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 julilaoshi/julilaoshi-design --skill skillgit clone --depth 1 https://github.com/julilaoshi/julilaoshi-designWrote 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/julilaoshi/julilaoshi-design/skill)<a href="https://agentmods.dev/skills/julilaoshi/julilaoshi-design/skill"><img src="https://agentmods.dev/badge/skills/julilaoshi/julilaoshi-design/skill/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/julilaoshi/julilaoshi-design/skill"><img src="https://agentmods.dev/badge/skills/julilaoshi/julilaoshi-design/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00612 |
| Opus 5.5 | $0.00021 | $0.00245 |
| Sonnet 5.5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
julilaoshi-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 1mo 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
julilaoshi-design
Produce the user's requested editable design and a verified preview. Affinity and HTML are the primary routes; Pencil is a compatibility option. Use the user's own content and visual preferences, together with ordinary design judgment. No other design skill, private library or author-specific style is required.
Choose the route
- Existing Affinity document or requested native vector editing: read Affinity. Check the installed application version and the tools actually available.
- Browser-based design or HTML output: read HTML. A standalone page can be authored directly; the optional bundled editor is in the full repository's
web/directory. - Existing
.penfile or explicit Pencil request: read Pencil. - Preserve a requested format. Infer the route from the request and source; ask one short question only if a missing choice materially changes the result. Never switch an existing native file to HTML without a reason agreed with the user.
- Other desktop editors require their own verified tool access and sample-file test. Do not advertise Illustrator support as tested.
Work
- Read the actual source. Determine the message, audience, size, output format, editable parts and protected objects from available context. Only ask for information that changes the result.
- Build a useful first draft or apply the requested local correction. Choose hierarchy and layout for this user's content; avoid inventing facts, forcing a house style or moving approved objects.
- Use available computer-use tools or a verified application interface. Read the current document and selection before editing. Follow current tool documentation, without requesting broader permissions just to reduce prompts.
- Work in a recoverable copy when testing or changing file format. Keep native source files separate from previews and generated interchange files.
- Inspect the full result and affected detail for text clipping, overlap, wrong objects, missing resources and unintended changes. Save to the actual requested path; reopen or read back when persistence is part of the task.
- Deliver source and preview/export as requested. State what was changed, what was actually verified and any remaining limitation. A successful tool call or changed file hash alone is not visual validation.
What ships with it
4 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.
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.
- 1mo ago Changed · -312 lines · -16 tokens per session 9ab501f1a905
- 1mo ago First seen · 344 lines · 68 tokens per session scan A 674bfc90a54d
julilaoshi-design is a skill published in the GitHub repository julilaoshi/julilaoshi-design (121 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 612 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ui-html-renderer
Use this specialist for unusually complex stateful HTML, blank/runtime-risk repair, strict source-to-HTML fidelity, reusable component galleries, brand boards, or detailed implementation handoff. Ordinary single-page HTML uses ui-design-executor, which already preserves HTML-default delivery and baseline…
product-ui
Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…
frontend-taste
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…
frontend-patterns
CSS design system principles -- token usage, semantic layering, mobile-first, component isolation.
design-tokens
Project-level DESIGN.md tokens reference. When the project has a DESIGN.md file, agents producing UI / components / visuals must consult this skill to use canonical color/typography/spacing tokens rather than inventing new ones. Triggers on: UI generation, component creation, design brief, visual asset, tailwind…