When the user wants to apply NLP to supply chain, extract information from documents, analyze supplier communications, classify items, or process unstructured text.
Use when iteratively improving agent prompts through automated LLM-as-Judge evaluation. Runs eval→fix→commit loop with circuit breakers.
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
Chemistry expert covering organic, inorganic, physical chemistry, lab safety, and experimental techniques
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
Prüft KI-Anbieterverträge gegen die unternehmenseigenen Governance- Positionen; kennzeichnet Training auf Daten, Haftung, Modelländerungen und KI-Richtlinien-Konsistenz — from…
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for i — from…
Coordinate parallel agent execution with context handoff. Use when: (1) task has parallelizable subtasks, (2) need to explore multiple areas, (3) research and implementation can…
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies.
Discounted cash flow (DCF) valuation model built from Longbridge financial data — historical FCF (operating cash flow minus capex), projected FCF with growth assumptions, WACC…
FX carry-trade analysis via Longbridge Securities — combines spot rates, interest-rate differentials (high-yield vs low-yield currencies), volatility, and historical price trends…
4-D prompt engineering assistant that transforms vague requirements into high-precision prompts through guided interaction.
Route AI/ML tasks to correct Yzmir pack - frameworks, training, RL, LLMs, architectures, production
Identify, analyze, and prioritize project risks using qualitative and quantitative methods. Develop mitigation strategies to minimize impact and maximize project success…
[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes.
Set up metrics collection and visualization with Prometheus and Grafana. Configure scrape targets, create PromQL queries, build dashboards, and implement alerting.
Build React chat interfaces with Vercel AI SDK v6. Covers useChat/useCompletion/useObject hooks, message parts structure, tool approval workflows, and 18 UI error solutio — from…
Expert security auditor specializing in comprehensive security assessments, compliance validation, and risk management.
Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for…
Transform textbook content based on the 10-dimension user profile to provide personalized learning experiences. Agent: AIEngineer
Provides expertise in converting Figma designs to HTML/CSS using Figma MCP tools, with data attributes for content tracking and comprehensive analysis.
React Flow 라이브러리를 사용한 노드 기반 UI 개발 지원. 노드/엣지 생성, 커스터마이징, 레이아웃, 상호작용 구현 시 사용. 항상 최신 문서를 WebFetch로 참조하여 정확한 정보 제공. — from majiayu000/claude-skill-registry-data
Creates a timestamped markdown draft file for iterating on long-form content like PR descriptions, release notes, or issue descriptions
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data.
Design RESTful or GraphQL APIs with proper conventions. Creates endpoint specifications, request/response schemas, and documentation.
Run structured What-If scenario analysis with 4–6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order).
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement — from majiayu000/claude-skill-registry
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, conn — from…
Query Prometheus metrics, check resource usage, and analyze platform performance in the Kagenti platform — from majiayu000/claude-skill-registry
Build AI agents with OpenAI Agents SDK, tool registration, conversation history, and stateless execution. Use when creating AI agents, registering tools, or handling conversations.
NestJS backend framework - modules, controllers, services, DI, guards, pipes, interceptors, exception filters, middleware, DTOs with class-validator
Sistema de planificación basado en archivos estilo Manus para organizar y rastrear el progreso de tareas complejas. Crea task_plan.md, findings.md y progress.md.
OpenCode - Open source AI coding agent for terminal, desktop, and IDE with multi-provider LLM support, custom agents, MCP integration, and granular permissions
Evolutionary mechanisms for the agent to rewrite its own prompts (Neuroplasticity).
High-level SDK for Azure AI Foundry projects with agents, connections, deployments, and evaluations. — from majiayu000/claude-skill-registry
Google Gemini CLI orchestration (v0.22.0+) for AI-assisted development. Capabilities: second opinion/cross-validation, real-time Google Search grounding, codebase architecture…
CRISPR library design for genetic screens. Covers sgRNA selection, library composition, control design, and oligo ordering.
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) opt — from…
Strategic positioning skill for developing differentiated market position, positioning statements, and competitive framing.
Remove batch effects from RNA-seq data using ComBat, ComBat-Seq, limma removeBatchEffect, and SVA for unknown batch variables.
AI 패턴 제거, 전지적 저자 시점, 체계적 인용을 통한 고품질 한국어 글쓰기 표준. 금지 어휘, 문장 종결 규칙, 어휘 다양화 전략을 정의한다. 콘텐츠를 작성하거나 검토하거나 품질을 검증할 때 사용한다. — from majiayu000/claude-skill-registry
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) opt — from…
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.
Use when building API endpoints with @frappe.whitelist() in Frappe. Covers endpoint design, permission patterns, error handling, client integration, file uploads, background jobs,…
Extracts and documents design tokens (colors, typography, spacing, shadows, etc.) from Figma designs. Updates the "デザイントークン" section in screen spec.md.
Use when seeking analogous solutions from other domains, when stuck on a problem and need fresh perspectives, or when evaluating whether approaches from field X might apply to…
Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root causes, and incorporates learnings into agent definitions.
Expert infrastructure security engineer specializing in DevSecOps, cloud security, and compliance frameworks.
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage — from…
Guide Test-Driven Development workflow for FastLED. Use when implementing new features or fixing bugs with a test-first approach.
Manage Google Cloud Secret Manager for storing and fetching environment secrets. Use when working with deployment, secrets, or gcloud commands.
LinkedIn Content-Erstellung, Engagement und Monitoring für B2B/Manufacturing. Regionale Anpassung (US/EU/Asien), Artikel mit Teasern, Bildgenerierung via Gemini, Kommenta — from…
Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR s — from…
Defines editorial priorities for AndesRC blog. Maps topics to funnel stages (TOFU/MOFU/BOFU), identifies pillar vs.
Runme.dev形式の実行可能マークダウン作成・編集用規約。 使用タイミング: (1) マークダウンファイルに実行可能なコードブロックを追加（verify.md, README.mdなど） (2) Runme.devセル設定の追加・編集（name, cwd, excludeFromRunAllなど） (3) runme fmtでフォーマット適用 (4)…
Auto-discovers and configures Language Server Protocol (LSP) servers for your project's languages
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Check task status in the tracker and local artifacts. Use when the user invokes /status or asks for project/task status.
Enforce feature work on a dedicated git branch and submission via pull request. Use when implementing any feature, fix, or refactor so work is isolated, reviewed, and merged via…
First principles analysis. USE WHEN first principles, fundamental, root cause, decompose. SkillSearch('firstprinciples') for docs. — from majiayu000/claude-skill-registry