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 guia-matthieu/clawfu-skills --skill design-trends-2026git clone --depth 1 https://github.com/guia-matthieu/clawfu-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/guia-matthieu/clawfu-skills/design-trends-2026)<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/design-trends-2026"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/design-trends-2026/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/guia-matthieu/clawfu-skills/design-trends-2026"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/design-trends-2026.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
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 | $0.00137 | $0.07807 |
| Opus 5 | $0.00068 | $0.03904 |
| Sonnet 5 | $0.00027 | $0.01561 |
| Haiku 4.5 | $0.00014 | $0.00781 |
Grade A, and why
design-trends-2026 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 13d 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 — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Trends 2026
Apply the 10 dominant graphic design aesthetics of 2026 to any creative project — based on Kittl × Savee's trend report, backed by Adobe, Figma, and Pinterest platform data.
When to Use This Skill
- Briefing a designer or AI image generator — translate vague "make it modern" into precise style vocabulary
- Creating brand identity or visual refresh — pick aesthetics that match your audience and positioning
- Building mood boards — combine trends with intent, not just screenshots
- Designing social/marketing assets — use visual languages trending on platforms right now
- Pitching creative direction — back your choices with data signals, not just taste
Methodology Foundation
Source: Kittl × Savee — "2026 Design Trends Report" (January 2026)
Core Principle: 2026 design sits at the crossroads of two forces: human-made visuals are returning (Adobe reports +30% searches for hand-drawn elements), while AI accelerates exploration (60% of designers use AI for early concepts per Figma 2024). The best work in 2026 lives in between — messy meets precise, nostalgic meets futuristic, chaotic meets intentional.
Why This Matters: Trends aren't decoration — they're cultural signals. Choosing the right visual language connects you to what your audience already feels. Choosing the wrong one makes you invisible or dated. This skill gives you the vocabulary, the data, and the decision framework to pick deliberately.
What Claude Does vs What You Decide
"Claude maps the territory. You pick the direction."
| Claude handles | You provide |
|---|---|
| Identifying which trend(s) fit your brief | Your brand personality and audience |
| Generating precise AI image prompts per trend | Final aesthetic judgment and taste |
| Combining multiple trends into coherent direction | Business context (premium vs accessible, etc.) |
| Explaining the cultural signal behind each trend | Whether a trend aligns with your positioning |
| Creating mood board descriptions and style guides | Validation with real audience feedback |
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.
- 13d ago First seen · 768 lines · 137 tokens per session scan A 740dbc5b7445
design-trends-2026 is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 137 tokens to every session and 7,807 once invoked, about $0.0007 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
svg-check
Apply when editing, generating, or reviewing any SVG diagram. Pixel-perfect Playwright bbox-check is the acceptance test — eyeballing is not sufficient. Run on every SVG before declaring done.
drawio
Apply when creating or reviewing architecture diagrams, Mermaid diagrams, or draw.io files.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
ads-performance-analytics
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…