メニュー
One-off image generation (prompt -> image file) using Transloadit via the `transloadit` CLI. Prefer builtin templates (`builtin/generate-image@latest`) and download outputs locally via `-o`.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Craft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, image-based references, or design-system consistency matter. Not for marketing pages, landing pages, campaigns, or brand-only work.
Tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, or library publishing.
Run technical UI quality audits across accessibility, performance, theming, responsive behavior, and anti-patterns.
Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
Complete reference for implementing OAuth 2.0 login flows with major AI service providers: OpenAI/ChatGPT, Anthropic Claude/Claude Code, Google Gemini, and GitHub Copilot. USE THIS SKILL whenever working on authentication, login, OAuth, tokens, or API access for any of these AI services — even if the user just says "how do I log in to X API", "I need to auth with Claude/OpenAI/Gemini/Copilot", "implement OAuth for AI service", "refresh tokens", "PKCE flow", "authorization code grant", "device code flow", or anything relating to integrating user authentication into an app that uses these AI APIs. Also trigger when comparing auth patterns across AI providers, troubleshooting 401/403 errors on AI APIs, or building MCP servers/clients that need user-scoped AI tokens.
Complete reference for building apps with the Pollinations API — a multi-modal AI generation platform supporting text, image, video, audio, and embeddings. Use this skill whenever working with Pollinations, gen.pollinations.ai, pollinations.ai, or any of their models. ALWAYS trigger on: text generation with Pollinations models, image generation via URL or API, video generation, TTS/audio generation, embeddings, BYOP (Bring Your Own Pollen) OAuth flows, MCP server setup, CLI usage, account/balance/usage APIs, or safety filtering. Also trigger when the user mentions "pollen", "flux model", "pollinations image", "polli CLI", device flow for Pollinations, or wants to integrate Pollinations into any TypeScript/Node/Python/React app. If the user wants to generate any media with AI without paying OpenAI directly, this is a strong candidate — check this skill.
| name | transform-generate-image-with-transloadit |
| description | One-off image generation (prompt -> image file) using Transloadit via the `transloadit` CLI. Prefer builtin templates (`builtin/generate-image@latest`) and download outputs locally via `-o`. |
Do not use --watch for inputless templates.
npx -y @transloadit/node assemblies create \
--template builtin/generate-image@latest \
-f prompt='A minimal product photo of a chameleon on white background' \
-o ./out/ \
-j
Footnote (discover more builtin templates):
npx -y @transloadit/node templates list --include-builtin exclusively-latest --fields id,name --json
npx -y @transloadit/node assemblies get <assemblyIdOrUrl> -j
Notes: