Which region is your PRIMARY audience: US, EU, SEA, or LATAM?"
Where does your PRIMARY audience live?
|-- North America (USA, Canada)
| --> 01-us.md (USD, FTC, LinkedIn/X/TikTok/YouTube)
|-- European Union (UK, DE, FR, ES, IT, NL, etc.)
| --> 02-eu.md (EUR, GDPR + EU AI Act, LinkedIn/Substack/Instagram)
|-- Southeast Asia EXCEPT Vietnam (SG, MY, ID, TH, PH)
| --> 03-sea.md (USD/local, PDPA, LinkedIn/TikTok/LINE)
|-- Latin America (BR, MX, AR, CO, CL)
| --> 04-latam.md (USD/local, LGPD, WhatsApp/Instagram/TikTok)
|-- Vietnam only
| --> Use `22-personal-brand-context` (VN foundation)
|-- Multi-region
--> Pick LARGEST audience as primary; note secondary in section 12
Inside the chosen region variant, ask: "Are you primarily a Founder/CEO, a Coach/Consultant, or a Creator/KOL?"
| Role | Best for | Distinguishing trait |
|------|----------|---------------------|
| Founder | CEO, Co-founder, Startup/SME owner | Personal brand serves the COMPANY (B2B leads, deal flow, talent) |
| Coach | Consultant, Mentor, Trainer, Course creator | Personal brand IS the product (revenue from courses, coaching, programs) |
| Creator | YouTuber, TikToker, KOL, Podcaster, Streamer | Audience-first; revenue from brand deals + own products |
Multi-role (e.g. founder who also creates content) -> pick MAIN role; note secondary in section 1 (Profile).
After choosing region + role, read the matching variant file in variants/ and walk through each section:
Notes:
Variant summary:
variants/01-us.md — USD, FTC, LinkedIn/X (founder), LinkedIn/YouTube (coach), TikTok/IG/YouTube (creator). Examples: Naval, Hormozi, MrBeast.variants/02-eu.md — EUR, GDPR + EU AI Act, LinkedIn/Xing (DACH), Substack newsletter culture. Examples: Daniel Ek, Felicia Hogendorf, Khaby Lame.variants/03-sea.md — USD/SGD/MYR/IDR/THB/PHP, PDPA, LinkedIn for B2B, TikTok-heavy creators, LINE in Thailand. Examples: Anthony Tan, Vannia Wirawan, Mae Fah Luang.variants/04-latam.md — USD/BRL/MXN/ARS/COP, LGPD, WhatsApp Business critical for coaches, Instagram + TikTok for creators. Examples: David Velez, Alex Cavoukian, Luisa Fernanda W.Save to .agents/personal-brand-context-global.md (create the .agents/ folder if missing).
# Personal Brand Context (Global) — [Full name]
> Region variant: [US / EU / SEA / LATAM]
> Primary role: [Founder / Coach / Creator]
> Primary currency: [USD / EUR / SGD / BRL / etc.]
> Last updated: [YYYY-MM-DD]
> Compatible with: Claude Code, ChatGPT, Gemini, any AI agent
---
[13+ sections following the chosen variant + role, including Visual Asset Inventory]
In every global PB skill (23-personal-brand-strategy-global, 24-ai-avatar-production-global, 25-28-*), add this block under "Collect info":
## Collect info
### Step 0: Check personal brand context
Check whether `.agents/personal-brand-context-global.md` exists:
- **Yes** -> Read everything; pull region / role / niche / audience / voice / story. Do NOT re-ask.
- Also pull visual identity + visual asset inventory for design/avatar prompts. Do NOT re-ask image roles if the file already labels them.
- **No** -> Suggest user run `22-personal-brand-context-global` first.
If user wants to continue anyway, ask 2-3 minimum questions about identity + region.
Skills that will read this file:
23-personal-brand-strategy-global — Personal brand strategy24-ai-avatar-production-global — AI avatar production (needs voice + visual identity)25-* through 28-* — All other global PB skillsBefore finishing:
.agents/personal-brand-context-global.mdproduct-marketing-context-global — Global product foundation (parallel to this skill)22-personal-brand-context — Vietnam personal brand foundation (parallel)23-personal-brand-strategy-global — Reads this file first24-ai-avatar-production-global — Needs brand voice + visual identity from this file*Global PB Foundation Skill | Over Powers Agency | v1.1.0*
agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括:生成(文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx)、编辑修改(把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头)、风格转换(风格迁移、转绘、换风格)、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断:只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改,无论措辞如何(如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"),都必须触发此技能。
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts
This skill is a practical, 'use-it-while-debugging' reference for getting a LiveKit + Letta voice agent working reliably.
Download screenshot baselines from the latest CI run and commit them. Use when asked to update, accept, or refresh component screenshot baselines from CI, or after the screenshot-test GitHub Action reports differences. This skill should be run as a subagent.
| Turn vague taste, screenshots, URLs, product notes, or "make it feel like this" references into a grounded DESIGN.md plus an implementation handoff. Use it before prototypes, decks, redesigns, or image remix work when the user needs a reusable visual direction rather than a one-off prompt.
>- Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.
This skill helps users automatically extract channel-level and video detail data from a specific YouTube channel via BrowserAct API. Agent should proactively apply this skill when users express needs like extracting channel video data, getting latest or popular videos from a YouTube channel, tracking competitor channel content, extracting video metrics such as views likes comments, retrieving subscriber count and channel info, monitoring posting cadence of a YouTube channel, gathering video data for content strategy analysis, getting earliest videos of a YouTube creator, analyzing engagement signals across a full channel, and downloading structured YouTube video details without manual scraping.
Take minhnv0807/22-personal-brand-context-global from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.