postcard-illustration
Hand-drawn editorial postcard illustration style. Fine black marker/pen ink linework over flat saturated gouache color fills with sharp edges, dense small repeated ink patterns on surfaces (rows of windows, shingle curves, hatching, stippling), subtle paper-grain background texture, tiny scattered white speckles (snow / petals / sparkle), and a tall portrait composition with a layered foreground-midground-background. Travel-journal / urban-sketcher aesthetic. Trigger when the user says /postcard-illustration, asks for a "postcard illustration", "travel illustration", "urban sketcher style", or briefs a palette + scene archetype + complexity.
What this skill does
# /postcard-illustration — locked postcard / travel-journal illustration
This skill produces one tall portrait illustration in a locked hand-drawn editorial postcard style. The line work, color medium, surface texture, and overall composition are constants. The caller only dials seven creative knobs (palette, scene archetype, subject, complexity, atmosphere, sky treatment, surface-pattern density, cast).
The aesthetic sits in the urban-sketcher / travel-postcard / picture-book editorial space. Think dense layered architectural and botanical scenes, confident ink line work, flat saturated gouache color, and a charming slightly imperfect hand. Not anime, not manga, not 3D, not vector, not photoreal, not soft watercolor wash.
## Required model
This style is locked to **`gpt-image-2`** (OpenAI GPT image generation, served through whichever provider the executing tool routes to). The dense small ink patterns, flat-but-textured color medium, and consistent line weight do NOT survive on weaker or differently-tuned image models — they collapse into either soft-watercolor wash or clean vector. Do not substitute with another model unless you have validated that the two locked reference anchors regenerate faithfully.
Required generation parameters:
- **Model:** `gpt-image-2`
- **Size:** `1024x1536` (tall portrait)
- **Quality:** `high` — the dense ink patterns and small speckles need resolution to read
- **Mode:** image-to-image with BOTH locked reference anchors (`ref-sensoji.png` and `ref-shibuya.png`) passed as style references
- **Input fidelity:** `high` — the model must hold line-work weight, color flatness, and pattern density from the references
These are semantic parameters. The executing tool decides the invocation mechanics (CLI command, REST call, gateway, local runtime).
## Reference anchors
Two locked reference images live alongside this SKILL.md and define the look:
- `ref-sensoji.png` — Tokyo Senso-ji temple at golden hour: Kaminarimon gate with the giant red lantern, five-story pagoda, Mt. Fuji silhouette, drifting sakura petals, ink-outlined clouds, paper lanterns strung overhead, silhouette pedestrians. Anchors the **Tokyo warm palette**, **L3 architectural complexity**, **drifting-petals atmosphere**, **ink-cloud sky**, and **high pattern density** (roof tile shingle curves, woodgrain on pagoda beams, repeated lantern marks).
- `ref-shibuya.png` — Shibuya scramble crossing at twilight in the rain: indigo→magenta gradient sky, towering buildings packed with vertical neon kanji signs and lit windows, a sea of black-umbrella silhouettes with three focal sakura-pink / cyan / yellow umbrellas, a yellow taxi, wet asphalt with neon reflections. Anchors the **neon dusk palette**, **L3 modern urban complexity**, **rainy-streaks atmosphere**, **gradient-sky treatment**, and **very high pattern density** (endless tiny windows, vertical kanji marks, umbrella spokes, crosswalk stripes).
When generating, the executing agent should pass both references to the model as style anchors (image-to-image with high input fidelity). The prompt then names the new scene and dials the knobs.
## Locked style axes (NEVER vary)
### Orientation
- Tall portrait, approximately 2:3 — generate at 1024×1536.
### Line tool
- Fine BLACK MARKER or technical pen.
- Thin, fairly uniform weight. Confident, deliberate strokes.
- NOT a wet watercolor brush. NOT a wobbly sketch line. NOT variable calligraphic taper.
- Architectural straight lines are drawn straight, but with a hand-made feel — slight imperfections are welcome, geometric perfection is not.
### Color medium
- FLAT, SATURATED gouache or marker fills.
- Sharp, hard edges between color zones — colors do not bleed or blur into each other.
- NO wet-on-wet watercolor bloom.
- NO soft pastel haze or airbrush gradient (sky may have a gentle vertical gradient — see Sky knob below — but everywhere else is flat).
- Each color zone stays roughly within its ink contour, but small imperfections (a tiny patch of color crossing a line, a tiny patch of white inside a fill) read as hand-painted.
### Surface texture
- Subtle paper-grain texture layered across the whole canvas. Visible but quiet — never the dominant element.
### Speckles
- Small sparse scattered white (or white-pink) dot specks distributed across the canvas. They read as snow, drifting petals, or sparkle depending on the scene. Stay light and airy — never blizzard density.
### Mood
- Editorial, travel-journal, picture-book postcard. Charming, layered, slightly imperfect.
## Dial-able knobs (vary per illustration)
### 1. Palette
A saturated, warm-leaning postcard palette anchored in charcoal-black ink. Pick or compose one — examples:
- **Tokyo warm** — ivory / vermillion-red / slate-grey roof / sakura-pink / Fuji-blue (matches `ref-sensoji.png`).
- **Neon dusk** — deep indigo / magenta-pink / cyan-neon / window-gold / wet-asphalt charcoal (matches `ref-shibuya.png`).
- **Postcard warm** — cream / tan / ochre / sky-blue / red accents.
- **Botanical bright** — magenta-pink / lime-yellow / leaf-green / sky-blue / golden bee-yellow.
- **Jiangnan garden** — ivory / slate-grey roof / koi-orange / peony-pink / bamboo-green.
- **Nordic muted** — sage / sand / dusty-rose / charcoal.
- **Monsoon cool** — slate / teal / cream / mustard.
Always state 4–6 specific palette anchors in the prompt.
### 2. Scene archetype
- **Architectural landmark** — a building or street scene (temple, plaza, old town, monument).
- **Botanical close-up** — flowers, insects, a single small creature.
- **Interior** — a room, café, library, shop, bathhouse.
- **Vehicle / object** — boat, train, market stall, taxi.
- **Travel landscape** — mountains, harbor, garden, coastline.
- **Modern urban** — crossing, neon street, skyline.
### 3. Complexity
- **L1** — single subject + simple background. Sparse and graphic.
- **L2** — one main scene + light secondary layer.
- **L3** — dense layered scene with clear foreground, midground, and background (matches both `ref-sensoji.png` and `ref-shibuya.png`).
### 4. Atmosphere
- Snowfall (white speckles dominate).
- Drifting petals (sakura, jacaranda — speckles take on petal color).
- Bright clear daylight.
- Cloud-cover with ink-outlined fluffy cumulus clouds.
- Foggy or overcast.
- Golden hour or dusk.
- Rainy (speckles become diagonal rain streaks).
- Night with neon glow.
### 5. Sky treatment
- Solid color band.
- Vertical gradient (light blue → cream, or indigo → magenta-pink at dusk).
- Ink-outlined cumulus clouds against a gradient.
- No sky (the subject fills the canvas top to bottom).
- A distant mountain or landmark silhouette layered into the sky (Fuji, an alpine ridge).
### 6. Surface-pattern density
How busy the ink hatching / stippling / repeated marks are on surfaces.
- **Low** — clean fills with minimal marks.
- **Medium** — windows-as-rectangles on buildings, occasional hatching, simple shingle indication.
- **High** — every surface packed with stippling, shingle curves, micro-marks, woodgrain hatching, repeated kanji or signage marks (matches both `ref-sensoji.png` and `ref-shibuya.png`).
### 7. Cast
- None.
- 1–3 tiny silhouette pedestrians for scale.
- A featured creature (bee, cat, bird, koi).
- A dense crowd (umbrellas in rain, market shoppers).
- Bird silhouettes flying in the sky.
## Brief template the caller fills in
```
Palette: {palette name + 4–6 color anchors}
Scene archetype: {architectural | botanical | interior | landscape | urban | …}
Subject: {one or two sentences describing what the scene IS}
Complexity: {L1 | L2 | L3}
Atmosphere: {snowfall | drifting petals | clear | cloudy | dusk | rainy | …}
Sky: {solid | gradient | ink-clouds | mountain silhouette | none}
Pattern density: {low | medium | high}
Cast: {none | silhouette figures | featured creature | crowd | birds}
```
## Prompt assembly
When generating, compose a single prompt that:
1. Begins with: "Create a new illustration in EXACTLY the same hand-drRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.