DYLA-ai: Skill for Claude Code

.agents/skills/design/SKILL.md

design is a skill for Claude Code from Federico-Anastasi/DYLA-ai. It costs 66 tokens per session (2,093 once invoked), scanned A, original, MIT.

A design workspace for creating social posts, stories, and banners as precisely sized web-based artboards. It exports the designs as HTML and downloadable PNG images.

In plain words
What is it for?
Use it to create a batch of branded graphics, save one artboard per design, and export finished images for publishing.
Why use it?
It keeps each design at the exact dimensions needed for its format and provides rules for consistent visual decisions. The designs can be reviewed and edited in the workspace before export.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is Federico-Anastasi/DYLA-ai's own configuration. It tells Claude Code how to work on DYLA-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DYLA-ai configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Federico-Anastasi/DYLA-ai/main/.agents/skills/design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Federico-Anastasi/DYLA-ai

Made for: Claude Code.

Wrote 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.

agentmods badge for design

README.md
[![agentmods](https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/design/github.svg)](https://agentmods.dev/skills/federico-anastasi/dyla-ai/design)
Your own site
<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.

agentmods 80×15 button for design

Your own site · 80×15
<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>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.02093
Opus 5 $0.00033 $0.01046
Sonnet 5 $0.00013 $0.00419
Haiku 4.5 $0.00007 $0.00209

Measured 11d ago against content hash b696b5a8d266, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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.

.agents/skills/design/SKILL.md · 182 lines

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

  1. Read context.md — brand and direction already recorded? Designs already there?
  2. Read the material — brief, docs (see PHASE 1)
  3. If design.json already exists: ask "Edit, or start a new batch?"
  4. Q&A (BLOCKING — 3 to 5 questions): campaign, brand, direction
  5. Write design.json straight away with meta.status: "draft"
  6. Present a conversational summary (BLOCKING — wait for validation or edits)
  7. On confirmation: set meta.status: "confirmed"
  8. 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.json or the input brief, and docs/* — the business, what is being announced or promoted
  • projects/{project}/context.md — brand tokens and direction may already be there
  • projects/{project}/design.json — if it exists
  • knowledge/ — 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"
  }
]
```

Read the full file on GitHub · 182 lines

Changes

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.

  1. 11d ago First seen · 182 lines · 66 tokens per session scan A b696b5a8d266

Subscribe to this mod's changes

design is a skill published in the GitHub repository Federico-Anastasi/DYLA-ai (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 2,093 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

banner-design

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold…

jdanigo/hydraia · 118 tokens

baoyu-infographic

A generator for infographics, which are visual summaries that organize information with text, shapes, and relationships. It combines one of 21 information layouts with one of 21 visual styles and supports custom sizes and languages.

StarryCod/cogitum · 23 tokens

baoyu-infographic

An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.

NousResearch/hermes-agent · 23 tokens

desktop-brand-builder

Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.

QwenLM/qwen-code · 69 tokens

flier

Design a print-ready, single-page flier as one self-contained HTML file: exactly one fixed-size page.

asgeirtj/system_prompts_leaks · 7 tokens

deck-swiss-international

A slide-deck template based on Swiss International graphic design: a strict 16-column grid, large clear text, charts, and one fixed bright accent colour. It provides 22 layouts for covers, timelines, comparisons, metrics, and other content.

nexu-io/html-anything · 38 tokens