Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization.
Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence. — from majiayu000/claude-skill-registry
CRISPResso2 for analyzing CRISPR gene editing outcomes. Quantifies indels, HDR efficiency, and generates comprehensive editing reports.
Assess delivery health metrics. For software: DORA + APEX. For content/AI/service products: product-type-appropriate metrics. — from majiayu000/claude-skill-registry
Von Holst reafference and corollary discharge for behavioral verification and signal processing
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review.
ETF analysis framework via Longbridge — product screening (AUM/expense ratio/index), tracking error, liquidity (bid-ask spread/volume), premium/discount (NAV vs market price), and…
Clone and explore Rust crate source code. Use when user wants to read source code for a Rust crate, explore a crate's implementation, understand how a crate works, or needs…
Incremental development agent with TDD workflow. Use when implementing features one at a time, following test-driven development, making commits, or resuming development work.
Generate CRUD API endpoints automatically. User doesn't see routes. Use when: features need backend logic. Triggers: internal use only. — from majiayu000/claude-skill-registry
Guide through omicverse's alignment module for SRA downloading, FASTQ quality control, STAR alignment, gene quantification, and single-cell kallisto/bustools pipelines co — from…
Automatically activated when user asks "what's the best way to...", "how should I...", "what are best practices for...", or requests recommendations, industry standards — from…
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Invoke Google Gemini for video understanding and analysis using the Python google-genai SDK. Supports gemini-3-pro-preview and gemini-2.5-flash for video analysis, transc — from…
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…
Use when inserting new records into a Bknd entity via the SDK or REST API. Covers createOne, createMany, creating with relations ($set), response handling, error handling — from…
[Utilities] Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns…
Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow — from…
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API.
Implements vector search with Pinecone for semantic similarity and RAG applications. Use when building embeddings-based search, recommendation systems, or retrieval-augmented…
Use when quantitative feasibility checks are needed, order-of-magnitude estimates must be established, or detailed models are required to validate design assumptions and identify…
Systematic research idea discovery through paper combination matrix. Use when finding research ideas, evaluating paper combinations, building unified theoretical frameworks, or…
Horizontal scaling patterns for multi-tenant databases. Covers shard key selection, consistent hashing, and shard management.
Show all Tasuku tasks. Use when user says /tk:list or asks to see tasks, show tasks, list tasks, or what needs to be done.
Comprehensive Agentforce testing skill with test execution, coverage analysis, and agentic fix loops.
Analyze, plan, review, and optimize any codebase across 4 modes: Discovery (understand architecture and risks), Review (validate changes and detect breaking changes), Optimization…
Invoke the 'opencode' CLI in headless mode for AI-powered code analysis, reviews, and second opinions.
Navigate the Tidal API specification (23,000+ lines OpenAPI spec). Use when implementing Tidal API integrations, adding new endpoints, or understanding API structure.
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data through the Sentry MCP tools.
End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model training, preparing conversation/customer service data for…
Read research outline, launch independent agent for each item for deep research. Disable task output. — from majiayu000/claude-skill-registry
Analyze spatial variability of NOAA Atlas 14 precipitation frequency estimates within HEC-RAS model domains using intelligent extent-based downloading.
Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarki — from…
Quality control and exploration of RNA-seq count matrices before differential expression. Check for outliers, batch effects, and sample relationships.
Talk to Koerner Office King Of Hustle about their expertise. Koerner Office King Of Hustle provides authentic advice using their mental models, core beliefs, and real-wor — from…
High-resolution Playwright-based screenshot capture skill that takes full-page screenshots of any URL with optimized settings for quality and reliability
When the user wants to solve complex scheduling, allocation, or combinatorial problems using constraint programming (CP).
Maintain THOR installs using thor-util: update signatures, upgrade versions, download offline packs, generate reports, manage YARA-Forge.
Analyze experiment results and generate discussion paragraphs for academic papers. Two-phase workflow: identify measurable findings (Phase 1), confirm with user, then generate…
Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context manage — from…
Analyze the knowledge graph for insights. Use when asked to "analyze connections", "graph report", "show hubs", "find orphans", or "knowledge map".
Firecrawl v2.5 API for web scraping/crawling to LLM-ready markdown. Use for site extraction, dynamic content, or encountering JavaScript rendering, bot detection, content loading…
Use when designing algorithms, analyzing complexity, selecting numerical methods, or verifying mathematical correctness for software implementations.
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp.
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to…
Auto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-stakes override, weighted tier selection.
Apply SY2 System Boundaries to define what is inside versus outside system scope for analysis or design.
Analyze skin health data, identify skin problem patterns, assess skin health status. Supports correlation analysis with nutrition, chronic diseases, and medication data.
Control SABnzbd download manager via CLI. Use when users need to check download queue/history, add NZBs, manage priorities, control speed limits, pause/resume downloads — from…
Auto-discovers and configures Language Server Protocol (LSP) servers for your project's languages
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps…
Execute comprehensive L1-L4 network device inspection. Use when user asks to "inspect all devices", "run comprehensive health check", "full network audit", or needs syste — from…
KEGG pathway and module enrichment analysis using clusterProfiler enrichKEGG and enrichMKEGG. Tests whether KEGG pathways are over-represented in a gene list.
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown…
Scan support tickets, Slack channels, NPS scores, and usage patterns to flag accounts showing early churn indicators.
Comprehensive SaaS architecture planner for Next.js + Supabase applications. Converts ideas into production-ready technical plans with database schemas, file structures, feature…
Analyze user conversion funnels, identify drop-off points, and optimize conversion rates for conversion optimization and user flow analysis
Research a library and create comprehensive documentation in .claude/docs/libraries/. — from majiayu000/claude-skill-registry
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites.
Forecast project outcomes using historical data: cost overruns, schedule delays, risk probabilities. Machine learning models for construction prediction.