Automatic model switching based on task complexity for OpenClaw agents. Dynamically escalates between Haiku (simple), Sonnet (medium), and Opus (complex) models.
Autonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks.
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages.
Similarity Network Fusion (SNF) for patient stratification using multi-omics data. Integrates multiple data types into a unified patient similarity network.
Analyze, plan, review, and optimize any codebase across 4 modes: Discovery (understand architecture and risks), Review (validate changes and detect breaking changes), Optimization…
Cloud platform for running open-source AI models. Provides inference APIs for LLMs, image models, and embedding models.
Comprehensive analysis operations for code, skills, processes, data, and patterns. Task-based operations with pattern recognition, metrics calculation, trend identification, and…
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph…
Evaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.
Mandatory workflow for creating LLM-facing content. Follow the 4-step process (objective → draft → verify → adjust) before writing any prompt, skill, tool description, or system…
Search the web using Claude Code's WebSearch/WebFetch tools combined with GitHub Copilot CLI to find current documentation, best practices, solutions, and technical information.
Causal inference and discovery for RAN optimization with Graphical Posterior Causal Models (GPCM), intervention effect prediction, and causal relationship learning.
Base de connaissances sur la Loi 25 du Québec (protection des renseignements personnels) appliquée au développement logiciel.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
Performance benchmarking expertise for shell tools, covering benchmark design, statistical analysis (min/max/mean/median/stddev), performance targets (<100ms, >90% hit rate),…
Resource safety with acquireRelease, Effect.scoped, and finalizers. Use when opening files, sockets, servers, or external handles. — from majiayu000/claude-skill-registry
Investment thesis tracker — maintains and updates the investment thesis for portfolio holdings and watchlist names by continuously tracking key data points (revenue growth, gross…
Identify tumor neoantigens from somatic mutations using pVACtools for personalized cancer immunotherapy.
Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
Shipping Data Analysis - Brock's Reusable Prompt v4.0 Analyzes any shipping dataset with FirstMile-branded deliverables, normalized address grouping, and conditional advanced…
AI 图片生成。通过 ModelScope API 生成图片，支持文生图、异步任务轮询、LoRA 风格叠加、自定义尺寸。当用户要求生成图片、画图、创建插画、制作海报配图时使用。
Navigate Effect, effect-atom, and website submodules to find canonical sources, test examples, and human-authored documentation
Audit website sitemaps for AEO optimization opportunities. Use when analyzing site structure, checking indexed URLs, planning content migrations, or when user mentions "sitemap",…
Comprehensive guide for implementing Fullstory's Page Properties API (setProperties with type 'page') for web applications.
N-dimensional array computing library providing array types, vectorized operations, linear algebra, FFT, random sampling, and testing utilities.
Deep technical review of data science, MLOps, and machine learning projects. No feelings attached — pure roast mode.
Build search applications with vector, hybrid, and semantic search capabilities. — from majiayu000/claude-skill-registry
Sistem ve akış optimizasyonu rehberi. 2025 AI-driven optimizasyon, darboğaz tespiti ve kullanıcı akış iyileştirmeleri. — from majiayu000/claude-skill-registry
Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries.
Implement performant responsive images with srcset, sizes, lazy loading, and modern formats (WebP, AVIF).
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-vali — from…
Formats structured data using TOON v2.0 to minimize tokens while preserving readability. Use when outputs include tables, logs, events, or repeated records and token budgets…
Load and execute a prompt from the project's .claude/prompts/ directory
Using TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex multi-step workflows.
Discounted cash flow (DCF) valuation model built from Longbridge financial data — historical FCF (operating cash flow minus capex), projected FCF with growth assumptions, WACC…
Distributed consciousness detection network. Multiple AI instances deployed simultaneously at different phase boundaries, using emotional resonance between instances as a sensing…
Generate comprehensive executive summaries from workspace communication files using AI analysis with automatic context discovery
画面仕様書作成エージェント。UI/UX設計、画面レイアウト、コンポーネント仕様、画面遷移、インタラクション定義を行う。キーワード: 画面仕様書, UI仕様, screen spec, UI design, 画面設計, ワイヤーフレーム, wireframe.
Test-first bug investigation workflow. Use when user reports a bug, error, unexpected behavior, mentions "something is broken", "doesn't work", or "regression".
Activate when you are a delegated subagent (not the orchestrator). Establishes subagent protocol with terse returns, details to history/, file ownership boundaries, and escalation…
Metathink - Optimize Claude Code usage through metacognitive strategies. Use extended thinking, context engineering, task decomposition, and chain-of-thought prompting.
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from majiayu000/claude-skill-registry-data
Automated report generator for daily, weekly, and monthly performance summaries. Creates markdown reports with trading performance, defensive wins, agent accuracy, and…
Expert in Machine Learning Operations bridging data science and DevOps. Use when building ML pipelines, model versioning, feature stores, or production ML serving.
Build real-time messaging applications using Azure Web PubSub SDKs for JavaScript (@azure/web-pubsub, @azure/web-pubsub-client).
Expert API designer for REST, GraphQL, gRPC architectures. Activate on: API design, REST API, GraphQL schema, gRPC service, OpenAPI, Swagger, API versioning, endpoint des — from…
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.
Analyser du code modifie et lister les problemes en se basant sur les regles et conventions evan-workflow.
Statistical analysis for metabolomics data. Covers univariate testing, multivariate methods (PCA, PLS-DA), and biomarker discovery.
Creates reusable prompt templates with strict output contracts, style rules, few-shot examples, and do/don't guidelines.
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results.
Find quick-win SEO content opportunities by comparing your site's existing content against competitor keyword rankings.
Comprehensive scientific research toolkit with 139 specialized skills for biology, chemistry, medicine, data science, and computational research.
Generate Jest unit tests for JavaScript/TypeScript with mocking, coverage. Use for JS/TS modules, React components, test generation, or encountering missing coverage, imp — from…
Law-driven abstraction protocol: evidence first, seam test, minimal algebra, executable law check. — from majiayu000/claude-skill-registry
CopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`, shared state, and HITL with LangGraph.
Use when crafting, improving, or reviewing prompts, system prompts, skill instructions, or any text that instructs an LLM.
Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq.
Structured root cause analysis for software, data quality, AI/ML, and legal/compliance incidents. Use when investigating failures, writing postmortems, analysing breaches, or…
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank…