Khi nguoi dung muon tao hoac cap nhat tai lieu goc ve personal brand — dinh vi ca nhan, niche, story arc, content pillars, audience ca nhan, brand voice, visual identity, visual asset inventory (anh style ref, face ref, logo, palette), monetization muc tieu. Cung dung khi nguoi dung nhac 'personal brand', 'thuong hieu ca nhan', 'ho so ca nhan', 'founder context', 'coach context', 'creator context', 'ICP cho ca nhan', 'anh reference ca nhan', 'visual identity ca nhan'. Foundation skill — chay TRUOC moi skill personal brand khac (23-28). Tao file `.agents/personal-brand-context.md` voi 13+ sections.
npx skills add https://github.com/minhnv0807/ai-business-skills --skill 22-personal-brand-context
> Day la foundation skill cho THUONG HIEU CA NHAN — chay TRUOC moi skill personal brand khac (23-28). Tao file .agents/personal-brand-context.md chua thong tin goc ve con nguoi, dinh vi, story, audience, voice — de cac skill khac khong phai hoi lai.
>
> Song song voi product-marketing-context: Skill kia phuc vu san pham/dich vu, skill nay phuc vu CON NGUOI — founder, coach, creator.
| Doi tuong | Vi du cu the |
|-----------|-------------|
| Founder / CEO | Muon xay thuong hieu ca nhan song song cong ty |
| Coach / Consultant | Muon dinh vi chuyen gia, ban khoa hoc / dich vu tu van |
| Creator / KOL | Muon phat trien kenh noi dung, tang follower, monetize |
product-marketing-context thay the20-brief-client-intake de thu thap inputSkill nay tao 1 file goc (.agents/personal-brand-context.md) voi 13+ sections mo ta BAN LA AI trong goc nhin marketing, gom ca kho asset hinh anh de cac skill design/avatar biet anh nao dung lam style, mat, logo, palette. Tat ca skill personal brand khac (23-28) se doc file nay truoc khi lam viec — giong nhu "ho so y te" ma moi bac si doc truoc khi kham.
Truoc khi co file nay, moi lan dung 1 skill personal brand:
Sau khi co file .agents/personal-brand-context.md:
Buoc 1: Kiem tra file hien co
|
|-- Co file → Hoi user muon cap nhat section nao
|-- Khong co → Buoc 2
|
Buoc 2: Chon variant (Founder / Coach / Creator)
|
Buoc 3: Thu thap thong tin theo variant
|
Buoc 4: Tao file `.agents/personal-brand-context.md`
Kiem tra co file .agents/personal-brand-context.md khong.
Neu co:
Neu khong co — chuyen sang Buoc 2.
Hoi user 1 cau: "Ban la Founder/CEO, Coach/Consultant, hay Creator/KOL?"
| Variant | File | Phu hop voi | Dac biet co |
|---------|------|------------|-------------|
| Founder | variants/01-founder.md | CEO, Co-founder, Founder startup/SME | Section "Conflict brand ca nhan vs cong ty" |
| Coach | variants/02-coach.md | Coach, Consultant, Mentor, Trainer | Section "Phuong phap doc quyen" + "Hoc vien thanh cong" |
| Creator | variants/03-creator.md | YouTuber, TikToker, KOL, Blogger | Section "Niche giai tri/giao duc/lifestyle" + "Brand deal floor price" |
1. User noi ro (VD: "toi la founder") → Load variant tuong ung
2. User mo ho (VD: "toi day marketing online") → Hoi: "Ban day nhu Coach 1-1/khoa hoc, hay lam content nhu Creator?"
3. User lam nhieu vai (VD: "vua la founder vua lam content") → Chon variant CHINH + ghi chu vai phu
Sau khi chon variant, doc file variant tuong ung trong variants/ va di qua tung section:
Luu y quan trong:
Xem chi tiet tung variant:
variants/01-founder.md — 14 sections (them: Visual Asset Inventory + Conflict brand ca nhan vs cong ty)variants/02-coach.md — 15 sections (them: Visual Asset Inventory + Phuong phap doc quyen + Hoc vien thanh cong)variants/03-creator.md — 15 sections (them: Visual Asset Inventory + Niche giai tri/giao duc/lifestyle + Brand deal floor price)Luu vao .agents/personal-brand-context.md (tao folder .agents/ neu chua co).
Format file:
# Personal Brand Context — [Ho ten]
> Variant: [Founder / Coach / Creator]
> Cap nhat lan cuoi: [YYYY-MM-DD]
> Dung bang: Claude Code, ChatGPT, Gemini, bat ky AI agent nao
---
[Noi dung 13-15 sections theo variant da chon, bao gom Visual Asset Inventory]
Trong moi skill personal brand (23-28), them doan nay vao buoc "Thu thap thong tin":
## Thu thap thong tin
### Buoc 0: Kiem tra personal brand context
Kiem tra co file `.agents/personal-brand-context.md` khong:
- **Co** → Doc toan bo, lay thong tin ca nhan/audience/voice/story. Khong hoi lai.
- Lay them visual identity + visual asset inventory de dung cho design/avatar prompt. Khong hoi lai anh nao dung lam gi neu file da ghi ro.
- **Khong** → De nghi user chay skill `22-personal-brand-context` truoc.
Neu user muon tiep tuc, hoi 2-3 cau toi thieu ve ban than ho.
Skills se doc file nay:
23-personal-brand-strategy — Chien luoc thuong hieu ca nhan24-ai-avatar-production — San xuat AI avatar25-* den 28-* — Cac skill personal brand khacTruoc khi ket thuc:
.agents/personal-brand-context.mdproduct-marketing-context — Foundation skill cho san pham (song song voi skill nay)23-personal-brand-strategy — Chien luoc tong the, doc context file nay truoc24-ai-avatar-production — Tao AI avatar, can brand voice + visual identity tu file nay*Skill 22 | 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 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.