Data analysis, machine learning, LLM apps, and prompt design (9.2K skills)
Universal AI-powered web scraper for any platform. Scrape data from Instagram, Facebook, TikTok, YouTube, Google Maps, Google Search, Google Trends, Booking.com, and TripAdvisor. Use for lead gener...
The English summary is being prepared. Showing the original description.
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...
The English summary is being prepared. Showing the original description.
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
The English summary is being prepared. Showing the original description.
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
The English summary is being prepared. Showing the original description.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
The English summary is being prepared. Showing the original description.
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
The English summary is being prepared. Showing the original description.
Use for Nauthilus configuration loading, config schema and defaults, Viper-backed config formats, config dump behavior, vim syntax generation, template validation, prompt guideline sync, documentation under README/IDP/server docs, config converters, and generated documentation or syntax artifacts.
The English summary is being prepared. Showing the original description.
Collect this machine's local Claude Code conversation data with the asz collector. Resolves the local Claude data directory (honouring CLAUDE_CONFIG_DIR and XDG_CONFIG_HOME), builds the binary, lists what is discoverable, and lands everything into the storage root. Use when asked to collect, backfill, re-collect, or inspect local Claude Code sessions, or to check what the collector can see.
The English summary is being prepared. Showing the original description.
Model sports rules, event formats, prediction types, scoring implications, lock rules, data requirements, and provider constraints for FriendlyBet. Use when adding or comparing sports such as football, basketball, American football, tennis, tournaments, leagues, playoffs, brackets, weekly picks, or World Cup-specific logic.
The English summary is being prepared. Showing the original description.
Provision database infrastructure, initialize migration framework, configure environments, and verify connectivity/migration gates
The English summary is being prepared. Showing the original description.
Transforms user prompts into optimized prompts using established frameworks (RTF, RISEN, Chain of Thought, RODES). Analyzes intent, selects framework, and produces structured, ready-to-use prompts.
The English summary is being prepared. Showing the original description.
Generate or refresh docs/ARCHITECTURE.md from current codebase state with evidence-backed component and data-flow mapping
The English summary is being prepared. Showing the original description.
Analyzes codebase structure, data flow, module relationships, and key patterns to generate and maintain a living architecture document (ARCHITECTURE.md).
The English summary is being prepared. Showing the original description.
Define system architecture, error architecture, and data strategy with map guards and ideation context reload
The English summary is being prepared. Showing the original description.
Manage database migrations and schema versioning. Use when planning migrations, version control, rollback strategies, or data transformations for any database paradigm.
The English summary is being prepared. Showing the original description.
Systematic methodology for verifying that IA, BE, and FE specification layers are mutually consistent. Covers coverage matrices, field mapping checks, error code propagation, access control consistency, and data contract drift detection.
The English summary is being prepared. Showing the original description.
InnoLive 팀 LLM 위키에 확인된 세션 사실을 반영하고 검증한 뒤 요청 범위에 맞춰 커밋과 PR까지 진행한다. 위키 문서화·업데이트 요청에 사용한다. 위키 검색·질문이나 코드 레포 수정에는 사용하지 않는다.
The English summary is being prepared. Showing the original description.
Bootstrap a new Gradle module in any Kotlin Android project. Walks the user through choosing one of three module types — library module (`com.android.library`), feature module (regular Android library that hosts a feature/UI, install-time only), or dynamic feature module (`com.android.dynamic-feature`, on-demand/conditional/instant delivery). Use whenever the user wants to add a module, modularize code, extract a util/data/ui layer, create a new feature, set up Play Feature Delivery, or asks "should this be a library or feature module?". Discovers the project's existing conventions (plugin aliases, namespaces, sibling modules, version catalog) instead of hardcoding any. Pushes back on bad combos (e.g. utility code in a dynamic feature). Stops at scaffolding; app-level wiring is out of scope.
The English summary is being prepared. Showing the original description.
Use this skill when changing persisted local data, storage keys, caches, or any offline/sync behavior.
The English summary is being prepared. Showing the original description.
Use this skill when working on camera, gallery, file pick/upload/download, file preview, sharing, or filesystem-backed media. For Preferences keys, use mobile-local-data.
The English summary is being prepared. Showing the original description.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
The English summary is being prepared. Showing the original description.
Zod 4 — TypeScript-first schema validation with static type inference. Use when writing Zod schemas, validating data, defining types with Zod, parsing input, creating form validation schemas, defining API request/response schemas, working with z.object, z.string, z.number, z.enum, z.array, z.union, z.discriminatedUnion, z.file, z.jwt, z.email, z.uuid, z.url, z.codec, z.toJSONSchema, z.fromJSONSchema, z.int, z.stringbool, z.templateLiteral, z.record, z.partialRecord, or any other Zod API. Also use when migrating from Zod 3 to Zod 4, or when the user's package.json shows zod@^4. CRITICAL: Always use Zod 4 APIs. Never use deprecated Zod 3 patterns unless user explicitly requests Zod 3 compatibility.
The English summary is being prepared. Showing the original description.
TanStack Query (React Query) v5 best practices for data fetching, caching, mutations, and server state management. Use when building data-driven React applications, setting up query configurations, implementing mutations/optimistic updates, configuring caching strategies, integrating with SSR, or fixing v4→v5 migration errors.
The English summary is being prepared. Showing the original description.
AI Personal Assistant network skill. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages, looking up contacts from the local PA directory, or performing any cross-PA task. Reads contact data from data/pa-directory.json in the workspace. Does NOT contain hardcoded contact data — each PA maintains their own directory file.
The English summary is being prepared. Showing the original description.