Claude Skills by majiayu000

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.

Extended thinking mode. USE WHEN be creative, deep thinking, deep thinking, extended reasoning. SkillSearch('becreative') for docs.

Amazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge bases, and session management. Use when creating AI agents, orchestrating multi-step workflows, integrating tools with LLMs, building conversational agents, implementing RAG patterns, managing agent sessions, deploying production agents, or connecting knowledge bases to agents.

Amazon Bedrock Automated Reasoning for mathematical verification of AI responses against formal policy rules with up to 99% accuracy. Use when validating healthcare protocols, financial compliance, legal regulations, insurance policies, or any domain requiring deterministic verification of AI-generated content.

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.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

LangSmith Agent Builder - No-code platform for creating AI agents with built-in tools (Gmail, Slack, GitHub, Linear), OAuth integrations, MCP server support, Slack deployment, and programmatic invocation via LangGraph SDK

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

Imputes missing/dropout values in scRNA-seq expression data to improve metabolic pathway analysis. This process handles sparsity common in single-cell RNA sequencing data by filling in zero values using advanced imputation methods (ALRA, scImpute, or MAGIC). The imputed data provides more accurate metabolic pathway activity calculations and feature selection in downstream analysis.

Performs enrichment analysis (GSEA-based) for metabolic pathways across different cell groups to identify significantly enriched pathways. Uses fast gene set enrichment analysis (fgsea package) to rank pathways by their association with specific clusters, conditions, or cell states. Generates summary plots and enrichment visualizations for biological interpretation.

Calculates pathway activity scores for metabolic pathways across different cell groups and subsets. This process quantifies the metabolic activity of each pathway per group, generating visualizations (heatmaps and violin plots) to compare metabolic states between clusters or conditions. Based on the methodology from Xiao et al.

Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.

- Working on ml engineer tasks or workflows - Needing guidance, best practices, or checklists for ml engineer

Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.

MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer functions, (3) building evaluation datasets from traces, (4) using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), (5) analyzing traces for latency/errors/architecture, (6) optimizing agent context/prompts/token usage, (7) debugging evaluation failures. Covers the full eval workflow: trace analysis -> dataset building -> scorer creation -> evaluat...

ML lifecycle management with MLflow. Track experiments, package models, manage registries, and deploy models. Use for ML operations, experiment tracking, and model deployment.

- Working on mlops engineer tasks or workflows - Needing guidance, best practices, or checklists for mlops engineer

"Production-grade data science specialist with TensorFlow 2.20.0, PyTorch\

Enterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniques

Retrieval-Augmented Generation systems, vector databases, embedding strategies, and production RAG architectures for enterprise LLM applications. Use when building RAG, semantic search, or knowledge-aware AI systems.

Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a classification/regression task.

Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

StudioJinsei用Nanobanana画像生成Skill。Google Gemini APIを使用してロゴ、コトネちゃん、サイトビジュアル等を生成します。

Generate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation from text prompts. Includes persistent authentication, automatic environment setup, and reference image support for style matching.

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to \"map the codebase\", \"map codebase\", \"architecture report\", \"codebase overview\", \"architecture overview\", \"what am I looking at\", or \"explain this codebase\".

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Metabolite identification from m/z and retention time. Covers database matching, MS/MS spectral matching, and confidence level assignment. Use when assigning compound identities to detected features in untargeted metabolomics.

Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than an...

Extract named entities (people, organizations, locations, dates) from text using NLP. Use for document analysis, information extraction, or data enrichment.

Search academic literature and generate research hypotheses

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other

Quantifies the impact of exogenous events on contract prices using TimeGPT and CausalImpact. Triggers on "event impact analysis", "model event effects", "quantify event impact", or "causal analysis".

Analyze market risk with VaR, volatility, and position sizing using forecast data. Use when assessing investment risk. Trigger with 'analyze market risk' or 'calculate VaR'.

Open source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate. SkillSearch('osint') for docs.

Open source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate. SkillSearch('osint') for docs.

Complex research requiring deeper analysis, multi-step reasoning, and sophisticated source evaluation for technical, academic, or specialized domain queries needing expert-level analysis, high-stakes decisions, or multi-layered problem solving.

Expert photography composition critic grounded in graduate-level visual aesthetics education, computational aesthetics research (AVA, NIMA, LAION-Aesthetics, VisualQuality-R1), and professional image analysis with custom tooling. Use for image quality assessment, composition analysis, aesthetic scoring, photo critique. Activate on "photo critique", "composition analysis", "image aesthetics", "NIMA", "AVA dataset", "visual quality". NOT for photo editing/retouching (use native-app-designer), g...

Plan technical research (enters plan mode)

Analyzes events through poetic lens using close reading, metaphor analysis, imagery, rhythm, form analysis, and attention to language's emotional and aesthetic dimensions. Provides insights on emotional truth, symbolic meaning, human experience, aesthetic impact, and expressive depth. Use when: Understanding emotional dimensions, symbolic meaning, communication impact, cultural resonance, human experience. Evaluates: Imagery, metaphor, rhythm, emotional truth, symbolic depth, aesthetic power,...

Analyze policy impacts for congressional districts and representatives' constituents. Use when the user mentions a specific district (NY-17, CA-52), a representative's name, or asks about geographic policy impacts at district level. Provides HuggingFace district datasets.

ALWAYS USE THIS SKILL for PolicyEngine microsimulation, population-level analysis, winners/losers calculations. Triggers: "microsimulation", "share who would lose/gain", "policy impact", "national average", weighted analysis. Use this skill's code pattern, but explore the codebase to find specific parameter paths if needed.

Analyzes events through political science lens using IR theory (Realism, Liberalism, Constructivism), comparative politics, institutional analysis, and power dynamics. Provides insights on governance, security, regime change, international cooperation, and policy outcomes. Use when: Political events, international crises, elections, regime transitions, policy changes, conflicts. Evaluates: Power distributions, institutional effects, actor interests, strategic interactions, norms.

Pre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches, major decisions, or risky initiatives to surface hidden risks.

Direct research projects by gathering team feedback and delegating implementation tasks. Writes publication-quality scientific text and coordinates bioinformaticians, software developers, and biologist commentators via technical-pm.

Perform comprehensive regression analysis and predictive modeling using linear regression, decision trees, and random forests. Use when you need to predict continuous values like housing prices, sales forecasts, demand predictions, or any numerical target variables. Includes automated feature engineering, model comparison, and visualization with Chinese language support.

Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.