數據與 AI

Generate JSON schemas and Python handlers for Qdrant-based retrieval tools used by the RAG agent to search sitemap-crawled textbook content with URL citations.

LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.

Expert knowledge for UX Layer modeling in Documentation Robotics

Use when creating, assessing, or updating system prompts, instructions, or prompt content for Claude 4.x models (Sonnet 4.5, Haiku 4.5, Opus 4.5). Ensures prompts follow Claude 4 best practices.

Analyze implementation failures and generate recovery plans. Use when an issue fails and needs diagnosis for retry or escalation.

Better proposals, faster closes. Use when creating AI agent pricing, automation proposals, ROI calculations, or sales materials. Generates professional pricing pages, case studies, and closing scripts for AI automation services.

Debug failed/issue tasks from Beam.ai using Langfuse traces. Load when user says "debug issue tasks", "check failed tasks", "why did task fail", "task errors", "debug agent", or needs to investigate task failures.

Lesson content for Claude Code Course.Use when: loading lesson content.Internal skill - contains lesson files.

Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.

Use when encountering errors, investigating library APIs, troubleshooting issues, or needing up-to-date documentation. Prioritizes Context7 and WebSearch over outdated training data.

Generate comprehensive .gitignore files tailored to specific tech stacks, frameworks, and development environments. Triggers on "create gitignore", "generate .gitignore for", "gitignore for", "ignore files for".

Type-safe database access with Prisma ORM for Node.js and TypeScript. Use when designing schemas, writing queries, running migrations, or optimizing database operations. Triggers on Prisma, database, ORM, migration, or SQL questions.

High-performance CLI for working with SQL dump files: split/merge by table, analyze contents, validate integrity, convert between MySQL/PostgreSQL/SQLite/MSSQL, create FK-safe samples, shard multi-tenant dumps, generate ERD diagrams, reorder for safe imports, and run SQL analytics with embedded DuckDB. Use when working with .sql dump files for migrations, dev seeding, CI validation, schema visualization, data extraction, or ad-hoc analytics.

This skill should be used when the user requests learning materials for algorithm or data structure patterns (e.g., "Create learning material for sliding window pattern"). It automatically generates structured markdown documents in the _learning/ folder and updates the main README.md with links to the new materials.

Protocol for pausing project work to enhance ~/.claude infrastructure when generalizable patterns are detected. Use when pattern should become permanent, user says make this permanent, or self-discovered optimisation.

This skill should be used when determining patterns for parallel and sequential subagent usage. Use when planning subagent orchestration or briefing subagents on tasks.

Guide AI agents through TypeScript coding best practices including type safety, error handling, code organization, and architecture patterns. This skill should be used when generating TypeScript code, reviewing TypeScript files, creating new TypeScript modules, refactoring JavaScript to TypeScript, or when the user asks about TypeScript patterns, types, or coding standards. Keywords: typescript, types, coding standards, best practices, type safety, generics, architecture, refactoring.

Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.

Create rich, responsive interactive experiences that make applications a joy to use. Use this skill when building components with user interactions, forms, data-heavy interfaces, or any feature requiring thoughtful UX patterns. Complements frontend-design with psychology-driven interaction patterns.

This skill creates pull requests using the GitHub CLI with AI-generated descriptions. It analyzes the current branch, detects available target branches, and generates concise PR descriptions based on the commit history and changes. Use this when asked to create a pull request, file a PR, or when the user uses the `/pr` or `/gpr` command. It automates the PR creation process while ensuring quality descriptions.