菜单
Use when completed Brandmint outputs should be published into NotebookLM and turned into NotebookLM artifacts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
End-to-end brand identity orchestration system. Generates text strategy, visual assets, campaign copy, video deliverables, and publishing outputs using 44 specialized skills across 9 categories. Chains FAL.AI/Nano Banana/Flux visual generation with brand positioning, buyer personas, and campaign workflows via wave-based execution. Includes Remotion-based programmatic video generation.
Transform markdown documentation folders into professional Astro-based wikis using refero-design principles (research-first, anti-AI-slop: no default emojis, no 3-column layouts, sections + dividers + media blocks over cards, neutral color system). Use when the user has a folder of .md files and wants to generate a polished wiki/documentation site with dark/light mode support, readable typography, and professional aesthetics. Triggers on requests involving markdown-to-wiki conversion, documentation site generation, Astro wiki creation, or brand wiki themes.
Defines brand voice persona and tone calibration using persona and positioning data to produce a reusable meta-prompt for copywriting.
Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro, alibaba image pro, dashscope pro, professional text rendering
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabilities: text-to-image, multi-image editing, complex text rendering. Triggers: qwen image, qwen-image, alibaba image, dashscope image, qwen image 2, qwen image pro
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
| name | notebooklm-publisher |
| description | Use when completed Brandmint outputs should be published into NotebookLM and turned into NotebookLM artifacts. |
Wave: 7 (Publishing) Type: Post-hook (no text skills or visual assets) Depends on: Wave 6 (all brand outputs complete)
Transforms all brandmint pipeline outputs into a Google NotebookLM notebook and generates 5 branded artifacts:
| Artifact | Type | Format | Est. Time |
|---|---|---|---|
| Brand Overview Deck | slide-deck | 5-15 min | |
| Product Showcase Deck | slide-deck | 5-15 min | |
| Audio Overview | audio | MP3 | 10-20 min |
| Brand Report | report | Markdown | 5-15 min |
| Mind Map | mind-map | JSON | <1 min |
Source Building: Reads .brandmint/outputs/*.json (16 skill outputs) and
brand-config.yaml, converts them into 5 structured markdown documents
optimised for NotebookLM processing
Notebook Creation: Creates a "{Brand} — Brand Intelligence" notebook in NotebookLM and uploads the 5 source documents
Artifact Generation: Generates artifacts with brand-specific instructions that inject colours, typography, voice/tone, and positioning data
Parallel Execution: Mind map first (instant), then decks + report in parallel (3 workers), then audio (sequential). Total ~25 min wall time.
Download: All artifacts downloaded to deliverables/notebooklm/artifacts/
pip install notebooklm-py # or: pip install 'brandmint[publishing]'
notebooklm login # Google OAuth — opens browser
bm launch --config brand-config.yaml --waves 1-7
bm publish notebooklm --config brand-config.yaml
bm publish notebooklm --config brand-config.yaml --dry-run
bm publish notebooklm --config brand-config.yaml --artifacts audio-overview,mind-map
bm publish notebooklm --config brand-config.yaml --force
<brand-dir>/
deliverables/
notebooklm/
sources/
brand-foundation.md
brand-strategy.md
campaign-content.md
communications-social.md
visual-asset-catalog.md
artifacts/
brand-overview-deck.pdf
product-showcase-deck.pdf
brand-audio-overview.mp3
brand-report.md
brand-mind-map.json
publish-report.json
State is persisted at .brandmint/notebooklm-state.json. Re-running the
command skips already-completed steps (sources already indexed, artifacts
already downloaded). Use --force to start fresh.
| Document | Skills | Purpose |
|---|---|---|
| Brand Foundation | niche-validator, buyer-persona, competitor-analysis + config | Market, audience, brand definition |
| Brand Strategy | positioning, MDS, voice-and-tone, product description, visual identity | Strategy and identity |
| Campaign Content | campaign copy, video script, ads, press release | Marketing creative |
| Communications & Social | email sequences, social calendar, hooks, influencer, reviews | Comms and distribution |
| Visual Asset Catalog | Generated asset inventory | Visual system reference |