Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Yrzhe/claude-skills --skill design-distillergit clone --depth 1 https://github.com/Yrzhe/claude-skillsWrote 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/yrzhe/claude-skills/design-distiller)<a href="https://agentmods.dev/skills/yrzhe/claude-skills/design-distiller"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/design-distiller/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/yrzhe/claude-skills/design-distiller"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/design-distiller.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 | $0.00063 | $0.03697 |
| Opus 5 | $0.00032 | $0.01849 |
| Sonnet 5 | $0.00013 | $0.00739 |
| Haiku 4.5 | $0.00006 | $0.00370 |
Grade A, and why
design-distiller 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 12d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Distiller
Give any website URL, extract the complete design system into a Design MD + composable design tokens.
Triggers
/design-distiller- "scrape this website's design" / "extract design system"
- "design scrape" / "make a Design MD"
- "analyze this site's design"
Core Concepts
Design MD
A pure Markdown design system document that AI agents can read directly to generate matching UI. Format follows awesome-design-md.
Reference Pool
references/{slug}/ — One folder per website, containing the full Design MD + screenshot assets. This is the raw material library.
Digest Pool
digests/ — Cross-site design tokens decomposed by dimension (typography, colors, spacing, components, etc.). Each entry is tagged with its source website. Used for mix-and-match composition when building new sites.
Output Structure
design-distiller/
├── references/ # Reference Pool
│ └── {slug}/
│ ├── DESIGN.md # Full Design MD (9 modules)
│ ├── meta.json # Metadata
│ └── screenshots/ # Key page screenshots
│ ├── homepage.png
│ ├── homepage-mobile.png
│ └── components.png
└── digests/ # Digest Pool
├── typography.md # All font systems
├── colors.md # All color systems
├── spacing.md # All spacing systems
├── components.md # All component patterns
├── depth.md # All shadow & elevation systems
├── motion.md # All motion specs
├── layouts.md # All layout systems
└── philosophy.md # All design philosophies
Pre-loaded References
The Reference Pool ships with 55 pre-loaded brands imported from awesome-design-md and the nothing-design skill. These text-only imports differ from freshly scraped references:
- No
screenshots/— visual data was not captured during batch import. Screenshots are generated only when running the full 4-phase pipeline on a new URL. - No
meta.json— metadata is generated only by the pipeline's Generate phase. Pre-loaded references have their metadata embedded in the Digest Pool cross-references instead. - Nothing uses an extended format —
references/nothing/contains multi-file documentation (DESIGN.md + tokens.md + components.md + platform-mapping.md) from a standalone design system skill. It does not follow the standard 9-module format because its craft rules and composition philosophy cannot be reduced to that template.
What ships with it
60 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.
- CHANGELOG.md 3.3 KB
- digests/colors.md 16 KB
- digests/components.md 14 KB
- digests/depth.md 12 KB
- digests/layouts.md 10 KB
- digests/motion.md 5.7 KB
- digests/philosophy.md 14 KB
- digests/spacing.md 9.7 KB
- digests/typography.md 20 KB
- prompts/analyzer.md 4.9 KB
- prompts/digester.md 6.1 KB
- prompts/generator.md 2.9 KB
- prompts/scraper.md 5.8 KB
- references/airbnb/DESIGN.md 14 KB
- references/airtable/DESIGN.md 3.5 KB
- references/apple/DESIGN.md 20 KB
- references/bmw/DESIGN.md 9.6 KB
- references/cal/DESIGN.md 17 KB
- references/claude/DESIGN.md 20 KB
- references/clay/DESIGN.md 17 KB
- references/clickhouse/DESIGN.md 15 KB
- references/cohere/DESIGN.md 14 KB
- references/coinbase/DESIGN.md 4.9 KB
- references/composio/DESIGN.md 20 KB
- references/cursor/DESIGN.md 19 KB
- references/elevenlabs/DESIGN.md 15 KB
- references/expo/DESIGN.md 18 KB
- references/figma/DESIGN.md 11 KB
- references/framer/DESIGN.md 17 KB
- references/hashicorp/DESIGN.md 15 KB
- references/ibm/DESIGN.md 19 KB
- references/intercom/DESIGN.md 6.3 KB
- references/kraken/DESIGN.md 4.2 KB
- references/linear.app/DESIGN.md 22 KB
- references/lovable/DESIGN.md 17 KB
- references/minimax/DESIGN.md 14 KB
- references/mintlify/DESIGN.md 17 KB
- references/miro/DESIGN.md 4.7 KB
- references/mistral.ai/DESIGN.md 15 KB
- references/mongodb/DESIGN.md 15 KB
- references/nothing/components.md 6.1 KB
- references/nothing/DESIGN.md 9.2 KB
- references/nothing/platform-mapping.md 1.9 KB
- references/nothing/tokens.md 5.8 KB
- references/notion/DESIGN.md 18 KB
- references/nvidia/DESIGN.md 17 KB
- references/ollama/DESIGN.md 15 KB
- references/opencode.ai/DESIGN.md 15 KB
- references/pinterest/DESIGN.md 12 KB
- references/posthog/DESIGN.md 18 KB
- references/raycast/DESIGN.md 18 KB
- references/replicate/DESIGN.md 14 KB
- references/resend/DESIGN.md 18 KB
- references/revolut/DESIGN.md 8.4 KB
- references/runwayml/DESIGN.md 14 KB
- references/sanity/DESIGN.md 21 KB
- references/sentry/DESIGN.md 14 KB
- references/spacex/DESIGN.md 11 KB
- references/spotify/DESIGN.md 13 KB
- references/stripe/DESIGN.md 20 KB
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.
- 12d ago First seen · 429 lines · 63 tokens per session scan A 708d33b1bac4
design-distiller is a skill published in the GitHub repository Yrzhe/claude-skills (33 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 3,697 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.