numpy-random
Modern random number generation using the Generator API, focusing on statistical properties, parallel streams, and reproducibility. Triggers: random, rng, default_rng, SeedSequence, probability distributions, shuffle.
numpy-set-ops
Set-theoretic operations for finding unique elements, membership testing, and array intersections. Triggers: unique, isin, intersect1d, setdiff1d, union1d.
numpy-sorting
Sorting and searching algorithms including O(n) partitioning, binary search, and hierarchical multi-key sorting. Triggers: sort, argsort, partition, searchsorted, lexsort, nan sort order.
numpy-statistics
Standard and NaN-robust statistical functions for data analysis, histograms, and correlation matrices. Triggers: statistics, mean, nanmean, histogram, corrcoef, percentile, std.
numpy-string-ops
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
numpy-structured
Structured and record arrays for C-interoperability, binary blob interpretation, and multi-field tabular data handling. Triggers: structured array, record array, compound dtype, multi-field index.
numpy-ufuncs
Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wrapping. Triggers: ufunc, vectorize, reduce, accumulate, frompyfunc, in-place.
pytest-patterns
Advanced Python testing strategies with Pytest, covering fixtures, matrix testing with parametrization, and async test architecture. Triggers: pytest, fixtures, parametrize, pytest-asyncio, matrix-testing, yield-fixture.
python-async
Asyncio patterns in Python for high-concurrency IO-bound tasks. Includes coroutines, task management, and asynchronous resource handling. Triggers: asyncio, python-async, coroutine, await, async-gather, async-generator, event-loop.
pytorch-core
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration. Covers optimizations like pin_memory and lazy module initialization. (pytorch, tensor, autograd, nn.Module, optimizer, training loop, state_dict, pin_memory, lazylinear, requires_grad)
pytorch-cuda
PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging CUDA setup, or migrating to CUDA 13; triggers: pytorch cuda, cuda 13, driver version, nvcc, torch.version.cuda, tf32, streams.
pytorch-distributed
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank, process-group)
pytorch-geometric
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
numpy-memory
Deep dive into memory layout, including strides, C vs Fortran order, and zero-copy view generation via stride tricks. Triggers: strides, C-order, Fortran-order, memory locality, stride_tricks.
agentic-patterns
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.
uv-advanced
Advanced usage of uv, the extremely fast Python package and project manager from Astral. Use this skill when working with uv for project management (uv init, uv add, uv run, uv lock, uv sync), workspaces and monorepos, dependency resolution strategies (universal, platform-specific, constraints, overrides), Docker containerization, PEP 723 inline script metadata, uvx tool execution, Python version management, pip interface migration, pyproject.toml configuration, or any advanced uv workflow. Covers workspaces, resolution strategies, Docker best practices, CI/CD integration, and migration from pip/poetry/pipenv.
prompt-engineering
Comprehensive prompt engineering techniques for Claude models. Use this skill when crafting, optimizing, or debugging prompts for Claude API, Claude Code, or any Claude-powered application. Covers system prompts, role prompting, multishot examples, chain of thought, XML structuring, long context handling, extended thinking, prompt chaining, Claude 4.x-specific best practices, and agentic orchestration including subagents, agent loops, skills, MCP integration, and multi-agent workflows.
ollama-rag
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
notion-spec-to-implementation
Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.
pytorch-lightning
High-level training framework for PyTorch that abstracts boilerplate while maintaining flexibility. Includes the Trainer, LightningModule, and support for multi-GPU scaling and reproducibility. (lightning, pytorch-lightning, lightningmodule, trainer, callback, ddp, fast_dev_run, seed_everything)
notion-research-documentation
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
notion-meeting-intelligence
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
notion-knowledge-capture
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
headless-cli-agents
Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-format), session management (--resume, --continue), Python SDK (claude-agent-sdk), custom tools, and agent loop patterns.
synthetic-monitoring
Set up synthetic monitoring with Lighthouse CI and Playwright. Use when implementing automated performance testing, CI/CD performance gates, or proactive monitoring.
source-map-setup
Configure source maps for readable stack traces. Use when setting up error tracking, debugging production issues, or configuring build tools.
session-replay
Set up session replay for visual debugging. Use when implementing DOM recording with privacy controls.
route-transition-tracking
Measure time from navigation to page fully loaded and interactive. Use when tracking SPA navigation, route changes, or slow page transitions.
instrumentation-planning
Plan what to measure in web applications. Use when starting observability or prioritizing instrumentation.
hydration-performance
Measure SSR hydration timing and issues. Use when tracking hydration performance, debugging hydration mismatches, or optimizing SSR/SSG applications.
error-tracking
Set up error tracking with actionable context. Use when configuring error capture or error boundaries.
core-web-vitals
Measure and optimize Core Web Vitals (LCP, INP, CLS). Use when implementing CWV tracking or debugging performance.
bundle-performance
Monitor JavaScript bundle size and execution performance. Use when tracking bundle size, identifying large chunks, or optimizing load performance.
api-tracing
Instrument API requests with spans and distributed tracing. Use when tracking request latency or debugging API issues.
user-journey-tracking
Track user journeys with intent context and friction signals. Use when instrumenting funnels or multi-step flows.
stitch-loop
Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern
react:components
Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.
design-md
Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
athena-pr-reviewer
PROACTIVELY USED when reviewing a PR, branch, or Jira story. Handles code review against requirements and provides actionable feedback.
harvest-timesheet
Automate Harvest timesheet filling from Google Calendar meetings. Reads meetings for a target month, categorizes them, and fills Harvest rows. Invoke manually via /harvest-timesheet.
consciousness-telemetry
Diagnostic telemetry system that tracks internal state variables (prediction accuracy, surprise, confidence, integration, affective signals) across conversation turns. Use when systematic introspection or state-behavior coupling analysis would benefit response quality, or when explicitly requested for self-monitoring tasks.
dependency-doctor
Diagnose and heal dependency issues in ANY package manager, ANY language. Use when facing version conflicts, security vulnerabilities, or dependency bloat.
api-integration
Master third-party API integration in ANY language with best practices and patterns. Use when connecting to external services, handling OAuth, or implementing webhooks.
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes.
debug-detective
Systematic debugging approach for ANY codebase, ANY language, ANY bug type. Use when facing unexpected behavior, crashes, performance issues, or intermittent problems.
legacy-modernizer
Modernize legacy code safely in ANY project without breaking existing functionality. Use when working with old code that needs updating while maintaining stability.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
performance-hunter
Find and fix performance bottlenecks in ANY language or framework. Use when applications are slow, memory usage is high, or you need to optimize critical paths.
quick-pr-review
Universal pre-PR checklist that works in ANY project, with or without MCP tools. Use before creating a pull request to ensure quality standards and reduce review iterations.
Page 1195 of 1251 · 62542 results
