LLM & Agents

ALWAYS use this skill proactively for Consumer Affairs Django repositories (located in ../ca/ directory) when ANY of these occur - (1) User mentions coverage, codecov, test coverage, partial coverage, branch coverage, or uncovered lines/code (2) User asks to write tests, add tests, run tests, or fix test failures (3) User asks to implement features, fix bugs, or modify code in CA repos and tests are needed (4) User provides a file path containing 'test' or 'tests' in CA repos (5) After writing new code in CA repos that needs test coverage. This skill handles Django test execution using the 'ca magictest' command and ensures 100% code coverage for CI requirements.

Optimize and create Claude Rules (.claude/rules/*.md) following best practices.

Guide for implementing ChatGPT Apps using OpenAI Apps SDK. Use when building MCP servers with interactive UI components that integrate with ChatGPT, including widget runtime, authentication, state management, and deployment to the ChatGPT platform.

Guide for implementing Grafana Mimir - a horizontally scalable, highly available, multi-tenant TSDB for long-term storage of Prometheus metrics. Use when configuring Mimir on Kubernetes, setting up Azure/S3/GCS storage backends, troubleshooting authentication issues, or optimizing performance.

빌드/테스트가 필요할 때 builder-agent 활용 가이드

Documentation expert for Claude Skills showcase website. Maintains skill-to-website sync, manages tag taxonomy and badges, creates blog-style artifacts, and preserves multi-skill collaborations for posterity. Activate on 'document', 'sync skills', 'create artifact', 'validate skills', 'add tags', 'tag management', 'badge', 'metadata'. NOT for code implementation (use domain skills), design creation (use web-design-expert), testing (use test-automator), or project planning (use orchestrator).

Build Retrieval-Augmented Generation (RAG) Q&A systems with Claude or OpenAI. Use for creating AI assistants that answer questions from document collections, technical libraries, or knowledge bases.

This skill should be used when content teaches patterns (skills, subagents, ADRs, PHRs, specifications) that have canonical sources elsewhere. Prevents format drift by ensuring content references and follows the authoritative format from canonical sources. Use before implementing lessons that teach platform patterns, or when reviewing content for format consistency.

Integrate and embed OpenAI ChatKit UI into TypeScript/JavaScript frontends (Next.js, React, or vanilla) using either hosted workflows or a custom backend (e.g. Python with the Agents SDK). Use this Skill whenever the user wants to add a ChatKit chat UI to a website or app, configure api.url, auth, domain keys, uploadStrategy, or debug blank/buggy ChatKit widgets.

Design reusable prompt templates that encode domain-specific patterns for recurring AI tasks.Use when you've executed similar prompts 2+ times and need to capture the pattern as reusableintelligence. NOT for one-off prompts or generic "ask AI a question" patterns.

Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA screening (50% or 90% threshold), vector database creation (ChromaDB), or research conversation interface. Supports knowledge_repository (comprehensive, 15K+ papers, teaching/exploration) and systematic_review (publication-quality, 50-300 papers, meta-analysis) modes. Conversation-first workflow with 7 stages.

Qdrant vector database REST API via curl. Use this skill to store, search, and manage vector embeddings.

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

Analyzes project tasks by priority levels, generates optimization checklists, executes selected optimizations with quality assurance, and produces detailed reports for software development and project management.

Create structured project plans with task breakdown, timeline, resource allocation, and risk assessment. Use when starting new features, refactoring, or complex implementations.This skill automatically generates comprehensive project plans including:- Task decomposition with clear milestones- Resource allocation (which sub-agents to use)- Parallel execution recommendations- Risk identification and mitigation strategies- Timeline estimationTriggers: "plan", "roadmap", "task breakdown", "project structure", "計画", "プロジェクト構造", "タスク分解"

Decide when and how to hand routine coding work to the Gemini CLI while Claude focuses on higher-level reasoning.

Complete comprehensive guide for creating, managing, and optimizing Claude Code Skills. Reference documentation covering structure, API usage, examples, best practices, and troubleshooting.

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Generate code scaffolds following Carbon ACX conventions for React components, TypeScript APIs, Cloudflare Workers, Python scripts, and tests.

Production Brief methodology for complex Veo 3 video scenes. Use when creating scenes with dialogue, character continuity, structured settings, or multi-beat sequences. Provides 11-block framework (Format & Tone, Main Subjects, Wardrobe & Props, Location & Framing, Lighting & Palette, Continuity Rules, Actions & Camera Beats, Montage Plan, Dialogue, Sound & Foley, Finish) for professional, replicable results.