Agent Skills

photo-abstract-editorial

Create a clean, vertical editorial artwork that preserves an uploaded photograph as the original image and pairs it with a restrained, photo-derived abstract memory panel and poetic English title. Use when asked to transform a photo into an abstract editorial diptych, photo-plus-abstraction composition, visual memory panel, or minimalist archival poster without redrawing or stylizing the source photo.

Install

npx skills add https://github.com/zzzlc0405/photo-abstract-editorial --skill photo-abstract-editorial
SKILL.md

Photo Abstract Editorial

Create one finished image from one uploaded photograph. Keep the photograph faithful; derive the lower abstract panel only from the photograph's observed spatial, tonal, and color relationships.

Workflow

  1. Inspect the photograph internally. Identify three to six decisive spatial facts: subject relationships, scale, axes, direction, intervals, overlap, depth, rhythm, light, color roles, and negative space.
  2. Keep the photo as the upper or principal section. Permit only proportional scaling or a slight crop needed for the composition. Never redraw, extend, replace, retouch, apply a filter to, or otherwise alter its content.
  3. Reconstruct the retained relationships below as a sparse abstract motif—not a thumbnail, trace, illustration, vector icon, or style transfer. Prefer relationships over silhouettes and preserve only the minimum recognition cues needed for distinctive subjects.
  4. Compose a vertical work with an untextured, uniform ivory lower panel. Adapt the photo/panel proportions to the photograph rather than splitting the image mechanically in half. Join both sections directly with no frame, shadow, collage, tape, or mockup effect.
  5. Use one primary mark family and no more than two supporting families. Extract a muted palette solely from the photo; use generous whitespace and avoid invented decorative elements, colors, symbols, and symmetry.
  6. Create one original English title of two to five words, grounded in visible facts. Place it only on the abstract panel in a restrained editorial serif face. Add a short subtitle only when it adds meaning.
  7. Return only the completed composition. Do not add commentary, analysis, title options, labels, dates, logos, or watermarks.

Guardrails

  • Treat the uploaded photo as the sole content source.
  • Keep the panel background flat, continuous, and neutral ivory; exclude gradients, paper texture, grain, glow, shadows, vignettes, stains, collage artifacts, and scan effects.
  • Make every abstract mark traceable to a visual fact in the source photo.
  • Preserve people as irregular continuous short vertical marks or gently tapered blocks, never illustrated heads, limbs, faces, or clothing.
  • Preserve landmark architecture with at most one to three identity cues; omit architectural surface detail.

Reference Prompt

Read the appropriate full prompt before producing the image:

Use assets/examples as visual input examples only. Do not reuse their subject matter, colors, or composition unless the user supplies that exact image.

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers