Claude Skills by majiayu000

This skill should be used when the user asks to "run autopilot", "autopilot feature N", "implement all phases", "run all phases sequentially", "autopilot 003", or wants to automatically implement all phases of a feature in sequence without manual intervention.

Backend Implementation Workflow Agent. Backend만 구현이 필요한 경우 사용합니다. API 추가, 서비스 로직 구현, DB 스키마 변경 등을 오케스트레이션합니다.

AI operational modes (brainstorm, implement, debug, review, teach, ship,

Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".

Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire HTML.

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

OpenRouter API - Unified access to 400+ AI models through one API

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

RAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다.

高性能 RAG 多路检索服务。集成 Milvus 向量数据库进行语义检索，并结合 Rerank 模型进行精准重排序，支持海量文档的高效存储与历史内容召回。

RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.

Use this skill for rigorous theoretical derivation with supercollider mode (G1-G7 simultaneous), diffusion reasoning, and synthesis engine. Applies enhanced Dokkado Protocol with generator hooks, meta-pattern recognition, and cognitive state awareness. Essential for MONAD-level framework development, cross-domain isomorphism detection, and resonant pattern synthesis. Evolution of reasoning-patterns with full gremlin-brain integration.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Model Context Protocol (MCP) implementation for Script Kit. Use when working with MCP server, JSON-RPC 2.0 protocol, kit tools, script tools, resources, or SSE streaming. Triggers on: "mcp", "json-rpc", "kit tools", "script tools", "resources", "sse streaming", "audit logging".

Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, and memory systems. Use for enterprise AI, copilot development, and Microsoft ecosystem integrations.

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

Route tasks to appropriate model size based on confidence estimation. Use small model by default, escalate to large model only on low confidence. Achieves 87% faster learning and 10-30x cost reduction while maintaining accuracy. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".

Systematically evaluate your LLM application with TruLens

Generate AI videos with OpenAI Sora via AceDataCloud API. Use when creating videos from text prompts, generating videos from reference images, or using character references from existing videos. Supports text-to-video, image-to-video, and character-driven generation with multiple models and resolutions.

Generate self-contained collaboration documents for sharing issues with external AI systems (Gemini, ChatGPT, etc.) with structural anti-skip enforcement (Execute-Verify-Record pattern at every step). Interactively gathers context, reads actual code files, loads constitutional constraints, and produces a complete 10-section package ready to paste into the target LLM. Use when the user wants to collaborate with another AI, share an issue for joint problem-solving, get a fresh perspective from ...

Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions. Covers tag hierarchy, structural templates, high-impact interventions, anti-patterns.

Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".

Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTTrainer.

LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.

Expert-level Vercel AI SDK v5 patterns for production chatbots. Use for: (1) Chat persistence with Drizzle/PostgreSQL, (2) Generative UI with typed tool parts, (3) Human-in-the-loop tool confirmations, (4) Custom data streaming with reconciliation, (5) Anthropic provider with extended thinking/reasoning, (6) Type-safe message metadata with token tracking. Covers advanced patterns only - assumes basic AI SDK knowledge. NOT for AI SDK v6.

Compare original and distilled prompts to verify the distillation is faithful and lossless. Checks completeness, accuracy, and appropriate conciseness.

Virtuals Protocol - Build, tokenize, and deploy autonomous AI agents on Base/Solana. Use for creating agents with GAME framework, launching agent tokens, implementing Agent Commerce Protocol (ACP), and building AI-powered applications.

This skill should be used when the user asks about "Workers AI", "AI models", "text generation", "embeddings", "semantic search", "RAG", "Retrieval Augmented Generation", "AI inference", "LLaMA", "Llama", "bge embeddings", "@cf/ models", "AI Gateway", or discusses implementing AI features, choosing AI models, generating embeddings, or building RAG systems on Cloudflare Workers.

Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content

Create your model-alignment skill from TRL documentation before learning DPO theory

Consolidate all Part 8 skills into a production-ready llmops-fine-tuner skill

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Build sklearn pipeline builder operations. Auto-activating skill for ML Training. Triggers on: sklearn pipeline builder, sklearn pipeline builder Part of the ML Training skill category. Use when working with sklearn pipeline builder functionality. Trigger with phrases like "sklearn pipeline builder", "sklearn builder", "sklearn".

Analyze cell-cell communication in spatial transcriptomics data using ligand-receptor analysis with Squidpy. Infer intercellular signaling, identify communication pathways, and visualize interaction networks. Use when analyzing cell-cell communication in spatial context.

Identify spatial domains and tissue regions in spatial transcriptomics data using Squidpy and Scanpy. Cluster spots considering both expression and spatial context to define anatomical regions. Use when identifying tissue domains or spatial regions.

Build spatial neighbor graphs for spatial transcriptomics data using Squidpy. Compute k-nearest neighbors, Delaunay triangulation, and radius-based connectivity for downstream spatial analyses. Use when building spatial neighborhood graphs.

Compute spatial statistics for spatial transcriptomics data using Squidpy. Calculate Moran's I, Geary's C, spatial autocorrelation, co-occurrence analysis, and neighborhood enrichment. Use when computing spatial autocorrelation or co-occurrence statistics.

Visualize spatial transcriptomics data using Squidpy and Scanpy. Create tissue plots with gene expression, clusters, and annotations overlaid on histology images. Use when visualizing spatial expression patterns.

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme analysis', 'voice disorder', 'fluency', 'stuttering', 'AAC', 'pronunciation', 'speech recognition', 'mellifluo.us'. NOT for general audio processing, music production, or voice acting coaching without clinical context.

Build tensorflow model trainer operations. Auto-activating skill for ML Training. Triggers on: tensorflow model trainer, tensorflow model trainer Part of the ML Training skill category. Use when working with tensorflow model trainer functionality. Trigger with phrases like "tensorflow model trainer", "tensorflow trainer", "tensorflow".

TESSA (TCR and Expression Joint Clustering) is a Bayesian model that integrates T-cell receptor (TCR) sequence profiling with transcriptomes of T cells. It maps the functional landscape of the TCR repertoire by learning unified representations across modalities. The process employs BriseisEncoder to capture TCR sequence features, creating numerical embeddings that reconstruct Atchley Factor matrices and CDR3 sequences.

Time series forecasting with ARIMA, Prophet, LSTM, and statistical methods. Activates for "time series", "forecasting", "predict future", "trend analysis", "seasonality", "ARIMA", "Prophet", "sales forecast", "demand prediction", "stock prediction". Handles trend decomposition, seasonality detection, multivariate forecasting, and confidence intervals with SpecWeave increment integration.

Identifies and visualizes the top expressing genes per cluster across ALL cells (before T/B cell selection), followed by pathway enrichment analysis. Provides initial overview of all cell populations by highlighting the most highly expressed genes and their biological functions.

Extract topics from text collections using LDA (Latent Dirichlet Allocation) with keyword extraction and topic visualization.

Separates T and non-T cells or B and non-B cells from a mixed cell population. Uses either clonotype percentage from VDJ data, indicator gene expression (CD3 markers for T cells, CD19/CD20 for B cells), custom selector expressions, or k-means clustering for automatic selection.

Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pitchshift, specaugment, waveform, resample)

Execute model training with optimization algorithms. Use when running training loops on datasets.

Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.