Borrowing it
Nothing to install: this file belongs to mrhinkle/VibeCoding-a-Website. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrhinkle/VibeCoding-a-Website/main/.claude/skills/brand-to-images/SKILL.mdgit clone --depth 1 https://github.com/mrhinkle/VibeCoding-a-WebsiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/brand-to-images)<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/brand-to-images"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/brand-to-images/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/brand-to-images"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/brand-to-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.02728 |
| Opus 5 | $0.00015 | $0.01364 |
| Sonnet 5 | $0.00006 | $0.00546 |
| Haiku 4.5 | $0.00003 | $0.00273 |
Grade A, and why
brand-to-images scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand-to-Images Skill
This skill takes your brand guidelines and transforms them into image prompts optimized for Manus (image generation orchestration) and Nano Banana (Claude's visual generation model). The result is a collection of production-ready prompts that you can feed directly into Manus to generate cohesive, on-brand images.
How This Works
Input: Either a site-brief.json from the site-interviewer skill, or brand guidelines you provide directly.
Process:
- Extract brand elements (colors, tone, mood, industry)
- Map your website pages to image needs (hero, sections, team, etc.)
- Generate detailed, visual prompts optimized for Nano Banana
- Organize by page and image type for easy reference
- Include usage guidance for each image type
Output: A image-prompts.md file with prompts organized by page, plus guidance on how to use Manus to execute them.
Key Concepts
Nano Banana Best Practices
Nano Banana (Claude's image generation model) works best when:
- Prompts are visual and specific (describe what you see, not abstract concepts)
- Prompts avoid text within images (no logos, watermarks, or words overlaid)
- Prompts include style/mood descriptors (not just "a photo of X")
- Prompts are concise but vivid (200 words is the sweet spot)
- Prompts use photographic or illustrative language depending on the image type
What You Cannot Do with Images
Before generating prompts, understand these limitations:
- Cannot generate text/logos inside images (must be added in design)
- Cannot generate faces that are too recognizable (for legal reasons)
- Cannot generate trademarked products or brand logos
- Should avoid generating specific people (use generic archetypes instead)
See references/nano-banana-prompt-guide.md for complete best practices.
Skill Workflow
Step 1: Load Brand Data
You can provide:
- Option A: A
site-brief.jsonfile (from site-interviewer) - Option B: Brand guidelines directly in this conversation
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 320 lines · 31 tokens per session scan A 20dadce87ff3
brand-to-images is a skill published in the GitHub repository mrhinkle/VibeCoding-a-Website (13 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,728 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-raw-grid
A brutalist poster-series case study for a music festival — the concept, the system, and how it scaled across formats. Built as a decision-grade design craft deck for design peers, client.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
ip-as-logo
Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent…
logo-design
Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from brand-identity, which produces the complete system (logo plus…
creative-brief-selector
Produce a creative brief grounded in live reference sites and deliberately distinct from existing demos, for any new brand build. Composes with brand-archetype-system and creative-direction. Use this skill at the start of any brand or microsite build when the result needs to land in a specific aesthetic position and…