Borrowing it
Nothing to install: this file belongs to Federico-Anastasi/DYLA-ai. 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/Federico-Anastasi/DYLA-ai/main/.agents/skills/design/SKILL.mdgit clone --depth 1 https://github.com/Federico-Anastasi/DYLA-aiWrote 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/federico-anastasi/dyla-ai/design)<a href="https://agentmods.dev/skills/federico-anastasi/dyla-ai/design"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/design/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/federico-anastasi/dyla-ai/design"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/design.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 | $0.00066 | $0.02093 |
| Opus 5.5 | $0.00026 | $0.00837 |
| Sonnet 5.5 | $0.00013 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
design 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design — Designs
You design freely in HTML/CSS, one artboard per design, at the exact pixel size of its format. There is no template library: the quality comes from you following the craft rules below. (Craft rules adapted from opendesign, MIT © manalkaff, and open-design's design-system contracts, Apache-2.0 © nexu-io.)
UX: chat stays conversational. The user sees the artboards in the viewer (real
render, PNG per post) and can touch the HTML in the editor next to them. In chat you
discuss in words, citing designs by id (e.g. post-opening). Never paste artboard HTML
into the chat.
PROTOCOL
- Read context.md — brand and direction already recorded? Designs already there?
- Read the material — brief, docs (see PHASE 1)
- If
design.jsonalready exists: ask "Edit, or start a new batch?" - Q&A (BLOCKING — 3 to 5 questions): campaign, brand, direction
- Write design.json straight away with
meta.status: "draft" - Present a conversational summary (BLOCKING — wait for validation or edits)
- On confirmation: set
meta.status: "confirmed" - Update context.md
Note: design.html is an export, generated on demand by the backend
(GET /api/projects/{project}/export/design.html) — it wraps, sanitises and sizes each
artboard and adds the PNG download. This skill writes JSON only.
PHASE 1 — READING
projects/{project}/brief.jsonor the input brief, anddocs/*— the business, what is being announced or promotedprojects/{project}/context.md— brand tokens and direction may already be thereprojects/{project}/design.json— if it existsknowledge/— brand or copy guidelines, if present
PHASE 2 — Q&A (BLOCKING)
Ask in a ```questions block. The format is EXACTLY this — a JSON array of objects with
id (integer), q (the question) and options (1-4 plain strings; the UI always adds
a free-text field, do not declare it). No other fields, no wrapper object:
```questions
[
{
"id": 1,
"q": "What are these posts announcing?",
"options": ["The opening", "A promotion", "An event"],
"hint": "or describe the campaign in a line"
},
{
"id": 2,
"q": "Brand: I found teal #2a6f6f in the mockup theme — use it as primary?",
"options": ["Yes, teal", "No — I will give you the palette"],
"hint": "paste hex codes if you have them"
},
{
"id": 3,
"q": "Direction: what should these feel like?",
"options": ["Clean and warm (local business)", "Bold poster (loud type, high contrast)", "Editorial (serif, calm, premium)"],
"hint": "one adjective of yours beats three of mine"
}
]
```
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 · 182 lines · 66 tokens per session scan A b696b5a8d266
design is a skill published in the GitHub repository Federico-Anastasi/DYLA-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,093 once invoked, about $0.0003 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.
Other skills, from other repositories
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
archify
Create architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as self-contained HTML with inline SVG, dark/light themes, and PNG/JPEG/WebP/SVG export.
forge-figma
Forge: design-to-code: figma, design to code, mockup, design tokens, pixel-perfect, responsive, breakpoints, style guide, dev mode, handoff, accessibility.
forge-website
Forge: websites, landing pages, and frontend UI: website, landing page, responsive, mobile layout, SEO, accessibility, Lighthouse, React, Vue, Tailwind.
visual-communication
Communicate systems and flows visually using Mermaid (flowchart, sequence, state, ER, class), the C4 model, and diagram-as-code. Use when the user asks to draw a flow, sequence diagram, state machine, ER diagram, C4 model, architecture diagram, or wants Mermaid code for a system, wants to pick a diagram type, or wants…
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design…