Pixel Art

Operational Steps

1. 确认输入参数完整
2. 执行核心操作（参考本目录下的 scripts/ 或 references/）
3. 验证输出符合契约
4. 保存结果并报告

IO_CONTRACT

• input: request: str, context: dict — 用户请求描述、上下文信息
• output: result: dict — 技能执行结果（结构因技能而异）

对应原则：P2（机械原子暴露输入输出规范）

Pixel Art

Convert any image into retro pixel art, then optionally animate it into a short MP4 or GIF with era-appropriate effects (rain, fireflies, snow, embers).

Two scripts ship with this skill:

• scripts/pixel_art.py — photo → pixel-art PNG (Floyd-Steinberg dithering)
• scripts/pixel_art_video.py — pixel-art PNG → animated MP4 (+ optional GIF)

Each is importable or runnable directly. Presets snap to hardware palettes when you want era-accurate colors (NES, Game Boy, PICO-8, etc.), or use adaptive N-color quantization for arcade/SNES-style looks.

When to Use

• User wants retro pixel art from a source image
• User asks for NES / Game Boy / PICO-8 / C64 / arcade / SNES styling
• User wants a short looping animation (rain scene, night sky, snow, etc.)
• Posters, album covers, social posts, sprites, characters, avatars

Workflow

Before generating, confirm the style with the user. Different presets produce very different outputs and regenerating is costly.

Step 1 — Offer a style

Call clarify with 4 representative presets. Pick the set based on what the user asked for — don't just dump all 14.

Default menu when the user's intent is unclear:

clarify(
    question="Which pixel-art style do you want?",
    choices=[
        "arcade — bold, chunky 80s cabinet feel (16 colors, 8px)",
        "nes — Nintendo 8-bit hardware palette (54 colors, 8px)",
        "gameboy — 4-shade green Game Boy DMG",
        "snes — cleaner 16-bit look (32 colors, 4px)",
    ],
)

When the user already named an era (e.g. "80s arcade", "Gameboy"), skip clarify and use the matching preset directly.

Step 2 — Offer animation (optional)

If the user asked for a video/GIF, or the output might benefit from motion, ask which scene:

clarify(
    question="Want to animate it? Pick a scene or skip.",
    choices=[
        "night — stars + fireflies + leaves",
        "urban — rain + neon pulse",
        "snow — falling snowflakes",
        "skip — just the image",
    ],
)

Do NOT call clarify more than twice in a row. One for style, one for scene if animation is on the table. If the user explicitly asked for a specific style and scene in their message, skip clarify entirely.

Step 3 — Generate

Run pixel_art() first; if animation was requested, chain into pixel_art_video() on the result.

Preset Catalog

Named palettes live in scripts/palettes.py (see references/palettes.md for the complete list — 28 named palettes total). Any preset can be overridden:

pixel_art("in.png", "out.png", preset="snes", palette="PICO_8", block=6)

Scene Catalog (for video)

Invocation Patterns

Python (import)

import sys
sys.path.insert(0, "/home/teknium/.hermes/skills/creative/pixel-art/scripts")
from pixel_art import pixel_art
from pixel_art_video import pixel_art_video

# 1. Convert to pixel art
pixel_art("/path/to/photo.jpg", "/tmp/pixel.png", preset="nes")

# 2. Animate (optional)
pixel_art_video(
    "/tmp/pixel.png",
    "/tmp/pixel.mp4",
    scene="night",
    duration=6,
    fps=15,
    seed=42,
    export_gif=True,
)

CLI

cd /home/teknium/.hermes/skills/creative/pixel-art/scripts

python pixel_art.py in.jpg out.png --preset gameboy
python pixel_art.py in.jpg out.png --preset snes --palette PICO_8 --block 6

python pixel_art_video.py out.png out.mp4 --scene night --duration 6 --gif

Pipeline Rationale

Pixel conversion:

1. Boost contrast/color/sharpness (stronger for smaller palettes)
2. Posterize to simplify tonal regions before quantization
3. Downscale by block with Image.NEAREST (hard pixels, no interpolation)
4. Quantize with Floyd-Steinberg dithering — against either an adaptive N-color palette OR a named hardware palette
5. Upscale back with Image.NEAREST

Quantizing AFTER downscale keeps dithering aligned with the final pixel grid. Quantizing before would waste error-diffusion on detail that disappears.

Video overlay:

• Copies the base frame each tick (static background)
• Overlays stateless-per-frame particle draws (one function per effect)
• Encodes via ffmpeg libx264 -pix_fmt yuv420p -crf 18
• Optional GIF via palettegen + paletteuse

Dependencies

• Python 3.9+
• Pillow (pip install Pillow)
• ffmpeg on PATH (only needed for video — Hermes installs package this)

Pitfalls

• Pallet keys are case-sensitive ("NES", "PICO_8", "GAMEBOY_ORIGINAL").
• Very small sources (<100px wide) collapse under 8-10px blocks. Upscale the source first if it's tiny.
• Fractional block or palette will break quantization — keep them positive ints.
• Animation particle counts are tuned for ~640x480 canvases. On very large images you may want a second pass with a different seed for density.
• mono_green / mono_amber force color=0.0 (desaturate). If you override and keep chroma, the 2-color palette can produce stripes on smooth regions.
• clarify loop: call it at most twice per turn (style, then scene). Don't pepper the user with more picks.

Verification

• PNG is created at the output path
• Clear square pixel blocks visible at the preset's block size
• Color count matches preset (eyeball the image or run Image.open(p).getcolors())
• Video is a valid MP4 (ffprobe can open it) with non-zero size

Attribution

Named hardware palettes and the procedural animation loops in pixel_art_video.py are ported from pixel-art-studio (MIT). See ATTRIBUTION.md in this skill directory for details.

验证清单 · VERIFICATION

• 像素化后输出 PNG 在指定路径生成，且像素块尺寸与所选 preset 的 block 参数一致（NEAREST 降采样后无插值模糊）
• 输出图像颜色数量与 preset 调色板匹配（用 Image.open(p).getcolors() 或肉眼核对）
• 指定硬件调色板（如 NES / PICO_8 / GAMEBOY_ORIGINAL）时使用精确大小写键名，无 Key 错误或降级
• 如需动画：MP4 经 ffprobe 可正常打开且非零大小，场景粒子效果（如 night/rain/snow）符合所选 scene
• 源图宽度 <100px 时已先放大，避免 8-10px 大块下细节完全坍缩
• mono_green / mono_amber 单色调色板已强制 color=0.0 去饱和，无平滑区域条纹伪影

约束规则 · RULES

1. 输入约束: 参数类型、范围、格式必须校验
2. 输出约束: 返回值结构、编码、命名必须一致
3. 异常约束: 错误信息必须包含上下文和恢复建议
4. 安全约束: 不执行未验证的任意代码，不暴露内部状态

Golden 集合 · GOLDEN SET

• Golden Input: 标准输入样本（覆盖正常路径）
• Golden Output: 预期输出（精确匹配或格式校验）
• Golden Error: 预期错误信息（覆盖失败路径）

Golden 集合是测试的单一真理来源。所有改进必须通过 golden 测试。

违反规则的操作视为不安全，必须拒绝或隔离。

每项验证必须可执行、可记录、可复现。验证失败时记录原因和修复。

Genes (策略基因)

紧凑策略表示。条件→策略。需要深度时参考完整文档。

• [PIXE-001] 用户意图模糊时 → 提供 4 个代表性预设选项进行澄清，避免一次性展示所有 14 种风格
• [PIXE-002] 用户已明确指定特定时代或风格时 → 跳过澄清步骤，直接匹配对应的预设参数
• [PIXE-003] 需要生成动画效果时 → 在风格确认后单独询问场景类型，且每轮对话中澄清调用不超过两次
• [PIXE-004] 执行像素化转换时 → 先降采样再量化，确保抖动算法与最终像素网格对齐以保留细节
• [PIXE-005] 源图像尺寸过小（<100px）时 → 先对源图像进行放大处理，防止在大块像素块下细节完全丢失
• [PIXE-006] 使用单色或双色调色板（如 mono_green）时 → 强制去饱和（color=0.0），避免平滑区域出现条纹伪影
• [PIXE-007] 处理高分辨率或大尺寸图像动画时 → 调整粒子密度或更换随机种子，以适配非标准 640x480 画布的视觉效果