How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-brand-kitBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
Brand Kit
Generate a cohesive brand visual kit — logo concept, color palette moodboard, and typography pairing suggestions.
Inputs
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
brand_name | text | yes | — | Name of the brand. |
industry | text | yes | — | Industry or niche (e.g. "sustainable fashion", "fintech startup", "artisan bakery"). |
personality | text | no | modern, trustworthy, approachable | 3–5 brand personality adjectives (e.g. "bold, edgy, youthful" or "elegant, minimal, luxury"). |
color_preference | text | no | — | Optional color direction (e.g. "earthy greens and terracotta", "monochrome with gold accents"). |
Steps
Generate a multi-asset brand exploration in one parallel plan.
Phase A — Visual exploration (parallel)
Submit ONE the plan with:
- Logo concept A —
muapi image generate(model=gpt-image-2-text-to-image, aspect_ratio=1:1):
- Style: minimalist wordmark or lettermark on white background, flat design.
- Prompt: "Minimalist logo for '{{brandname}}', {{industry}} brand, {{personality}} personality. Clean vector-style, white background, professional. {{colorpreference}}".
- Logo concept B —
muapi image generate(model=nano-banana-2, aspect_ratio=1:1):
- Style: icon + wordmark combination.
- Prompt: "Modern logo mark + wordmark for '{{brandname}}', {{industry}}, {{personality}}. Bold, distinctive, scalable icon design, white background. {{colorpreference}}".
- Moodboard / Color palette —
muapi image generate(model=nano-banana-pro, aspect_ratio=16:9):
- A flat design moodboard showing: 5 brand colors (as swatches with hex-like labels), lifestyle photography inspo tiles, texture samples.
- Prompt: "Brand moodboard for a {{personality}} {{industry}} brand called '{{brandname}}'. Show 5 color palette swatches, 4 lifestyle photo tiles, typography samples. Flat lay design, white background. {{colorpreference}}".
- Pattern / texture asset —
muapi image generate(model=nano-banana-2, aspect_ratio=1:1):
- A seamless brand pattern or texture for use in backgrounds, packaging, stationery.
- Prompt: "Seamless brand pattern for {{brandname}}, {{industry}}, {{personality}} aesthetic. Subtle, tileable, modern. {{colorpreference}}".
Phase B — Deliverables summary
After the plan completes, return:
- Asset references (logo A, logo B, moodboard, pattern).
- Color palette recommendation: 5 hex codes with roles (Primary, Secondary, Accent, Neutral Light, Neutral Dark).
- Typography pairing: 2 Google Font pairings appropriate for the brand personality.
- Usage guidance: when to use each logo variant, color do/don'ts.
Notes
- If the user has reference images in the session, analyze their style before generating.
- Suggest logo A for digital-first brands, logo B for physical/retail brands.
- All four assets run in parallel for speed.
Trigger Keywords
brand kit, brand identity, logo, branding, brand design, visual identity
Notes for the Executing Agent
- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call
muapiCLI commands. Usemuapi auth configurefirst ifMUAPI_API_KEYis unset. - For model IDs without a CLI alias yet, fall back to the raw endpoint via
curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'and poll withmuapi predict wait <request_id>. - Substitute
{{input_name}}placeholders with the user's actual inputs before issuing each call.



