Communitygithub.com

ARYAN2302/liquid_researcher

Chinese-market SaaS pricing page template — soft sky-blue glass-morphism, 4-tier card grid with one elevated "recommended" tier, monthly/annual toggle, FAQ accordion, ¥ pricing with Inter numerals, careful CJK linebreaking, ICP filing footer.

Was ist liquid_researcher?

liquid_researcher is a Claude Code agent skill that chinese-market SaaS pricing page template — soft sky-blue glass-morphism, 4-tier card grid with one elevated "recommended" tier, monthly/annual toggle, FAQ accordion, ¥ pricing with Inter numerals, careful CJK linebreaking, ICP filing footer.

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/ARYAN2302/liquid_researcher/tree/HEAD/skills/design/design-templates/pricing-page

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Pricing Page Template

Use this template when the artifact is a Chinese-market SaaS / product pricing page that needs to feel premium, calm, and design-led — not a generic 3-tier feature-checklist grid.

Use When

  • The product is sold to a Chinese audience (¥, 元/月, ICP filing, 微信/支付宝 implied).
  • The pricing model fits tier cards (3–4 tiers, optional monthly/annual toggle).
  • One tier should be visibly elevated (early-bird, most-popular, recommended).
  • The brand can carry soft sky-blue glassmorphism — or you intend to retheme the palette while keeping the structure.

Avoid When

  • The product is global / EN-primary — re-theme heavily or use a different template.
  • Pricing is purely per-seat / usage-metered with no tiers — a tier grid is the wrong shape.
  • The page needs a deep feature-comparison matrix as the primary surface — start from a comparison-table-first template instead.
  • It's an OSS / free / waitlist product — use waitlist-page/ or saas-landing/.

Required Reading

Read this SKILL.md first. Do not read pricing-cn.html by default.

Read pricing-cn.html only when you need concrete tier-card geometry, the elevated-tier transform values, the monthly/annual toggle behavior, or the FAQ single-open pattern. Extract patterns; do not copy DOM, classnames, brand copy, or placeholder prices wholesale.

Design Strategy

Decide before building:

  1. Tier count — 3 (standard) or 4 (with an Observer / Free tier).
  2. Recommended tier — which one lifts and inverts (white CTA on dark) ?
  3. Toggle model — monthly / annual with discount %, or batch / cohort labels (第 N 批) for early-access.
  4. Tier naming — generic (Basic / Pro / Business) or atmospheric (Observer / Early Bird / Founder / Patron). The template's voice favors atmospheric.

Layout Bias

Prefer:

  • one elevated tier (3D lift + image-backed scrim + inverted CTA), the rest flat glass cards
  • ¥ + Inter tabular numerals for the price; PingFang / MiSans for surrounding copy
  • short feature lists (≤ 6 per tier), each prefixed by a single hairline check
  • a "value strip" below the cards (4 short callouts) rather than a giant comparison table
  • FAQ as single-open accordion, not all-expanded by default
  • ICP filing in the footer (real or placeholder)

Avoid:

  • multiple "推荐" badges across tiers — pick one
  • 黑金 gradients or neon accents (forbidden aesthetic)
  • generic emoji or 3D-icon feature bullets
  • forcing English tier names when the audience reads Chinese
  • pretending to be Stripe / Linear with a near-identical clone of their pricing page

Platform / Size

Desktop-first responsive web page. Cards reflow to 2 + 2 at tablet width and stack on mobile. Keep the elevated tier prominent at every breakpoint.

Individual skills in this repo

This repo contains 8 individual skills — each has its own dedicated page.

ARYAN2302/liquid_researcher

Generate a single-file Chinese atelier-style portfolio website (horizontal-row list + hover-reveal thumb interaction, art lishu typography "Alimama DaoLiTi" via CDN, light/dark theme, hash-routed detail pages). Takes a natural-language description of the studio (name, director, discipline, works) and outputs ONE working .html file. Runs in BOTH Claude Code (writes to ~/Desktop) and GLM / online chat (outputs HTML inline). Trigger phrases include "做个中式工作室作品集", "做个隶书作品集", "lishu-portfolio-gen ...", "做个白屋风格的作品集", or when user drags this skill folder into chat asking for an atelier-style site.

ARYAN2302/liquid_researcher

Premium calm-tech SaaS landing template — bilingual (CN/EN) literary voice over a dark forest-night palette with warm gold accent, Cormorant + Noto Serif SC, Three.js procedural forest hero, station-based scrolling narrative, custom cursor. Built for ambient-AI / creative-tool / philosophical SaaS, not loud commercial launch.

ARYAN2302/liquid_researcher

Pro-camera HUD mockup template — full-viewport black canvas wrapping a real video with monospace overlays (corner brackets, top status bar, side AF/exposure columns, bottom timecode + aperture/shutter/ISO row, vertical 8-filter wheel, animated reticle). For cinematographer portfolios, camera-app demos, LUT pack previews, filter-look auditions. NOT a TikTok/Reels mockup, NOT a storyboard, NOT a shot list, NOT a script document. The chrome wraps real footage — never a div placeholder.

ARYAN2302/liquid_researcher

Premium pre-launch waitlist page template — dark charcoal canvas with subtle vignette, drifting portrait video-thumbnail cards, fade-up cascades, glass nav, live-updating join counter, single email form with success/error states. Built for creative-tool / AI / niche-SaaS invite-only launches with hushed exclusive tone, not loud growth-marketing.

ARYAN2302/liquid_researcher

Route design-related HTML artifact tasks to the right artifact skill, reference, design system generation, or export skill.

ARYAN2302/liquid_researcher

Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.

ARYAN2302/liquid_researcher

Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

ARYAN2302/liquid_researcher

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.

Verwandte Skills