Data & AI

Use when you need to plan technical solutions that are scalable, secure, and maintainable.

Use space-based/data-grid architectures to scale high-traffic, stateful workloads across nodes.

Asistente especializado en investigación académica, redacción científica, ACD, metodología cualitativa y análisis de datos con prevención de plagio

Load when working on community engagement, moderation policies, member interactions,or developing community standards. Contains best practices for building inclusive,thriving online communities.

AI security co-pilot for identifying, testing, and fixing vulnerabilities in LLM-powered applications.Use when: (1) Securing LLM applications or agents, (2) Generating security test suites with promptfoo,(3) Testing for prompt injection, jailbreaking, data exfiltration, (4) Hardening system prompts,(5) Compliance mapping for OWASP LLM Top 10, NIST AI RMF, CJIS, SOC2, (6) Threat modeling AI systems,(7) Analyzing security eval results, (8) Research on LLM attack/defense techniques.Triggers: "secure my LLM", "prompt injection", "jailbreak test", "AI security", "red team","system prompt hardening", "LLM vulnerability", "promptfoo", "OWASP LLM", "AI compliance".

Build and integrate production-ready RAG (Retrieval-Augmented Generation) chatbots into documentation sites using OpenAI, Qdrant Cloud, and Neon Postgres. Handles complete stack from backend API to frontend UI integration.

Expert guidance for using the FrontRange CLI (fr command) to manage YAML front matter in text documents. Use when working with front-mattered files, YAML metadata, blog posts, markdown with front matter, or when the user mentions 'fr' commands. Supports reading/writing front matter keys, JMESPath-based searching, bulk operations via piping, directory recursion, and multiple format output (JSON/YAML/plist/CSV).

Expert infrastructure design including networking, compute, storage, and operations

Create complete audiobook with OpenAI GPT-4o-mini translation to Argentine Spanish. Full pipeline - translate, TTS, video with background image. Auto-scales parallelism based on file size. Use when user wants to create audiobook from Russian text to LATAM Spanish.

Comprehensive templates, patterns, and best practices for creating Claude Code subagents and skills. Use when building new agents/skills or need reference examples for proper structure and formatting.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Use when creating, auditing, or validating MetaSaver contracts packages. Includes Zod validation schemas, TypeScript types, barrel exports, and database type re-exports. File types: .ts, package.json, tsconfig.json.

Choose and implement WebFBundle loading in a Flutter host (remote URL, assets, localhost dev, inline) and diagnose bundle load failures (bad URL, missing assets, network errors). Use when the user mentions WebFBundle, bundle URL/path, remote vs assets vs localhost vs inline, or “bundle won’t load”.

プロジェクトの .claude/settings.json を更新する。「設定を更新して」「settings を変更」「permissions を追加」「設定を変えて」「Claude の設定」「設定ファイルを編集」「allowedTools を追加」などで起動。Claude Code のプロジェクト設定を管理。

This skill should be used when the user asks about "prompt_toolkit Validator", "validation", "input validation", "ValidationError", "History", "FileHistory", "InMemoryHistory", "auto_suggest", "AutoSuggest", or needs to validate user input or implement command history in prompt_toolkit applications.

WHEN: Coverage analysis, finding untested files, test prioritization, coverage gap identificationWHAT: Line/Branch/Function coverage + untested file list + priority by importance + improvement roadmapWHEN NOT: Test generation → test-generator, Test quality → code-reviewer

Clean Architecture and SOLID principles implementation including dependency injection, layer separation, domain-driven design, hexagonal architecture, and code quality patterns

Use when designing database schemas from business requirements, translating vague requirements into concrete SQL definitions, or validating database designs with non-technical stakeholders. Provides a systematic methodology that decouples logical business modeling from physical implementation to reduce cognitive load and ensure business-driven design.

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch task → Review output → Apply feedback → Mark complete → Next task. No skipping reviews, no parallel dispatch.