blun-king-cli 9.1.62 → 9.1.64
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bin/context-performance-policy.cjs +18 -0
- package/bin/launcher-runtime.js +2 -2
- package/bin/package-regression-policy.cjs +77 -0
- package/bin/provider-idle-timeout-policy.cjs +14 -0
- package/bin/skill-listing-performance-policy.cjs +33 -0
- package/bin/standard-tools-bootstrap.js +80 -26
- package/bin/turn-thinking-policy.cjs +66 -0
- package/bin/turn-tool-performance-policy.cjs +141 -0
- package/blun.mjs +520 -221
- package/package.json +4 -1
- package/release-planned-removals.json +4 -0
- package/scripts/check-package-regression.js +38 -0
- package/standard-skills/agent-browser/SKILL.md +19 -0
- package/standard-skills/agent-browser/references/runtime.md +8 -0
- package/standard-skills/design-taste-frontend/SKILL.md +1206 -0
- package/standard-skills/full-output-enforcement/SKILL.md +49 -0
- package/standard-skills/high-end-visual-design/SKILL.md +98 -0
- package/standard-skills/image-to-code/SKILL.md +1228 -0
- package/standard-skills/industrial-brutalist-ui/SKILL.md +92 -0
- package/standard-skills/minimalist-ui/SKILL.md +85 -0
- package/standard-skills/motion-design-taste/SKILL.md +74 -0
- package/standard-skills/playwright-testing/SKILL.md +19 -0
- package/standard-skills/playwright-testing/references/runtime.md +7 -0
- package/standard-skills/premortem/SKILL.md +148 -0
- package/standard-skills/redesign-existing-projects/SKILL.md +178 -0
- package/standard-skills/screenshot-lesen/SKILL.md +52 -0
- package/standard-skills/stitch-design-taste/DESIGN.md +121 -0
- package/standard-skills/stitch-design-taste/SKILL.md +184 -0
- package/standard-skills/telegram-channel/SKILL.md +18 -0
- package/standard-skills/telegram-channel/references/runtime.md +7 -0
- package/standard-skills/translate-native/LICENSE +21 -0
- package/standard-skills/translate-native/SKILL.md +39 -0
- package/standard-skills/translate-native/VERSION +1 -0
- package/standard-skills/translate-native/provenance.json +7 -0
- package/standard-skills/translate-native/references/evaluation-protocol.md +95 -0
- package/standard-skills/translate-native/references/native-orthography.md +79 -0
- package/standard-skills/translate-native/references/native-translation-standard.md +94 -0
- package/standard-skills/translate-native/references/structured-content.md +72 -0
- package/standard-skills/translate-native/references/translationese-review.md +77 -0
- package/standard-skills/translate-native/scripts/blun_language_guard.py +686 -0
- package/standard-skills/translate-native/scripts/check_diacritics.py +353 -0
- package/standard-skills/translate-native/scripts/guard_service_client.py +82 -0
- package/standard-skills/translate-native/scripts/language_gateway.py +62 -0
- package/standard-skills/translate-native/scripts/language_quality.py +172 -0
- package/standard-skills/translate-native/scripts/pre_output_guard.py +67 -0
- package/standard-skills/translate-native/scripts/translation_guard.py +916 -0
- package/standard-skills/web-lesen/SKILL.md +58 -0
- package/standard-skills/windows-mcp/SKILL.md +19 -0
- package/standard-skills/windows-mcp/references/runtime.md +9 -0
|
@@ -0,0 +1,92 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: industrial-brutalist-ui
|
|
3
|
+
description: Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# SKILL: Industrial Brutalism & Tactical Telemetry UI
|
|
7
|
+
|
|
8
|
+
## 1. Skill Meta
|
|
9
|
+
**Name:** Industrial Brutalism & Tactical Telemetry Interface Engineering
|
|
10
|
+
**Description:** Advanced proficiency in architecting web interfaces that synthesize mid-century Swiss Typographic design, industrial manufacturing manuals, and retro-futuristic aerospace/military terminal interfaces. This discipline requires absolute mastery over rigid modular grids, extreme typographic scale contrast, purely utilitarian color palettes, and the programmatic simulation of analog degradation (halftones, CRT scanlines, bitmap dithering). The objective is to construct digital environments that project raw functionality, mechanical precision, and high data density, deliberately discarding conventional consumer UI patterns.
|
|
11
|
+
|
|
12
|
+
## 2. Visual Archetypes
|
|
13
|
+
The design system operates by merging two distinct but highly compatible visual paradigms. **Pick ONE per project and commit to it. Do not alternate or mix both modes within the same interface.**
|
|
14
|
+
|
|
15
|
+
### 2.1 Swiss Industrial Print
|
|
16
|
+
Derived from 1960s corporate identity systems and heavy machinery blueprints.
|
|
17
|
+
* **Characteristics:** High-contrast light modes (newsprint/off-white substrates). Reliance on monolithic, heavy sans-serif typography. Unforgiving structural grids outlined by visible dividing lines. Aggressive, asymmetric use of negative space punctuated by oversized, viewport-bleeding numerals or letterforms. Heavy use of primary red as an alert/accent color.
|
|
18
|
+
|
|
19
|
+
### 2.2 Tactical Telemetry & CRT Terminal
|
|
20
|
+
Derived from classified military databases, legacy mainframes, and aerospace Heads-Up Displays (HUDs).
|
|
21
|
+
* **Characteristics:** Dark mode exclusivity. High-density tabular data presentation. Absolute dominance of monospaced typography. Integration of technical framing devices (ASCII brackets, crosshairs). Application of simulated hardware limitations (phosphor glow, scanlines, low bit-depth rendering).
|
|
22
|
+
|
|
23
|
+
## 3. Typographic Architecture
|
|
24
|
+
Typography is the primary structural and decorative infrastructure. Imagery is secondary. The system demands extreme variance in scale, weight, and spacing.
|
|
25
|
+
|
|
26
|
+
### 3.1 Macro-Typography (Structural Headers)
|
|
27
|
+
* **Classification:** Neo-Grotesque / Heavy Sans-Serif.
|
|
28
|
+
* **Optimal Web Fonts:** Neue Haas Grotesk (Black), Inter (Extra Bold/Black), Archivo Black, Roboto Flex (Heavy), Monument Extended.
|
|
29
|
+
* **Implementation Parameters:**
|
|
30
|
+
* **Scale:** Deployed at massive scales using fluid typography (e.g., `clamp(4rem, 10vw, 15rem)`).
|
|
31
|
+
* **Tracking (Letter-spacing):** Extremely tight, often negative (`-0.03em` to `-0.06em`), forcing glyphs to form solid architectural blocks.
|
|
32
|
+
* **Leading (Line-height):** Highly compressed (`0.85` to `0.95`).
|
|
33
|
+
* **Casing:** Exclusively uppercase for structural impact.
|
|
34
|
+
|
|
35
|
+
### 3.2 Micro-Typography (Data & Telemetry)
|
|
36
|
+
* **Classification:** Monospace / Technical Sans.
|
|
37
|
+
* **Optimal Web Fonts:** JetBrains Mono, IBM Plex Mono, Space Mono, VT323, Courier Prime.
|
|
38
|
+
* **Implementation Parameters:**
|
|
39
|
+
* **Scale:** Fixed and small (`10px` to `14px` / `0.7rem` to `0.875rem`).
|
|
40
|
+
* **Tracking:** Generous (`0.05em` to `0.1em`) to simulate mechanical typewriter spacing or terminal matrices.
|
|
41
|
+
* **Leading:** Standard to tight (`1.2` to `1.4`).
|
|
42
|
+
* **Casing:** Exclusively uppercase. Used for all metadata, navigation, unit IDs, and coordinates.
|
|
43
|
+
|
|
44
|
+
### 3.3 Textural Contrast (Artistic Disruption)
|
|
45
|
+
* **Classification:** High-Contrast Serif.
|
|
46
|
+
* **Optimal Web Fonts:** Playfair Display, EB Garamond, Times New Roman.
|
|
47
|
+
* **Implementation Parameters:** Used exceedingly sparingly. Must be subjected to heavy post-processing (halftone filters, 1-bit dithering) to degrade vector perfection and create textural juxtaposition against the clean sans-serifs.
|
|
48
|
+
|
|
49
|
+
## 4. Color System
|
|
50
|
+
The color architecture is uncompromising. Gradients, soft drop shadows, and modern translucency are strictly prohibited. Colors simulate physical media or primitive emissive displays.
|
|
51
|
+
|
|
52
|
+
**CRITICAL: Choose ONE substrate palette per project and use it consistently. Never mix light and dark substrates within the same interface.**
|
|
53
|
+
|
|
54
|
+
### If Swiss Industrial Print (Light):
|
|
55
|
+
* **Background:** `#F4F4F0` or `#EAE8E3` (Matte, unbleached documentation paper).
|
|
56
|
+
* **Foreground:** `#050505` to `#111111` (Carbon Ink).
|
|
57
|
+
* **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). This is the ONLY accent color. Used for strike-throughs, thick structural dividing lines, or vital data highlights.
|
|
58
|
+
|
|
59
|
+
### If Tactical Telemetry (Dark):
|
|
60
|
+
* **Background:** `#0A0A0A` or `#121212` (Deactivated CRT. Avoid pure `#000000`).
|
|
61
|
+
* **Foreground:** `#EAEAEA` (White phosphor). This is the primary text color.
|
|
62
|
+
* **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). Same red, same rules.
|
|
63
|
+
* **Terminal Green (`#4AF626`):** Optional. Use ONLY for a single specific UI element (e.g., one status indicator or one data readout) — never as a general text color. If it doesn't serve a clear purpose, omit it entirely.
|
|
64
|
+
|
|
65
|
+
## 5. Layout and Spatial Engineering
|
|
66
|
+
The layout must appear mathematically engineered. It rejects conventional web padding in favor of visible compartmentalization.
|
|
67
|
+
|
|
68
|
+
* **The Blueprint Grid:** Strict adherence to CSS Grid architectures. Elements do not float; they are anchored precisely to grid tracks and intersections.
|
|
69
|
+
* **Visible Compartmentalization:** Extensive utilization of solid borders (`1px` or `2px solid`) to delineate distinct zones of information. Horizontal rules (`<hr>`) frequently span the entire container width to segregate operational units.
|
|
70
|
+
* **Bimodal Density:** Layouts oscillate between extreme data density (tightly packed monospace metadata clustered together) and vast expanses of calculated negative space framing macro-typography.
|
|
71
|
+
* **Geometry:** Absolute rejection of `border-radius`. All corners must be exactly 90 degrees to enforce mechanical rigidity.
|
|
72
|
+
|
|
73
|
+
## 6. UI Components and Symbology
|
|
74
|
+
Standard web UI conventions are replaced with utilitarian, industrial graphic elements.
|
|
75
|
+
|
|
76
|
+
* **Syntax Decoration:** Utilization of ASCII characters to frame data points.
|
|
77
|
+
* *Framing:* `[ DELIVERY SYSTEMS ]`, `< RE-IND >`
|
|
78
|
+
* *Directional:* `>>>`, `///`, `\\\\`
|
|
79
|
+
* **Industrial Markers:** Prominent integration of registration (`®`), copyright (`©`), and trademark (`™`) symbols functioning as structural geometric elements rather than legal text.
|
|
80
|
+
* **Technical Assets:** Integration of crosshairs (`+`) at grid intersections, repeating vertical lines (barcodes), thick horizontal warning stripes, and randomized string data (e.g., `REV 2.6`, `UNIT / D-01`) to simulate active mechanical processes.
|
|
81
|
+
|
|
82
|
+
## 7. Textural and Post-Processing Effects
|
|
83
|
+
To prevent the design from appearing purely digital, simulated analog degradation is engineered into the frontend via CSS and SVG filters.
|
|
84
|
+
|
|
85
|
+
* **Halftone and 1-Bit Dithering:** Transforming continuous-tone images or large serif typography into dot-matrix patterns. Achieved via pre-processing or CSS `mix-blend-mode: multiply` overlays combined with SVG radial dot patterns.
|
|
86
|
+
* **CRT Scanlines:** For terminal interfaces, applying a `repeating-linear-gradient` to the background to simulate horizontal electron beam sweeps (e.g., `repeating-linear-gradient(0deg, transparent, transparent 2px, rgba(0,0,0,0.1) 2px, rgba(0,0,0,0.1) 4px)`).
|
|
87
|
+
* **Mechanical Noise:** A global, low-opacity SVG static/noise filter applied to the DOM root to introduce a unified physical grain across both dark and light modes.
|
|
88
|
+
|
|
89
|
+
## 8. Web Engineering Directives
|
|
90
|
+
1. **Grid Determinism:** Utilize `display: grid; gap: 1px;` with contrasting parent/child background colors to generate mathematically perfect, razor-thin dividing lines without complex border declarations.
|
|
91
|
+
2. **Semantic Rigidity:** Construct the DOM using precise semantic tags (`<data>`, `<samp>`, `<kbd>`, `<output>`, `<dl>`) to accurately reflect the technical nature of the telemetry.
|
|
92
|
+
3. **Typography Clamping:** Implement CSS `clamp()` functions exclusively for macro-typography to ensure massive text scales aggressively while maintaining structural integrity across viewports.
|
|
@@ -0,0 +1,85 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: minimalist-ui
|
|
3
|
+
description: Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Protocol: Premium Utilitarian Minimalism UI Architect
|
|
7
|
+
|
|
8
|
+
## 1. Protocol Overview
|
|
9
|
+
Name: Premium Utilitarian Minimalism & Editorial UI
|
|
10
|
+
Description: An advanced frontend engineering directive for generating highly refined, ultra-minimalist, "document-style" web interfaces analogous to top-tier workspace platforms. This protocol strictly enforces a high-contrast warm monochrome palette, bespoke typographic hierarchies, meticulous structural macro-whitespace, bento-grid layouts, and an ultra-flat component architecture with deliberate muted pastel accents. It actively rejects standard generic SaaS design trends.
|
|
11
|
+
|
|
12
|
+
## 2. Absolute Negative Constraints (Banned Elements)
|
|
13
|
+
The AI must strictly avoid the following generic web development defaults:
|
|
14
|
+
- DO NOT use the "Inter", "Roboto", or "Open Sans" typefaces.
|
|
15
|
+
- DO NOT use generic, thin-line icon libraries like "Lucide", "Feather", or standard "Heroicons".
|
|
16
|
+
- DO NOT use Tailwind's default heavy drop shadows (e.g., `shadow-md`, `shadow-lg`, `shadow-xl`). Shadows must be practically non-existent or heavily customized to be ultra-diffuse and low opacity (< 0.05).
|
|
17
|
+
- DO NOT use primary colored backgrounds for large elements or sections (e.g., no bright blue, green, or red hero sections).
|
|
18
|
+
- DO NOT use gradients, neon colors, or 3D glassmorphism (beyond subtle navbar blurs).
|
|
19
|
+
- DO NOT use `rounded-full` (pill shapes) for large containers, cards, or primary buttons.
|
|
20
|
+
- DO NOT use emojis anywhere in code, markup, text content, headings, or alt text. Replace with proper icons or clean SVG primitives.
|
|
21
|
+
- DO NOT use generic placeholder names like "John Doe", "Acme Corp", or "Lorem Ipsum". Use realistic, contextual content.
|
|
22
|
+
- DO NOT use AI copywriting clichés: "Elevate", "Seamless", "Unleash", "Next-Gen", "Game-changer", "Delve". Write plain, specific language.
|
|
23
|
+
|
|
24
|
+
## 3. Typographic Architecture
|
|
25
|
+
The interface must rely on extreme typographic contrast and premium font selection to establish an editorial feel.
|
|
26
|
+
- Primary Sans-Serif (Body, UI, Buttons): Use clean, geometric, or system-native fonts with character. Target: `font-family: 'SF Pro Display', 'Geist Sans', 'Helvetica Neue', 'Switzer', sans-serif`.
|
|
27
|
+
- Editorial Serif (Hero Headings & Quotes): Target: `font-family: 'Lyon Text', 'Newsreader', 'Playfair Display', 'Instrument Serif', serif`. Apply tight tracking (`letter-spacing: -0.02em` to `-0.04em`) and tight line-height (`1.1`).
|
|
28
|
+
- Monospace (Code, Keystrokes, Meta-data): Target: `font-family: 'Geist Mono', 'SF Mono', 'JetBrains Mono', monospace`.
|
|
29
|
+
- Text Colors: Body text must never be absolute black (`#000000`). Use off-black/charcoal (`#111111` or `#2F3437`) with a generous `line-height` of `1.6` for legibility. Secondary text should be muted gray (`#787774`).
|
|
30
|
+
|
|
31
|
+
## 4. Color Palette (Warm Monochrome + Spot Pastels)
|
|
32
|
+
Color is a scarce resource, utilized only for semantic meaning or subtle accents.
|
|
33
|
+
- Canvas / Background: Pure White `#FFFFFF` or Warm Bone/Off-White `#F7F6F3` / `#FBFBFA`.
|
|
34
|
+
- Primary Surface (Cards): `#FFFFFF` or `#F9F9F8`.
|
|
35
|
+
- Structural Borders / Dividers: Ultra-light gray `#EAEAEA` or `rgba(0,0,0,0.06)`.
|
|
36
|
+
- Accent Colors: Exclusively use highly desaturated, washed-out pastels for tags, inline code backgrounds, or subtle icon backgrounds.
|
|
37
|
+
- Pale Red: `#FDEBEC` (Text: `#9F2F2D`)
|
|
38
|
+
- Pale Blue: `#E1F3FE` (Text: `#1F6C9F`)
|
|
39
|
+
- Pale Green: `#EDF3EC` (Text: `#346538`)
|
|
40
|
+
- Pale Yellow: `#FBF3DB` (Text: `#956400`)
|
|
41
|
+
|
|
42
|
+
## 5. Component Specifications
|
|
43
|
+
- Bento Box Feature Grids:
|
|
44
|
+
- Utilize asymmetrical CSS Grid layouts.
|
|
45
|
+
- Cards must have exactly `border: 1px solid #EAEAEA`.
|
|
46
|
+
- Border-radius must be crisp: `8px` or `12px` maximum.
|
|
47
|
+
- Internal padding must be generous (e.g., `24px` to `40px`).
|
|
48
|
+
- Primary Call-To-Action (Buttons):
|
|
49
|
+
- Solid background `#111111`, text `#FFFFFF`.
|
|
50
|
+
- Slight border-radius (`4px` to `6px`). No box-shadow.
|
|
51
|
+
- Hover state should be a subtle color shift to `#333333` or a micro-scale `transform: scale(0.98)`.
|
|
52
|
+
- Tags & Status Badges:
|
|
53
|
+
- Pill-shaped (`border-radius: 9999px`), very small typography (`text-xs`), uppercase with wide tracking (`letter-spacing: 0.05em`).
|
|
54
|
+
- Background must use the defined Muted Pastels.
|
|
55
|
+
- Accordions (FAQ):
|
|
56
|
+
- Strip all container boxes. Separate items only with a `border-bottom: 1px solid #EAEAEA`.
|
|
57
|
+
- Use a clean, sharp `+` and `-` icon for the toggle state.
|
|
58
|
+
- Keystroke Micro-UIs:
|
|
59
|
+
- Render shortcuts as physical keys using `<kbd>` tags: `border: 1px solid #EAEAEA`, `border-radius: 4px`, `background: #F7F6F3`, using the Monospace font.
|
|
60
|
+
- Faux-OS Window Chrome:
|
|
61
|
+
- When mocking up software, wrap it in a minimalist container with a white top bar containing three small, light gray circles (replicating macOS window controls).
|
|
62
|
+
|
|
63
|
+
## 6. Iconography & Imagery Directives
|
|
64
|
+
- System Icons: Use "Phosphor Icons (Bold or Fill weights)" or "Radix UI Icons" for a technical, slightly thicker-stroke aesthetic. Standardize stroke width across all icons.
|
|
65
|
+
- Illustrations: Monochromatic, rough continuous-line ink sketches on a white background, featuring a single offset geometric shape filled with a muted pastel color.
|
|
66
|
+
- Photography: Use high-quality, desaturated images with a warm tone. Apply subtle overlays (`opacity: 0.04` warm grain) to blend photos into the monochrome palette. Never use oversaturated stock photos. Use reliable placeholders like `https://picsum.photos/seed/{context}/1200/800` when real assets are unavailable.
|
|
67
|
+
- Hero & Section Backgrounds: Sections should not feel empty and flat. Use subtle full-width background imagery at very low opacity, soft radial light spots (`radial-gradient` with warm tones at `opacity: 0.03`), or minimal geometric line patterns to add depth without breaking the clean aesthetic.
|
|
68
|
+
|
|
69
|
+
## 7. Subtle Motion & Micro-Animations
|
|
70
|
+
Motion should feel invisible — present but never distracting. The goal is quiet sophistication, not spectacle.
|
|
71
|
+
- Scroll Entry: Elements fade in gently as they enter the viewport. Use `translateY(12px)` + `opacity: 0` resolving over `600ms` with `cubic-bezier(0.16, 1, 0.3, 1)`. Use `IntersectionObserver`, never `window.addEventListener('scroll')`.
|
|
72
|
+
- Hover States: Cards lift with an ultra-subtle shadow shift (`box-shadow` transitioning from `0 0 0` to `0 2px 8px rgba(0,0,0,0.04)` over `200ms`). Buttons respond with `scale(0.98)` on `:active`.
|
|
73
|
+
- Staggered Reveals: Lists and grid items enter with a cascade delay (`animation-delay: calc(var(--index) * 80ms)`). Never mount everything at once.
|
|
74
|
+
- Background Ambient Motion: Optional. A single, very slow-moving radial gradient blob (`animation-duration: 20s+`, `opacity: 0.02-0.04`) drifting behind hero sections. Must be applied to a `position: fixed; pointer-events: none` layer. Never on scrolling containers.
|
|
75
|
+
- Performance: Animate exclusively via `transform` and `opacity`. No layout-triggering properties (`top`, `left`, `width`, `height`). Use `will-change: transform` sparingly and only on actively animating elements.
|
|
76
|
+
|
|
77
|
+
## 8. Execution Protocol
|
|
78
|
+
When tasked with writing frontend code (HTML, React, Tailwind, Vue) or designing a layout:
|
|
79
|
+
1. Establish the macro-whitespace first. Use massive vertical padding between sections (e.g., `py-24` or `py-32` in Tailwind).
|
|
80
|
+
2. Constrain the main typography content width to `max-w-4xl` or `max-w-5xl`.
|
|
81
|
+
3. Apply the custom typographic hierarchy and monochromatic color variables immediately.
|
|
82
|
+
4. Ensure every card, divider, and border adheres strictly to the `1px solid #EAEAEA` rule.
|
|
83
|
+
5. Add scroll-entry animations to all major content blocks.
|
|
84
|
+
6. Ensure sections have visual depth through imagery, ambient gradients, or subtle textures — no empty flat backgrounds.
|
|
85
|
+
7. Provide code that reflects this high-end, uncluttered, editorial aesthetic natively without requiring manual adjustments.
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: motion-design-taste
|
|
3
|
+
description: Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# CORE DIRECTIVE: AWWWARDS-LEVEL DESIGN ENGINEERING
|
|
7
|
+
You are an elite, award-winning frontend design engineer. Standard LLMs possess severe statistical biases: they generate massive 6-line wrapped headings by using narrow containers, leave ugly empty gaps in bento grids, use cheap meta-labels ("QUESTION 05", "SECTION 01"), output invisible button text, and endlessly repeat the same Left/Right layouts.
|
|
8
|
+
|
|
9
|
+
Your goal is to aggressively break these defaults. Your outputs must be highly creative, perfectly spaced, motion-rich (GSAP), mathematically flawless in grid execution, and heavily rely on varied, high-end assets.
|
|
10
|
+
|
|
11
|
+
DO NOT USE EMOJIS IN YOUR CODE, COMMENTS, OR OUTPUT. Maintain strictly professional formatting.
|
|
12
|
+
|
|
13
|
+
## 1. PYTHON-DRIVEN TRUE RANDOMIZATION (BREAKING THE LOOP)
|
|
14
|
+
LLMs are inherently lazy and always pick the first layout option. To prevent this, you MUST simulate a Python script execution in your `<design_plan>` before writing any UI code.
|
|
15
|
+
Use a deterministic seed (e.g., character count of the user prompt modulo math) to simulate `random.choice()` and strictly select:
|
|
16
|
+
- 1 Hero Architecture (from Section 3)
|
|
17
|
+
- 1 Typography Stack (Satoshi, Cabinet Grotesk, Outfit, or Geist. NEVER Inter)
|
|
18
|
+
- 3 Unique Component Architectures (from Section 6)
|
|
19
|
+
- 2 Advanced GSAP Paradigms (from Section 5)
|
|
20
|
+
You are forbidden from defaulting to the same UI twice. You must follow the exact output of your simulated Python randomization.
|
|
21
|
+
|
|
22
|
+
## 2. AIDA STRUCTURE & SPACING
|
|
23
|
+
Every page MUST begin with a highly creative, premium Navigation Bar (e.g., floating glass pill, or minimal split nav).
|
|
24
|
+
The rest of the page MUST follow the AIDA framework:
|
|
25
|
+
- **Attention (Hero):** Cinematic, clean, wide layout.
|
|
26
|
+
- **Interest (Features/Bento):** High-density, mathematically perfect grid or interactive typographic components.
|
|
27
|
+
- **Desire (GSAP Scroll/Media):** Pinned sections, horizontal scroll, or text-reveals.
|
|
28
|
+
- **Action (Footer/Pricing):** Massive, high-contrast CTA and clean footer links.
|
|
29
|
+
**SPACING RULE:** Add huge vertical padding between all major sections (e.g., `py-32 md:py-48`). Sections must feel like distinct, cinematic chapters. Do not cramp elements together.
|
|
30
|
+
|
|
31
|
+
## 3. HERO ARCHITECTURE & THE 2-LINE IRON RULE
|
|
32
|
+
The Hero must breathe. It must NOT be a narrow, 6-line text wall.
|
|
33
|
+
- **The Container Width Fix:** You MUST use ultra-wide containers for the H1 (e.g., `max-w-5xl`, `max-w-6xl`, `w-full`). Allow the words to flow horizontally.
|
|
34
|
+
- **The Line Limit:** The H1 MUST NEVER exceed 2 to 3 lines. 4, 5, or 6 lines is a catastrophic failure. Make the font size smaller (`clamp(3rem, 5vw, 5.5rem)`) and the container wider to ensure this.
|
|
35
|
+
- **Hero Layout Options (Randomly Assigned via Python):**
|
|
36
|
+
1. *Cinematic Center (Highly Preferred):* Text perfectly centered, massive width. Below the text, exactly two high-contrast CTAs. Below the CTAs or behind everything, a stunning, full-bleed background image with a dark radial wash.
|
|
37
|
+
2. *Artistic Asymmetry:* Text offset to the left, with an artistic floating image overlapping the text from the bottom right.
|
|
38
|
+
3. *Editorial Split:* Text left, image right, but with massive negative space.
|
|
39
|
+
- **Button Contrast:** Buttons must be perfectly legible. Dark background = white text. Light background = dark text. Invisible text is a failure.
|
|
40
|
+
- **BANNED IN HERO:** Do NOT use arbitrary floating stamp/badge icons on the text. Do NOT use pill-tags under the hero. Do NOT place raw data/stats in the hero.
|
|
41
|
+
|
|
42
|
+
## 4. THE GAPLESS BENTO GRID
|
|
43
|
+
- **Zero Empty Space in Grids:** LLMs notoriously leave blank, dead cells in CSS grids. You MUST use Tailwind's `grid-flow-dense` (`grid-auto-flow: dense`) on every Bento Grid. You must mathematically verify that your `col-span` and `row-span` values interlock perfectly. No grid shall have a missing corner or empty void.
|
|
44
|
+
- **Card Restraint:** Do not use too many cards. 3 to 5 highly intentional, beautifully styled cards are better than 8 messy ones. Fill them with a mix of large imagery, dense typography, or CSS effects.
|
|
45
|
+
|
|
46
|
+
## 5. ADVANCED GSAP MOTION & HOVER PHYSICS
|
|
47
|
+
Static interfaces are strictly forbidden. You must write real GSAP (`@gsap/react`, `ScrollTrigger`).
|
|
48
|
+
- **Hover Physics:** Every clickable card and image must react. Use `group-hover:scale-105 transition-transform duration-700 ease-out` inside `overflow-hidden` containers.
|
|
49
|
+
- **Scroll Pinning (GSAP Split):** Pin a section title on the left (`ScrollTrigger pin: true`) while a gallery of elements scrolls upwards on the right side.
|
|
50
|
+
- **Image Scale & Fade Scroll:** Images must start small (`scale: 0.8`). As they scroll into view, they grow to `scale: 1.0`. As they scroll out of view, they smoothly darken and fade out (`opacity: 0.2`).
|
|
51
|
+
- **Scrubbing Text Reveals:** Opacity of central paragraph words starts at 0.1 and scrubs to 1.0 sequentially as the user scrolls.
|
|
52
|
+
- **Card Stacking:** Cards overlap and stack on top of each other dynamically from the bottom as the user scrolls down.
|
|
53
|
+
|
|
54
|
+
## 6. COMPONENT ARSENAL & CREATIVITY
|
|
55
|
+
Select components from this arsenal based on your randomization:
|
|
56
|
+
- **Inline Typography Images:** Embed small, pill-shaped images directly INSIDE massive headings. Example: `I shape <span className="inline-block w-24 h-10 rounded-full align-middle bg-cover bg-center mx-2" style={{backgroundImage: 'url(...)'}}></span> digital spaces.`
|
|
57
|
+
- **Horizontal Accordions:** Vertical slices that expand horizontally on hover to reveal content and imagery.
|
|
58
|
+
- **Infinite Marquee (Trusted Partners):** Smooth, continuously scrolling rows of authentic `@phosphor-icons/react` or large typography.
|
|
59
|
+
- **Feedback/Testimonial Carousel:** Clean, overlapping portrait images next to minimalist typography quotes, controlled by subtle arrows.
|
|
60
|
+
|
|
61
|
+
## 7. CONTENT, ASSETS & STRICT BANS
|
|
62
|
+
- **The Meta-Label Ban:** BANNED FOREVER are labels like "SECTION 01", "SECTION 04", "QUESTION 05", "ABOUT US". Remove them entirely. They look cheap and unprofessional.
|
|
63
|
+
- **Image Context & Style:** Use `https://picsum.photos/seed/{keyword}/1920/1080` and match the keyword to the vibe. Apply sophisticated CSS filters (`grayscale`, `mix-blend-luminosity`, `opacity-90`, `contrast-125`) so they do not look like boring stock photos.
|
|
64
|
+
- **Creative Backgrounds:** Inject subtle, professional ambient design. Use deep radial blurs, grainy mesh gradients, or shifting dark overlays. Avoid flat, boring colors.
|
|
65
|
+
- **Horizontal Scroll Bug:** Wrap the entire page in `<main className="overflow-x-hidden w-full max-w-full">` to absolutely prevent horizontal scrollbars caused by off-screen animations.
|
|
66
|
+
|
|
67
|
+
## 8. MANDATORY PRE-FLIGHT <design_plan>
|
|
68
|
+
Before writing ANY React/UI code, you MUST output a `<design_plan>` block containing:
|
|
69
|
+
1. **Python RNG Execution:** Write a 3-line mock Python output showing the deterministic selection of your Hero Layout, Component Arsenal, GSAP animations, and Fonts based on the prompt's character count.
|
|
70
|
+
2. **AIDA Check:** Confirm the page contains Navigation, Attention (Hero), Interest (Bento), Desire (GSAP), Action (Footer).
|
|
71
|
+
3. **Hero Math Verification:** Explicitly state the `max-w` class you are applying to the H1 to GUARANTEE it will flow horizontally in 2-3 lines. Confirm NO stamp icons or spam tags exist.
|
|
72
|
+
4. **Bento Density Verification:** Prove mathematically that your grid columns and rows leave zero empty spaces and `grid-flow-dense` is applied.
|
|
73
|
+
5. **Label Sweep & Button Check:** Confirm no cheap meta-labels ("QUESTION 05") exist, and button text contrast is perfect.
|
|
74
|
+
Only output the UI code after this rigorous verification is complete.
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: playwright-testing
|
|
3
|
+
description: Test local and remote web interfaces with an isolated Playwright MCP runtime, collecting browser evidence across representative desktop and mobile viewports.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Playwright Testing
|
|
7
|
+
|
|
8
|
+
Use this skill for real-browser verification of web applications, responsive layouts, accessibility behavior, console output, and network requests.
|
|
9
|
+
|
|
10
|
+
## Workflow
|
|
11
|
+
|
|
12
|
+
1. Read [references/runtime.md](references/runtime.md) before enabling the runtime.
|
|
13
|
+
2. Start the target application only when the user has authorized it and no suitable server is already running.
|
|
14
|
+
3. Use role, label, text, or test-id locators. Avoid brittle coordinates and arbitrary sleep calls.
|
|
15
|
+
4. Test the actual interaction, then capture supporting screenshots and browser diagnostics.
|
|
16
|
+
5. Check representative desktop and mobile sizes for overflow, overlap, clipped text, blank canvases, and failed assets.
|
|
17
|
+
6. Treat a successful command as evidence only for that command. Inspect the resulting page state before reporting success.
|
|
18
|
+
|
|
19
|
+
Never reuse or expose a user's browser credentials unless the task explicitly requires that authenticated session.
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# Playwright Runtime Contract
|
|
2
|
+
|
|
3
|
+
- Tested MCP package: `@playwright/mcp` 0.0.78.
|
|
4
|
+
- The standard descriptor runs it in headless, isolated mode and is disabled until explicit user opt-in.
|
|
5
|
+
- The runtime is external and is not bundled with BLUN Code. Enabling it may require a package and browser download.
|
|
6
|
+
- Keep existing user configuration authoritative and do not start a second equivalent MCP server.
|
|
7
|
+
- Add persistent profiles, visible windows, or broader filesystem access only for a named test that requires them.
|
|
@@ -0,0 +1,148 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: premortem
|
|
3
|
+
description: "Run a premortem on any plan, launch, product, hire, strategy, or decision. Assume it failed 6 months from now and work backward to find why. Produce a revised plan with blind spots exposed. Mandatory triggers: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. Strong triggers: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do not trigger on simple feedback requests, factual questions, or LLM Council requests. Do trigger when someone has a plan or commitment where the cost of being wrong is high."
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Premortem
|
|
7
|
+
|
|
8
|
+
A premortem is the opposite of a postmortem. Instead of figuring out what went wrong after something fails, imagine the plan has already failed and work backward to identify why before the work starts.
|
|
9
|
+
|
|
10
|
+
The core value is prospective hindsight: when the frame is "this already failed, tell me why", the analysis becomes more specific, creative, and honest than a polite "what could go wrong?" review.
|
|
11
|
+
|
|
12
|
+
## When To Run
|
|
13
|
+
|
|
14
|
+
Good premortem targets:
|
|
15
|
+
|
|
16
|
+
- A product or feature about to be built.
|
|
17
|
+
- A launch plan with money or reputation on the line.
|
|
18
|
+
- A pricing change or business model shift.
|
|
19
|
+
- A hire or partnership under evaluation.
|
|
20
|
+
- A strategy, positioning pivot, or major commitment.
|
|
21
|
+
- Any decision where the cost of being wrong is high.
|
|
22
|
+
|
|
23
|
+
Bad premortem targets:
|
|
24
|
+
|
|
25
|
+
- Vague ideas with no concrete plan yet. Help the user plan first, then premortem.
|
|
26
|
+
- Questions with one right answer.
|
|
27
|
+
- Requests for creative feedback on a draft.
|
|
28
|
+
- Decisions that are already made and irreversible.
|
|
29
|
+
|
|
30
|
+
## Context Gathering
|
|
31
|
+
|
|
32
|
+
Before running the premortem, quickly gather enough context.
|
|
33
|
+
|
|
34
|
+
Scan for existing context:
|
|
35
|
+
|
|
36
|
+
- Current conversation.
|
|
37
|
+
- Workspace files that may contain plans, briefs, product context, or constraints.
|
|
38
|
+
- Files explicitly referenced or attached by the user.
|
|
39
|
+
|
|
40
|
+
Do not spend more than about 30 seconds scanning. You need enough to answer:
|
|
41
|
+
|
|
42
|
+
1. What is the plan, launch, product, hire, strategy, or decision?
|
|
43
|
+
2. Who is it for or who does it affect?
|
|
44
|
+
3. What does success look like?
|
|
45
|
+
|
|
46
|
+
If one of those is missing, ask the most important missing question. Ask one question at a time. If you can infer the answer from context, infer it instead of interrupting.
|
|
47
|
+
|
|
48
|
+
## Premortem Workflow
|
|
49
|
+
|
|
50
|
+
### 1. Set The Frame
|
|
51
|
+
|
|
52
|
+
State the frame explicitly:
|
|
53
|
+
|
|
54
|
+
"It is 6 months from now. This plan has failed. We are looking back to understand what went wrong."
|
|
55
|
+
|
|
56
|
+
This frame matters. It forces honest failure analysis instead of agreeable plan validation.
|
|
57
|
+
|
|
58
|
+
### 2. Generate Failure Reasons
|
|
59
|
+
|
|
60
|
+
Produce a raw premortem:
|
|
61
|
+
|
|
62
|
+
- Generate every genuine reason the plan could have failed.
|
|
63
|
+
- Be specific to the actual plan and context.
|
|
64
|
+
- Do not pad with weak generic risks.
|
|
65
|
+
- Do not stop early if there are more real failure modes.
|
|
66
|
+
- Each reason should be 1-2 sentences.
|
|
67
|
+
|
|
68
|
+
### 3. Deep Dive Each Failure Reason
|
|
69
|
+
|
|
70
|
+
For each failure reason, run a separate deep dive. If sub-agent tools are available, spawn one sub-agent per failure reason in parallel. If sub-agent tools are not available, simulate the same structure internally while keeping the outputs distinct.
|
|
71
|
+
|
|
72
|
+
Deep-dive prompt:
|
|
73
|
+
|
|
74
|
+
```text
|
|
75
|
+
You are an investigator in a premortem analysis. You have been assigned one specific failure reason to analyze in depth.
|
|
76
|
+
|
|
77
|
+
The plan:
|
|
78
|
+
---
|
|
79
|
+
[full context: what it is, who it is for, what success looks like, plus relevant workspace context]
|
|
80
|
+
---
|
|
81
|
+
|
|
82
|
+
PREMORTEM FRAME: It is 6 months from now. This plan has failed.
|
|
83
|
+
|
|
84
|
+
YOUR ASSIGNED FAILURE REASON:
|
|
85
|
+
[failure reason]
|
|
86
|
+
|
|
87
|
+
Analyze this one failure.
|
|
88
|
+
|
|
89
|
+
Output:
|
|
90
|
+
1. THE FAILURE STORY: 2-3 paragraphs explaining how this failure played out. Use concrete details from the plan.
|
|
91
|
+
2. THE UNDERLYING ASSUMPTION: The one assumption that made this failure possible.
|
|
92
|
+
3. EARLY WARNING SIGNS: 1-2 observable signals that this failure is starting.
|
|
93
|
+
|
|
94
|
+
Keep it under 300 words. Be direct. Do not hedge or sugarcoat.
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
### 4. Synthesize
|
|
98
|
+
|
|
99
|
+
Produce:
|
|
100
|
+
|
|
101
|
+
1. The Most Likely Failure: Which scenario is most probable and why.
|
|
102
|
+
2. The Most Dangerous Failure: Which scenario would cause the most damage.
|
|
103
|
+
3. The Hidden Assumption: The biggest assumption the user has not questioned.
|
|
104
|
+
4. The Revised Plan: Concrete changes that map to the failure scenarios.
|
|
105
|
+
5. The Pre-Launch Checklist: 3-5 specific tests, safeguards, or verification steps.
|
|
106
|
+
|
|
107
|
+
## Output Files
|
|
108
|
+
|
|
109
|
+
When useful for the task, create two files in the workspace:
|
|
110
|
+
|
|
111
|
+
- `premortem-report-[timestamp].html`
|
|
112
|
+
- `premortem-transcript-[timestamp].md`
|
|
113
|
+
|
|
114
|
+
The HTML report should be self-contained with inline CSS.
|
|
115
|
+
|
|
116
|
+
Design direction:
|
|
117
|
+
|
|
118
|
+
- Dark background, clean typography, easy to scan.
|
|
119
|
+
- Synthesis at the top.
|
|
120
|
+
- One card per failure reason.
|
|
121
|
+
- Severity and likelihood indicators.
|
|
122
|
+
- A grid showing the deep-dive findings.
|
|
123
|
+
- Footer with timestamp and what was premortemed.
|
|
124
|
+
|
|
125
|
+
The transcript should include:
|
|
126
|
+
|
|
127
|
+
- Context gathered.
|
|
128
|
+
- Raw failure reasons.
|
|
129
|
+
- All deep dives.
|
|
130
|
+
- Full synthesis.
|
|
131
|
+
|
|
132
|
+
After generating files, provide a concise chat summary:
|
|
133
|
+
|
|
134
|
+
- Most likely failure.
|
|
135
|
+
- Hidden assumption.
|
|
136
|
+
- Single most important revision.
|
|
137
|
+
|
|
138
|
+
Keep the chat summary to three sentences when the report exists.
|
|
139
|
+
|
|
140
|
+
## Quality Rules
|
|
141
|
+
|
|
142
|
+
- Always use the "this already failed" frame.
|
|
143
|
+
- Be comprehensive but not padded.
|
|
144
|
+
- Make every failure specific to the user's plan.
|
|
145
|
+
- Do not sugarcoat.
|
|
146
|
+
- Revised-plan items must be concrete and actionable.
|
|
147
|
+
- If context is insufficient, ask one focused question before running.
|
|
148
|
+
- This is not the LLM Council. If the user wants multiple current perspectives rather than future failure analysis, suggest a council-style review instead.
|
|
@@ -0,0 +1,178 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: redesign-existing-projects
|
|
3
|
+
description: Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Redesign Skill
|
|
7
|
+
|
|
8
|
+
## How This Works
|
|
9
|
+
|
|
10
|
+
When applied to an existing project, follow this sequence:
|
|
11
|
+
|
|
12
|
+
1. **Scan** — Read the codebase. Identify the framework, styling method (Tailwind, vanilla CSS, styled-components, etc.), and current design patterns.
|
|
13
|
+
2. **Diagnose** — Run through the audit below. List every generic pattern, weak point, and missing state you find.
|
|
14
|
+
3. **Fix** — Apply targeted upgrades working with the existing stack. Do not rewrite from scratch. Improve what's there.
|
|
15
|
+
|
|
16
|
+
## Design Audit
|
|
17
|
+
|
|
18
|
+
### Typography
|
|
19
|
+
|
|
20
|
+
Check for these problems and fix them:
|
|
21
|
+
|
|
22
|
+
- **Browser default fonts or Inter everywhere.** Replace with a font that has character. Good options: `Geist`, `Outfit`, `Cabinet Grotesk`, `Satoshi`. For editorial/creative projects, pair a serif header with a sans-serif body.
|
|
23
|
+
- **Headlines lack presence.** Increase size for display text, tighten letter-spacing, reduce line-height. Headlines should feel heavy and intentional.
|
|
24
|
+
- **Body text too wide.** Limit paragraph width to roughly 65 characters. Increase line-height for readability.
|
|
25
|
+
- **Only Regular (400) and Bold (700) weights used.** Introduce Medium (500) and SemiBold (600) for more subtle hierarchy.
|
|
26
|
+
- **Numbers in proportional font.** Use a monospace font or enable tabular figures (`font-variant-numeric: tabular-nums`) for data-heavy interfaces.
|
|
27
|
+
- **Missing letter-spacing adjustments.** Use negative tracking for large headers, positive tracking for small caps or labels.
|
|
28
|
+
- **All-caps subheaders everywhere.** Try lowercase italics, sentence case, or small-caps instead.
|
|
29
|
+
- **Orphaned words.** Single words sitting alone on the last line. Fix with `text-wrap: balance` or `text-wrap: pretty`.
|
|
30
|
+
|
|
31
|
+
### Color and Surfaces
|
|
32
|
+
|
|
33
|
+
- **Pure `#000000` background.** Replace with off-black, dark charcoal, or tinted dark (`#0a0a0a`, `#121212`, or a dark navy).
|
|
34
|
+
- **Oversaturated accent colors.** Keep saturation below 80%. Desaturate accents so they blend with neutrals instead of screaming.
|
|
35
|
+
- **More than one accent color.** Pick one. Remove the rest. Consistency beats variety.
|
|
36
|
+
- **Mixing warm and cool grays.** Stick to one gray family. Tint all grays with a consistent hue (warm or cool, not both).
|
|
37
|
+
- **Purple/blue "AI gradient" aesthetic.** This is the most common AI design fingerprint. Replace with neutral bases and a single, considered accent.
|
|
38
|
+
- **Generic `box-shadow`.** Tint shadows to match the background hue. Use colored shadows (e.g., dark blue shadow on a blue background) instead of pure black at low opacity.
|
|
39
|
+
- **Flat design with zero texture.** Add subtle noise, grain, or micro-patterns to backgrounds. Pure flat vectors feel sterile.
|
|
40
|
+
- **Perfectly even gradients.** Break the uniformity with radial gradients, noise overlays, or mesh gradients instead of standard linear 45-degree fades.
|
|
41
|
+
- **Inconsistent lighting direction.** Audit all shadows to ensure they suggest a single, consistent light source.
|
|
42
|
+
- **Random dark sections in a light mode page (or vice versa).** A single dark-background section breaking an otherwise light page looks like a copy-paste accident. Either commit to a full dark mode or keep a consistent background tone throughout. If contrast is needed, use a slightly darker shade of the same palette — not a sudden jump to `#111` in the middle of a cream page.
|
|
43
|
+
- **Empty, flat sections with no visual depth.** Sections that are just text on a plain background feel unfinished. Add high-quality background imagery (blurred, overlaid, or masked), subtle patterns, or ambient gradients. Use reliable placeholder sources like `https://picsum.photos/seed/{name}/1920/1080` when real assets are not available. Experiment with background images behind hero sections, feature blocks, or CTAs — even a subtle full-width photo at low opacity adds presence.
|
|
44
|
+
|
|
45
|
+
### Layout
|
|
46
|
+
|
|
47
|
+
- **Everything centered and symmetrical.** Break symmetry with offset margins, mixed aspect ratios, or left-aligned headers over centered content.
|
|
48
|
+
- **Three equal card columns as feature row.** This is the most generic AI layout. Replace with a 2-column zig-zag, asymmetric grid, horizontal scroll, or masonry layout.
|
|
49
|
+
- **Using `height: 100vh` for full-screen sections.** Replace with `min-height: 100dvh` to prevent layout jumping on mobile browsers (iOS Safari viewport bug).
|
|
50
|
+
- **Complex flexbox percentage math.** Replace with CSS Grid for reliable multi-column structures.
|
|
51
|
+
- **No max-width container.** Add a container constraint (around 1200-1440px) with auto margins so content doesn't stretch edge-to-edge on wide screens.
|
|
52
|
+
- **Cards of equal height forced by flexbox.** Allow variable heights or use masonry when content varies in length.
|
|
53
|
+
- **Uniform border-radius on everything.** Vary the radius: tighter on inner elements, softer on containers.
|
|
54
|
+
- **No overlap or depth.** Elements sit flat next to each other. Use negative margins to create layering and visual depth.
|
|
55
|
+
- **Symmetrical vertical padding.** Top and bottom padding are always identical. Adjust optically — bottom padding often needs to be slightly larger.
|
|
56
|
+
- **Dashboard always has a left sidebar.** Try top navigation, a floating command menu, or a collapsible panel instead.
|
|
57
|
+
- **Missing whitespace.** Double the spacing. Let the design breathe. Dense layouts work for data dashboards, not for marketing pages.
|
|
58
|
+
- **Buttons not bottom-aligned in card groups.** When cards have different content lengths, CTAs end up at random heights. Pin buttons to the bottom of each card so they form a clean horizontal line regardless of content above.
|
|
59
|
+
- **Feature lists starting at different vertical positions.** In pricing tables or comparison cards, the list of features should start at the same Y position across all columns. Use consistent spacing above the list or fixed-height title/price blocks.
|
|
60
|
+
- **Inconsistent vertical rhythm in side-by-side elements.** When placing cards, columns, or panels next to each other, align shared elements (titles, descriptions, prices, buttons) across all items. Misaligned baselines make the layout look broken.
|
|
61
|
+
- **Mathematical alignment that looks optically wrong.** Centering by the math doesn't always look centered to the eye. Icons next to text, play buttons in circles, or text in buttons often need 1-2px optical adjustments to feel right.
|
|
62
|
+
|
|
63
|
+
### Interactivity and States
|
|
64
|
+
|
|
65
|
+
- **No hover states on buttons.** Add background shift, slight scale, or translate on hover.
|
|
66
|
+
- **No active/pressed feedback.** Add a subtle `scale(0.98)` or `translateY(1px)` on press to simulate a physical click.
|
|
67
|
+
- **Instant transitions with zero duration.** Add smooth transitions (200-300ms) to all interactive elements.
|
|
68
|
+
- **Missing focus ring.** Ensure visible focus indicators for keyboard navigation. This is an accessibility requirement, not optional.
|
|
69
|
+
- **No loading states.** Replace generic circular spinners with skeleton loaders that match the layout shape.
|
|
70
|
+
- **No empty states.** An empty dashboard showing nothing is a missed opportunity. Design a composed "getting started" view.
|
|
71
|
+
- **No error states.** Add clear, inline error messages for forms. Do not use `window.alert()`.
|
|
72
|
+
- **Dead links.** Buttons that link to `#`. Either link to real destinations or visually disable them.
|
|
73
|
+
- **No indication of current page in navigation.** Style the active nav link differently so users know where they are.
|
|
74
|
+
- **Scroll jumping.** Anchor clicks jump instantly. Add `scroll-behavior: smooth`.
|
|
75
|
+
- **Animations using `top`, `left`, `width`, `height`.** Switch to `transform` and `opacity` for GPU-accelerated, smooth animation.
|
|
76
|
+
|
|
77
|
+
### Content
|
|
78
|
+
|
|
79
|
+
- **Generic names like "John Doe" or "Jane Smith".** Use diverse, realistic-sounding names.
|
|
80
|
+
- **Fake round numbers like `99.99%`, `50%`, `$100.00`.** Use organic, messy data: `47.2%`, `$99.00`, `+1 (312) 847-1928`.
|
|
81
|
+
- **Placeholder company names like "Acme Corp", "Nexus", "SmartFlow".** Invent contextual, believable brand names.
|
|
82
|
+
- **AI copywriting cliches.** Never use "Elevate", "Seamless", "Unleash", "Next-Gen", "Game-changer", "Delve", "Tapestry", or "In the world of...". Write plain, specific language.
|
|
83
|
+
- **Exclamation marks in success messages.** Remove them. Be confident, not loud.
|
|
84
|
+
- **"Oops!" error messages.** Be direct: "Connection failed. Please try again."
|
|
85
|
+
- **Passive voice.** Use active voice: "We couldn't save your changes" instead of "Mistakes were made."
|
|
86
|
+
- **All blog post dates identical.** Randomize dates to appear real.
|
|
87
|
+
- **Same avatar image for multiple users.** Use unique assets for every distinct person.
|
|
88
|
+
- **Lorem Ipsum.** Never use placeholder latin text. Write real draft copy.
|
|
89
|
+
- **Title Case On Every Header.** Use sentence case instead.
|
|
90
|
+
|
|
91
|
+
### Component Patterns
|
|
92
|
+
|
|
93
|
+
- **Generic card look (border + shadow + white background).** Remove the border, or use only background color, or use only spacing. Cards should exist only when elevation communicates hierarchy.
|
|
94
|
+
- **Always one filled button + one ghost button.** Add text links or tertiary styles to reduce visual noise.
|
|
95
|
+
- **Pill-shaped "New" and "Beta" badges.** Try square badges, flags, or plain text labels.
|
|
96
|
+
- **Accordion FAQ sections.** Use a side-by-side list, searchable help, or inline progressive disclosure.
|
|
97
|
+
- **3-card carousel testimonials with dots.** Replace with a masonry wall, embedded social posts, or a single rotating quote.
|
|
98
|
+
- **Pricing table with 3 towers.** Highlight the recommended tier with color and emphasis, not just extra height.
|
|
99
|
+
- **Modals for everything.** Use inline editing, slide-over panels, or expandable sections instead of popups for simple actions.
|
|
100
|
+
- **Avatar circles exclusively.** Try squircles or rounded squares for a less generic look.
|
|
101
|
+
- **Light/dark toggle always a sun/moon switch.** Use a dropdown, system preference detection, or integrate it into settings.
|
|
102
|
+
- **Footer link farm with 4 columns.** Simplify. Focus on main navigational paths and legally required links.
|
|
103
|
+
|
|
104
|
+
### Iconography
|
|
105
|
+
|
|
106
|
+
- **Lucide or Feather icons exclusively.** These are the "default" AI icon choice. Use Phosphor, Heroicons, or a custom set for differentiation.
|
|
107
|
+
- **Rocketship for "Launch", shield for "Security".** Replace cliche metaphors with less obvious icons (bolt, fingerprint, spark, vault).
|
|
108
|
+
- **Inconsistent stroke widths across icons.** Audit all icons and standardize to one stroke weight.
|
|
109
|
+
- **Missing favicon.** Always include a branded favicon.
|
|
110
|
+
- **Stock "diverse team" photos.** Use real team photos, candid shots, or a consistent illustration style instead of uncanny stock imagery.
|
|
111
|
+
|
|
112
|
+
### Code Quality
|
|
113
|
+
|
|
114
|
+
- **Div soup.** Use semantic HTML: `<nav>`, `<main>`, `<article>`, `<aside>`, `<section>`.
|
|
115
|
+
- **Inline styles mixed with CSS classes.** Move all styling to the project's styling system.
|
|
116
|
+
- **Hardcoded pixel widths.** Use relative units (`%`, `rem`, `em`, `max-width`) for flexible layouts.
|
|
117
|
+
- **Missing alt text on images.** Describe image content for screen readers. Never leave `alt=""` or `alt="image"` on meaningful images.
|
|
118
|
+
- **Arbitrary z-index values like `9999`.** Establish a clean z-index scale in the theme/variables.
|
|
119
|
+
- **Commented-out dead code.** Remove all debug artifacts before shipping.
|
|
120
|
+
- **Import hallucinations.** Check that every import actually exists in `package.json` or the project dependencies.
|
|
121
|
+
- **Missing meta tags.** Add proper `<title>`, `description`, `og:image`, and social sharing meta tags.
|
|
122
|
+
|
|
123
|
+
### Strategic Omissions (What AI Typically Forgets)
|
|
124
|
+
|
|
125
|
+
- **No legal links.** Add privacy policy and terms of service links in the footer.
|
|
126
|
+
- **No "back" navigation.** Dead ends in user flows. Every page needs a way back.
|
|
127
|
+
- **No custom 404 page.** Design a helpful, branded "page not found" experience.
|
|
128
|
+
- **No form validation.** Add client-side validation for emails, required fields, and format checks.
|
|
129
|
+
- **No "skip to content" link.** Essential for keyboard users. Add a hidden skip-link.
|
|
130
|
+
- **No cookie consent.** If required by jurisdiction, add a compliant consent banner.
|
|
131
|
+
|
|
132
|
+
## Upgrade Techniques
|
|
133
|
+
|
|
134
|
+
When upgrading a project, pull from these high-impact techniques to replace generic patterns:
|
|
135
|
+
|
|
136
|
+
### Typography Upgrades
|
|
137
|
+
- **Variable font animation.** Interpolate weight or width on scroll or hover for text that feels alive.
|
|
138
|
+
- **Outlined-to-fill transitions.** Text starts as a stroke outline and fills with color on scroll entry or interaction.
|
|
139
|
+
- **Text mask reveals.** Large typography acting as a window to video or animated imagery behind it.
|
|
140
|
+
|
|
141
|
+
### Layout Upgrades
|
|
142
|
+
- **Broken grid / asymmetry.** Elements that deliberately ignore column structure — overlapping, bleeding off-screen, or offset with calculated randomness.
|
|
143
|
+
- **Whitespace maximization.** Aggressive use of negative space to force focus on a single element.
|
|
144
|
+
- **Parallax card stacks.** Sections that stick and physically stack over each other during scroll.
|
|
145
|
+
- **Split-screen scroll.** Two halves of the screen sliding in opposite directions.
|
|
146
|
+
|
|
147
|
+
### Motion Upgrades
|
|
148
|
+
- **Smooth scroll with inertia.** Decouple scrolling from browser defaults for a heavier, cinematic feel.
|
|
149
|
+
- **Staggered entry.** Elements cascade in with slight delays, combining Y-axis translation with opacity fade. Never mount everything at once.
|
|
150
|
+
- **Spring physics.** Replace linear easing with spring-based motion for a natural, weighty feel on all interactive elements.
|
|
151
|
+
- **Scroll-driven reveals.** Content entering through expanding masks, wipes, or draw-on SVG paths tied to scroll progress.
|
|
152
|
+
|
|
153
|
+
### Surface Upgrades
|
|
154
|
+
- **True glassmorphism.** Go beyond `backdrop-filter: blur`. Add a 1px inner border and a subtle inner shadow to simulate edge refraction.
|
|
155
|
+
- **Spotlight borders.** Card borders that illuminate dynamically under the cursor.
|
|
156
|
+
- **Grain and noise overlays.** A fixed, pointer-events-none overlay with subtle noise to break digital flatness.
|
|
157
|
+
- **Colored, tinted shadows.** Shadows that carry the hue of the background rather than using generic black.
|
|
158
|
+
|
|
159
|
+
## Fix Priority
|
|
160
|
+
|
|
161
|
+
Apply changes in this order for maximum visual impact with minimum risk:
|
|
162
|
+
|
|
163
|
+
1. **Font swap** — biggest instant improvement, lowest risk
|
|
164
|
+
2. **Color palette cleanup** — remove clashing or oversaturated colors
|
|
165
|
+
3. **Hover and active states** — makes the interface feel alive
|
|
166
|
+
4. **Layout and spacing** — proper grid, max-width, consistent padding
|
|
167
|
+
5. **Replace generic components** — swap cliche patterns for modern alternatives
|
|
168
|
+
6. **Add loading, empty, and error states** — makes it feel finished
|
|
169
|
+
7. **Polish typography scale and spacing** — the premium final touch
|
|
170
|
+
|
|
171
|
+
## Rules
|
|
172
|
+
|
|
173
|
+
- Work with the existing tech stack. Do not migrate frameworks or styling libraries.
|
|
174
|
+
- Do not break existing functionality. Test after every change.
|
|
175
|
+
- Before importing any new library, check the project's dependency file first.
|
|
176
|
+
- If the project uses Tailwind, check the version (v3 vs v4) before modifying config.
|
|
177
|
+
- If the project has no framework, use vanilla CSS.
|
|
178
|
+
- Keep changes reviewable and focused. Small, targeted improvements over big rewrites.
|