Art & Design

Agent skill 'apple-design' from emilkowalski/skills. Use when the task matches this skill's domain.

Agent skill 'emil-design-eng' from emilkowalski/skills. Use when the task matches this skill's domain.

Agent skill 'pick-ui-library' from emilkowalski/skills. Use when the task matches this skill's domain.

Pixel-exact UI from design references, plus design audits and roasts. An agent skill for Claude Code, Codex and more.

Implement or refine a UI component from a reference screenshot by harnessing image comparison with the pxp CLI. Use for requests like "build this component from this PNG", "make this component match", or "pixel perfect this UI" when application code changes are expected. Also supports screenshot comparison without code changes when explicitly requested. Not for implementing a UI without a visual reference.

Generate or edit product, editorial, photographic and typography images with GPT Image 2.5. Sunburst favors quality; Flare favors speed. Automatically use the other variant on rate limits.

Organize a messy personal/local folder into a clear directory tree by reading file contents (not just names). Use when the user drops a pile of files or folders and asks to 整理/归类/分类 them, especially repeatedly over time. Covers content peeking for docx/xlsx/pptx/PDF/legacy .doc, bulk image identification, dry-run + rollback-table practice, and Windows-specific pitfalls (shutil.move nesting, sandboxed rmdir, recycle-bin forensics).

为论文框架图、流程图、机制示意图生成生图 Prompt，采用 nature-figure 的科学表达与视觉规划方法，但不执行绘图。无图时读稿生成新图提示词，有图时在保持内容的前提下生成视觉改进提示词。输出 Prompt 后必须停止等待确认；不调用 Imagegen、OpenRouter，不生成 Python/R/SVG 代码，不修改研究方法。适合与其他提示词 Skill 做同后端对比。

Autonomous image-generation director. Use whenever the user asks to create, generate, render, edit, transform, restyle, translate, repair, or improve an AI image or image prompt. Converts the user's request into a precise canonical JSON image spec, validates it, adapts it to the available image-generation tool/provider, and dispatches generation automatically so the user does not need to copy JSON or prompts. Handles references, identity preservation, products, people, photorealism, illustrations, posters, UI, text-in-image, aspect ratios, camera perspective, and negative constraints.

Search and fetch royalty-free stock photos from the Pexels API. Use when the user asks to find stock photos, seed placeholder/demo/seed images, populate a gallery, or needs real royalty-free imagery for a project (e.g. "find me 5 photos of X", "get stock images for the hero section", "seed images from Pexels").

Engineer and operate containerized environments. Use for Podman/Docker, images, compose, volumes, networking, health checks, startup, recovery and deployment automation.

Empirical fact-check for freshness-sensitive claims — versions, EOLs, package latest, GitHub Action SHAs, k8s apiVersions, AI model deprecations, image tags, or anything the model's training cutoff may have staled. Primary sources only. Auto-fires as a PreToolUse hook on Edit/Write/MultiEdit, but only in a repo with a `.scratchpad/dossier/` directory; `/dossier:verify` on demand works anywhere. Invoke when user says "verify", "fact-check", "is this current", "/dossier:verify", "double check", or when reviewing freshness claims.

Use when bringing a recipe in the spark-recipes repo up on the 2-node DGX Spark cluster — starting/staging a recipe directory, tearing down the currently-serving model, rebuilding the patched image, launching worker-then-head, and confirming health. Triggers: "bring up <recipe>", "start <recipe> on the sparks", "deploy the glm/qwen/deepseek recipe", "latest recipe not running", "fresh head/worker after a model change", DFlash2/DFlash enablement.

MikroTik RouterOS CHR (Cloud Hosted Router) with QEMU. Use when: running RouterOS in QEMU, booting CHR images, debugging CHR boot failures, setting up VirtIO devices for RouterOS, choosing between SeaBIOS and UEFI boot, configuring QEMU port forwarding for RouterOS REST API, setting up inter-VM socket networking or host-side L2 capture of guest broadcasts (e.g. MNDP), or selecting QEMU acceleration (KVM/HVF/TCG).

Use this skill whenever the user needs to operate a single container host through the Docker Engine API, Portainer, or Podman — a one-shot host overview; container reads (list/inspect, logs tail, CPU/memory stats, top processes, restart summary); image reads (list, inspect with history, dangling, disk usage); volume reads (list, inspect, dangling); network reads (list, inspect); system reads (info, version, df disk-usage, recent events); Portainer stacks + endpoints; Compose-project rollups (list_compose_stacks, docker+podman); Podman pods (list_pods, podman-only); three flagship analyses — restart-loop RCA (crash-looping containers + cause/action), resource-pressure analysis (CPU/memory vs limits), and image & volume bloat (prune candidates + reclaimable bytes); and eight guarded writes (restart/stop/start/remove a container, prune images/volumes, update resource limits, recreate a Portainer stack). Always use this skill for "Docker host overview", "which containers are crash-looping", "restart loop", "why d

Use when a jewelry / 珠宝 / 文玩 / 翡翠 / 钻石 / 黄金 / 珍珠 e-commerce merchant needs marketing material from one product photo — produces a full XHS-ready bundle (12 marketing images + 6 copywriting styles + product analysis JSON) for finished pieces, or a design suite (8 images: hand-drawn sketch + 3D render + lifestyle + CAD sheet + ...) when the input is a raw gemstone / 原石 / 散石. Auto-detects finished-product vs raw-material. Trigger phrases: 珠宝营销素材, 生成珠宝商品图, 珠宝小红书素材, 珠宝海报, 上手图, 一饰多搭, 钻石/翡翠/珍珠/玉/古法金/月光石 marketing bundle, jewelry design from raw stone, 原石设计图, 散石变成品.

Generate and edit images with the OpenAI Image API (gpt-image-2, gpt-image-1, DALL·E). Use when creating marketing assets, hero images, card art, regenerating landing visuals, or when the user mentions OpenAI image generation, DALL·E, gpt-image, or image gen scripts.

Extract, clean, join, update, verify, and deliver Excel, CSV, cloud spreadsheets, or tabular data from images through a conversation-driven agent workflow. Use when the user asks an agent to 做表格、合并表格、图片转Excel、清洗数据、更新Excel、Google Sheets、飞书表格 or WPS表格.

Use this skill when adding a competition's problems to the site database through the bulk-import draft pipeline — registering a brand-new competition in the taxonomy if it isn't there yet, authoring the draft folder (statements + solutions + images, one original language plus translations), and running the bulk-import CLI validate until it passes. Trigger phrases — "add a new competition", "import a competition's problems into the DB", "register a competition in the taxonomy", "create a bulk-import draft", "add a round/year of a competition". Do NOT use for editing handouts (use the handout-* skills). The skill ends at `validate`; `apply` runs only on the user's explicit say-so.

Use when creating, modifying, or reviewing an iOS Clean Architecture presentation layer with SwiftUI/UIKit state holders, explicit UiState, UiModel mapping, dependency injection, and state-based presentation code review.

Generate startup legal documents from attorney-drafted templates: NDAs, MSAs, DPAs, privacy policies, offer letters, and more. Download PDF, ODT, or Markdown through MCP or an agent skill. No account required.

Apply comment-quality criteria during implementation and the final comment-quality pass before final-review, multi-review, or architecture-review after code changes. Applies equally in Codex, Claude, and OMP for Python, Kotlin, React Web, React Native, iOS, Swift, and SwiftUI.

Higgsfield image prompt director covering Banana Pro, Soul Cinema, and GPT-2. Three asset types in strict order: (1) single-image character outfit on white seamless studio — the locked base reference, via Banana Pro (custom styling from prompt) or Soul Cinema (face/body from character ref + outfit from wardrobe ref), (2) 6-panel multi-angle character sheet off that base, (3) scene plates with or without characters in cinematic environments. Also GPT-2 for detail face/chest-up portraits. Reads reference images for hair, makeup, wardrobe, jewelry, identity markers. Outputs photorealistic prompts with locked hyperreal stack — skin pores, subsurface scattering, strand-by-strand hair, fabric weave, Kodak Vision3 film. Use for any character outfit reference, character sheet, model sheet, ref sheet, multi-angle sheet, scene plate, environment plate, face detail shot, or photorealistic still — even without saying 'Banana Pro,' 'Nano Banana,' or 'Soul Cinema.'

Convert slide images, screenshots, scanned PDFs, and image-only PPT/PPTX files into high-fidelity object-level editable PowerPoint, including semantic-region mixed reconstruction, measured flowcharts and knowledge graphs, native circle nodes and connectors, single-object thin and filled arrows, speaker-note preservation, and rendered QA. Use for 图片转可编辑PPT、截图还原PPT、扫描PDF恢复、图片型PPTX转换、流程图/知识图谱/复合图形/箭头重建; not for authoring a new deck from notes.