source-research
Search and cite primary sources from Source Library. Use when asked what historical authors wrote, to find quotes from old texts, investigate alchemical or philosophical works, or cite translated Latin/German s...
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Search and cite primary sources from Source Library. Use when asked what historical authors wrote, to find quotes from old texts, investigate alchemical or philosophical works, or cite translated Latin/German s...
Extract and catalog illustrations from historical books using AI vision. Generates rich metadata (subjects, figures, symbols, style, technique) and museum-style descriptions. Use when asked to extract images, r...
Quality auditor for Source Library. Prioritizes verifying original language texts (not modern translations), auditing metadata accuracy against title pages, USTC alignment, and translation quality. Use for syst...
Create a DOI-ready scholarly edition of a translated book. Use when asked to publish, create an edition, mint a DOI, or prepare a book for scholarly publication. Generates front matter, creates versioned editio...
Autonomous curator for Source Library. Discover, evaluate, and import historical texts from digital archives (Archive.org, Gallica, MDZ). Use for acquisition sessions, collection gap analysis, or building thema...
Batch process books through the complete pipeline - generate cropped images for split pages, OCR all pages, then translate with context. Use when asked to process, OCR, translate, or batch process one or more b...
Bibliographic research agent for analyzing books and manuscripts. Builds comprehensive "book biographies" showing production context, textual transmission, related editions, and scholarly networks. Use when ask...
Autonomous curator for Source Library - discover, evaluate, and import historical texts in alchemy, Hermetica, Kabbalah, Rosicrucianism, and early modern knowledge. Use when asked to curate books, find new sour...
Common Next.js anti-patterns: useEffect misuse (data fetch, browser detect), useState for server data, Pages Router patterns, serial await, over-using 'use client'.
Vercel AI SDK v5: generateText, streamText, useChat, tool calling (use tool() helper + inputSchema), embeddings. v5: sendMessage vs append, message.parts, string models.
Client component onClick/form → Server Action → set cookie. 'use client' calls 'use server' action using cookies() from next/headers.
SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.
Next.js App Router (13+). Migrating from Pages, file conventions (layout, page, loading, error), routing patterns, metadata, generateStaticParams.
Server Component navigation: for links, redirect() for conditional redirects. NO 'use client' needed for static links or server redirects.
Fetch data using URL parameter. Create app/[id]/page.tsx, await params to get ID, fetch API, render. Server Component (no 'use client').
Next.js dynamic routes with [param] folders. Access via params prop (Server) or useParams() (Client). Next.js 15+: await params. Default to app/[id]/ not app/products/[id]/.
Advanced Next.js routing: Route Handlers (API routes), Server Actions ('use server'), Parallel Routes (@slot), Intercepting Routes ((.)), Error Boundaries, Draft Mode, Suspense streaming.
Server vs Client Components in Next.js App Router. Server is default (async, cookies, headers, searchParams). Client needs 'use client' (hooks, events, browser APIs).
Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.
useSearchParams hook in Next.js. REQUIRES 'use client' + Suspense wrapper. Read URL query params: .get(), .getAll(), .has(). Update via router.push().
Error handling with @julian-i/try-error. Wrap throwable code with tryPromise (async) or tryThrow (sync). Forces reflection on error types, handling location, audience, and recovery.
Research topics by verifying actual source content. Use when asked to research or study links and documentation.
Code review with Codex CLI. Use for PR review, diff review, code analysis, or when user says "codexでレビュー", "コードレビュー".
GraphQL development best practices. Use when working with fragments, queries, mutations, or .graphql files.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.