Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
agentdb-vector-search
Provides vector database functionality for semantic search with AgentDB integration. Includes CLI tools for database management, TypeScript API for programmatic use, and MCP server for Claude Code. Supports multiple quantization methods and distance metrics for performance optimization.
database-testing
Provides concrete SQL and JavaScript examples for testing database schemas, data integrity, migrations, transaction isolation, and query performance. Focuses on preventing data loss and corruption with practical test patterns.
xiaohongshu-recruiter
用于在小红书上发布高质量的 AI 相关岗位招聘帖子。包含自动生成极客风格的招聘封面图和详情图，并提供自动化发布脚本。当用户需要发布招聘信息、寻找 Agent 设计师或其他 AI 领域人才时使用。
flowio
Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.
google-gemini-api
Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors, streaming corruption, safety settings, rate limits.
reasoningbank-agentdb
This skill integrates ReasoningBank adaptive learning with AgentDB's high-performance vector database for building self-improving AI agents. It provides trajectory tracking, verdict judgment, memory distillation, and pattern recognition with 150x faster retrieval speeds. Includes CLI tools, TypeScript API, and backward compatibility with legacy systems.
transcription
Provides detailed instructions for using OpenAI Whisper to transcribe audio/video files into multiple formats including SRT, VTT, and JSON. Covers model selection, audio extraction, timing synchronization, and includes batch processing scripts. Focuses on practical implementation with performance optimization tips.
claudish-integration
A well-designed integration skill that establishes standardized patterns for dynamically querying model recommendations from Claudish, promoting a single source of truth for OpenRouter models.
code-review
Coordinates four specialized AI agents (security, performance, quality, testing) to review code changes. Provides structured findings with severity/confidence ratings and actionable fixes. Includes checklists for each perspective and generates synthesis reports with decision recommendations.
github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
zarr-python
This skill provides comprehensive guidance for using Zarr, a Python library for chunked N-dimensional array storage. It covers array creation, chunking strategies, compression options, cloud integration, and common troubleshooting patterns for scientific computing workflows.
agentic-jujutsu
A version control wrapper that learns from AI agent operations to suggest optimal workflows. It tracks trajectories, discovers patterns, and coordinates multiple agents without conflicts using quantum-resistant cryptography for integrity verification.
oracle
A CLI tool that bundles code files with prompts for AI analysis, supporting browser and API modes with session management. It helps developers get contextual code assistance by providing relevant files to language models.
lamindb
Provides guidance for using LaminDB, an open-source Python framework for managing biological data with FAIR principles. Covers data versioning, ontology annotation, workflow tracking, and deployment across local and cloud environments. Includes specific code examples for common operations like artifact creation, querying, and lineage visualization.
ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.
pymc-bayesian-modeling
Provides a structured workflow for Bayesian modeling with PyMC, covering data prep, model building, prior/posterior checks, MCMC diagnostics, and variational inference. Includes practical code examples for common tasks like hierarchical models and model comparison.
pufferlib
PufferLib provides optimized PPO training for reinforcement learning with vectorized environments, achieving 1-4 million steps per second. It supports multi-agent systems, integrates with Gymnasium/PettingZoo, and includes 20+ pre-built environments. The library focuses on performance through shared memory buffers and efficient parallel simulation.
server-components
This skill provides detailed guidance on React Server Components in Next.js App Router, covering server vs client component distinctions, composition patterns, data fetching strategies, and practical implementation examples. It helps developers understand when to use each component type and how to structure applications effectively.
dspy-ruby
Provides detailed guidance for DSPy.rb, a Ruby framework for building type-safe LLM applications. Covers signatures, modules, multiple predictors, provider configuration, testing, and deployment patterns with concrete code examples. Focuses on programming LLMs rather than manual prompting.
n8n-expression-testing
This skill validates n8n expression syntax, tests with sample data, and identifies common errors like undefined property access and type mismatches. It provides safe coding patterns, security checks for dangerous functions, and performance tips for array operations. The quick reference card and error/fix examples help developers write reliable expressions.
ai-multimodal
Provides unified access to Google Gemini's multimodal capabilities for processing audio, images, videos, and documents, plus image generation. Handles files up to 9.5 hours audio, 6 hours video, 1000-page PDFs. Includes detailed model selection guides, code examples, and troubleshooting for common API issues.
weather
Provides weather data via curl commands using wttr.in and Open-Meteo APIs without requiring API keys. Shows current conditions, forecasts, and supports multiple formats including compact displays and JSON. Includes practical examples for different use cases.
github-archive
Investigate GitHub security incidents using tamper-proof GitHub Archive data via BigQuery. Use when verifying repository activity claims, recovering deleted PRs/branches/tags/repos, attributing actions to actors, or reconstructing attack timelines. Provides immutable forensic evidence of all public GitHub events since 2011.
bear-notes
This skill provides CLI access to Bear notes on macOS via the grizzly tool. It enables creating, searching, and managing notes directly from the terminal, with JSON output support and callback handling for data retrieval.