Build production-ready LLM applications, advanced RAG systems, and
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Build production-ready LLM applications, advanced RAG systems, and
Practical guide for building production ML systems based on Chip Huyen's AI Engineering book. Use when users ask about model evaluation, deployment strategies, monitoring, data pipelines, feature engineering, cost optimization, or MLOps. Covers metrics, A/B testing, serving patterns, drift detection, and production best practices.
In traditional software, inputs and outputs are defined. In AI, inputs and outputs are fuzzy. Evals (evaluations) are the "unit tests" for AI products. They allow you to move from "vibes-based" develo
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to systematically measure AI output quality.
Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates for AI features.
AIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。
Generate AI images using OpenAI's gpt-image-1 model with customizable aspect ratios and artistic themes. Use when the user wants to create images, generate artwork, or mentions image generation with specific styles like Ghibli, futuristic, Pixar, oil painting, or Chinese painting.
Integrate AI tools and APIs into business workflows and applications
ai-llm-engineering
Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs), future-guided learning, temporal validation, feature engineering, generative TS (Chronos), and production deployment. Emphasizes explainability, long-term dependency handling, and adaptive forecasting.
A production-ready pattern for integrating AI models (specifically Google Gemini) with automatic fallback, retry logic, structured output via Zod schemas, and comprehensive error handling. Use when integrating AI/LLM APIs, need automatic fallback when models are overloaded, want type-safe structured responses, or building features requiring reliable AI generation.
Crawl the latest AI-related news from multiple websites, merge and deduplicate them, select 10 in descending order of time, unify summaries into Chinese, and write to a JSON file.
Manage AI notes in ~/Compost/AI-Notes - read existing notes, list recent documents, and write new implementation plans (仕様書, 計画書, 設計書). Auto-triggers when reading from or writing to notes, specifications, or plans.
Design AI-powered immersive NPC systems for escape room games using proven actor techniques from Korean immersive escape rooms (Danpyeonsun, Ledasquare). Implements adaptive dialogue, emotional simulation, player profiling, and trust dynamics using Gemini/GPT-4. Creates character profiles with lying probabilities, improvisational responses, and cost-optimized streaming. Use for murder mystery NPCs, suspect interrogation, or dynamic character interactions.
In the era of LLMs, product development moves from writing static specifications to defining "correctness" through Evals. Since models are stochastic, you cannot "fix a bug" with a single line of code
Operational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG grounding/citations, tool/agent workflows, prompt safety (injection/exfiltration), and prompt evaluation/regression testing. Use when designing, debugging, or standardizing prompts for Codex CLI, Claude Code, and OpenAI/Anthropic/Gemini APIs.
Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.
AI-powered recommendation engine specialist using Google AI SDK for personalized content suggestions
Add rules or skills adapters for a new AI tool and wire config, CLI, completion, and tests.
Production best practices for building AI agents with Vercel AI SDK v5. Covers security, performance, error handling, testing, deployment patterns, and real-world implementation guidelines.
Manages AI SDK model configurations - updates packages, identifies missing models, adds new models with research, and updates documentation
Vercel AI SDK tool patterns for dx-toolkit - input schemas for smart queries, API key handling, raw response returns
ai-sdk-ui
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
GitHub repository skill for Mallikarjun-Roddannavar/ai-testcase-generator-mcp
Generate high-quality training datasets from documents, text corpora, and structured content. Use when creating AI training data from dictionaries, documents, or when generating examples for machine learning models. Optimized for low-resource languages and domain-specific knowledge extraction.
Analyze transcript files using OpenAI API (gpt-5-mini) to extract insights, summaries, key topics, quotes, and action items. This skill should be used when users have transcript files (from WhisperKit, YouTube, podcasts, meetings, etc.) and want AI-powered analysis, summaries, or custom insights extracted from the content. Supports both default comprehensive analysis and custom prompts for specific information extraction.
MANDATORY verification system that prevents Claude Code instances from making false claims or fabricating evidence. Enforces cryptographic verification, real testing evidence, and automatic claim validation before any success statements can be made.
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya).
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
Comprehensive AI writing detection patterns and methodology. Provides vocabulary lists, structural patterns, model-specific fingerprints, and false positive prevention guidance. Use when analyzing text for AI authorship or understanding detection patterns.
Skill to assist with how a GitHub repository is configured with GitHub integrations, including instructions for agents in markdown (AGENTS and CLAUDE), github actions for invoking agents, and specific
Create AI/BI dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.
aico-worktree
生成、维护、修剪AICTXT文档，保持在CRAFT大小限制内。当AICTXT创建和更新时使用。
AIEOS (AI Entity Object Specification) is a standardization framework designed to solve the "identity crisis" currently facing AI agents. Combined with Soul Documents, together they form a comprehensi
Cross-agent communication system for AI workflows. Check messages at session start, send notifications to other agents, and track multi-agent handoffs with correlation IDs.
Setup and use Docker AI (Gordon) for intelligent container operations
Airoha Technology (MediaTek subsidiary) MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Airoha Bluetooth audio SoCs or AirohaHandler.
Debug and implement Airtable synchronization logic including duplicate prevention, cache management, change detection, and RLS considerations; use when debugging sync failures, stale cache issues, or implementing new Airtable sync features
Use the aissist CLI tool for personal goal tracking, todo management, daily history logging, context-specific notes, guided reflections, and AI-powered semantic recall. Activate when users mention goals, tasks, todos, progress tracking, journaling, work history, personal assistant, meal planning, fitness tracking, or want to search their past activities and reflections.
aiworkflow-requirements
AKM (Asahi Kasei Microdevices) MPN encoding patterns, suffix decoding, and handler guidance. Use when working with AKM audio ICs, magnetic sensors, or electronic compasses.
Diagnose and fix Kubernetes deployment failures, especially ImagePullBackOff, CrashLoopBackOff, and architecture mismatches. Battle-tested from 4-hour AKS debugging session with 10+ failure modes resolved.
Alchemy IaC patterns for deploying TanStack Start apps to Cloudflare Workers with D1 databases. Use when setting up new TanStack Start projects, configuring Alchemy deployments, working with D1/Drizzle migrations, local development with Cloudflare bindings, or deploying to custom domains.
A skill for managing database migrations with Alembic. Use this for tasks involving Alembic initialization, configuration, creating new migration scripts (both autogenerated and manual), defining upgrade and downgrade logic, handling data migrations, testing migrations, performing rollbacks, and following production deployment best practices for database changes.
1. **Alert-based triggers:**
Designs and configures alerting rules for monitoring systems
Use when configuring Sentry alerts, managing issues, or setting up notifications. Covers alert rules, issue triage, and integrations.
Control Amazon Alexa devices and smart home via the `alexacli` CLI. Use when a user asks to speak/announce on Echo devices, control lights/thermostats/locks, send voice commands, or query Alexa.