Borrowing it
Nothing to install: this file belongs to YankielDBC2/codex-skills-library. 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/YankielDBC2/codex-skills-library/main/.agents/skills/visual-polish-ai-degenericizer-v2/SKILL.mdgit clone --depth 1 https://github.com/YankielDBC2/codex-skills-libraryWrote 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/yankieldbc2/codex-skills-library/visual-polish-ai-degenericizer-v2)<a href="https://agentmods.dev/skills/yankieldbc2/codex-skills-library/visual-polish-ai-degenericizer-v2"><img src="https://agentmods.dev/badge/skills/yankieldbc2/codex-skills-library/visual-polish-ai-degenericizer-v2/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/yankieldbc2/codex-skills-library/visual-polish-ai-degenericizer-v2"><img src="https://agentmods.dev/badge/skills/yankieldbc2/codex-skills-library/visual-polish-ai-degenericizer-v2.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 | $0.00037 | $0.00397 |
| Opus 5.5 | $0.00015 | $0.00159 |
| Sonnet 5.5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
visual-polish-ai-degenericizer-v2 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 2mo 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.
What it actually says
Visual Polish AI Degenericizer v2
Goal
Remove the recognizable AI-generated look from frontend UI and replace it with compact, branded, intentional design details.
When to use
Use after a first UI pass, during redesign polish, or when the user says the page looks generic, boring, too big, too spaced out, or like a template.
Workflow
- Audit the UI for generic patterns: huge hero text, vague gradients, repeated card grids, weak imagery, excessive whitespace, flat backgrounds, and identical sections.
- Identify the brand motif or product-specific visual language that should replace generic decoration.
- Tighten spacing, type scale, and section rhythm without making the layout cramped.
- Add specificity through shapes, masks, borders, textures, local imagery, microcopy, icons, or component variants.
- Break repeated patterns with asymmetry, featured cards, editorial sections, or denser mobile layouts where appropriate.
- Preserve existing functionality and avoid rewriting everything when targeted polish is enough.
Quality bar
- Run available validation commands.
- Check mobile and desktop visual balance.
- Verify no interaction, form, or navigation behavior was broken.
Validation
- UI feels made for this brand and product, not a generic SaaS starter.
- Spacing and typography are proportional across screen sizes.
- Sections vary in rhythm while staying cohesive.
- Polish improves clarity and conversion, not only decoration.
Final response
- List the generic patterns removed and the specific design improvements applied.
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.
- 2mo ago First seen · 51 lines · 37 tokens per session scan A a85097307fcb
visual-polish-ai-degenericizer-v2 is a skill published in the GitHub repository YankielDBC2/codex-skills-library (13 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 397 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
visual-polish-ai-degenericizer-v2 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visual-polish-ai-degenericizer-v2YankielDBC2/codex-skills-library | Skill | 13 | 3mo ago | MIT | A | 37 | Claude Code, Codex |
| impeccableoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 83 | Claude Code |
| designer-skillPyModel/designer-skill | Skill | 52 | 5d ago | MIT | A | 31 | Claude Code |
| unslopoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 71 | Claude Code |
| frontend-designIlm-Alan/frontend-design | Skill | 157 | 1mo ago | MIT | A | 49 | Claude Code, Codex |
| mk:frontend-designngocsangyem/MeowKit | Skill | 15 | 5d ago | MIT | A | 35 | Claude Code |
| better-uioyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |