design-system
Run a shared multi-site design system where every product swaps only its interface accent color: analyze any website's theme colors and roles, wire a new site…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,047 results
brand-identity
Use when translating a brand into interface: accent discipline, logo usage, voice-to-visual mapping, illustration style, and keeping product UI distinct from…
dark-mode
Use when deriving or fixing a dark theme: lightness mapping, elevation by surface lightness, shadow replacement, image dimming, and pure-black bans.
motion-review
Use when reviewing a diff that contains animation code and a Block or Approve verdict with a Before/After/Why table is required.
naming
Use when someone describes an effect or pattern without knowing its name and wants the exact term. For naming a thing, not designing or building one.
notifications
Use when designing notification surfaces: toasts, badges, push, inbox, frequency and batching, priority, quiet hours, and transactional email layout.
onboarding
Use when designing a first run: activation path, progressive disclosure, empty-state coaching over tours, permission prompts, and the first success moment.
perf
Use when a UI measurably janks or loads slowly: compositing, layout thrash, virtualization, image loading, and bundle weight. For choosing durations and…
gpt-image-2
Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual…
image-edit
Edit 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…
image-to-video
Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks…
nano-banana-2
Generate 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…
seedance-v2
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9…
product-design-image-to-code
Implement a selected image, screenshot, mockup, or Image Gen reference as a faithful responsive frontend after Product Design get-context has confirmed the…
rl-policy-optimization
Best practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.
case-control-study-planner
Design a structured case-control study framework with explicit source population logic, control selection rules, matching decisions, exposure measurement…
clinical-cohort-protocol-designer
Designs retrospective or prospective clinical cohort study protocols for biomedical and clinical research. Always use this skill when the user needs a…
ai-marketing-videos
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types:…
instagram-poster
Post images to Instagram automatically via Telegram. Generates images with WaveSpeed or uses your own. Bypasses Instagram bot detection using residential…
huashu-cad
Use natural language to produce editable CAD: floor plan replication, modification, and batch drawing output (DXF); mechanical assemblies such as gears, reducers, and joint modules (STEP); automatic interference and meshing verification; interactive exploded views, operation videos, and assembly engineering drawings. DWG requires a native or conversion environment.
alibabacloud-oss-direct-access-link-diagnosis
Read-only OSS direct-access link diagnosis: attributes preview-turns-download (0048 default-domain forced download incl. images on post-2019-09 buckets,…
image-maker
[HyperB][Codex Only] Generate or edit context-aware raster images with gpt-image-2 when HyperB work needs realistic, non-stock, non-AI-looking visuals for…
gh-pages-neo-brutalist
Use when scaffolding a GitHub Pages site for a new (or existing) repo and you want a cohesive neo-brutalist design system. Drops in Jekyll layouts, design…
video-transcript-downloader
When content creators and self-media creators need to download videos or extract subtitles from video websites, and when they need to obtain plain text transcripts or local media files, they can invoke it with one click. It automatically cleans up timelines and noise markers, downloads audio and video with one click, and generates clean paragraph-style subtitles, greatly improving the efficiency of secondary creation and content processing.