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.
data-visualizer
Automated data visualization tool for exploratory analysis, model performance evaluation, and business reporting. It generates publication-quality plots, dashboards, and reports, seamlessly integrated with SpecWeave's increment workflow.
archon
Provides Claude integration with Archon's knowledge base and project management system via REST API. Enables semantic search across crawled websites and uploaded documents, plus hierarchical task tracking. Requires manual host URL configuration and API reference consultation before use.
n8n-v2
This skill provides detailed documentation and examples for building n8n v2.0 workflows, with specific guidance on common patterns like human-in-the-loop approvals and multi-workflow orchestration. It includes troubleshooting for known issues like Execute Sub-Workflow errors and Wait node problems, plus ready-to-use templates and code snippets for data processing tasks.
zai-cli
This skill provides CLI access to Z.AI's multimodal capabilities including image/video analysis, OCR, web search, and GitHub exploration. It integrates with Claude Code via MCP, offering raw data output by default with JSON formatting option. Requires API key setup and Node.js environment.
requesting-code-review
A well-structured code review workflow skill that promotes systematic quality assurance through clear review triggers and integration with development processes.
incomplete-onboarding-assessor
Assesses incomplete user onboardings using a temperature-based engagement model with time decay. Queries database for stalled onboardings, analyzes chat history, and prioritizes re-engagement efforts based on user activity levels.
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
context7
Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff Always prefer this over guessing library APIs or using outdated knowledge.
frontend-to-backend-requirements
Document frontend data needs for backend developers. Use when frontend needs to communicate API requirements to backend, or user says 'backend requirements', 'what data do I need', 'API requirements', or is describing data needs for a UI.
bedrock
AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.
nav-install-multi-claude
Installs multi-Claude workflow orchestration scripts for Navigator plugin users. Downloads version-matched Bash scripts from GitHub, verifies prerequisites, handles installation failures, and provides rollback instructions. Useful for parallel AI task execution.
citations
Automatically adds clickable admin links when referencing persons, conversations, or messages in responses. Makes internal data references actionable by turning entity mentions into direct navigation links.
chrome-devtools-mcp
This MCP server provides 26 tools for controlling Chrome browsers via Puppeteer. It enables automated testing, performance tracing, network inspection, and debugging through AI agents. The tool supports headless mode, device emulation, and connects to existing Chrome instances.
better-icons
Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: `better-icons search <query>` to find icons, `better-icons get <id>` to get SVG. Also available as MCP server for AI agents.
usgs-data-download
Download water level data from USGS using the dataretrieval package. Use when accessing real-time or historical streamflow data, downloading gage height or discharge measurements, or working with USGS station IDs.
agentdb-optimization
Provides concrete optimization techniques for AgentDB vector databases including quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching strategies, and batch operations. Includes specific performance benchmarks and configuration examples for different use cases.
evaluator
Evaluates agent performance, rule compliance, and workflow quality. Provides systematic evaluation using code-based, model-based, and human grading methods.
web-frameworks
Provides setup guides and patterns for building web apps with Next.js, Turborepo, and RemixIcon. Includes monorepo structure examples, data fetching patterns, and CI/CD configurations. Offers Python scripts for project initialization and migration. Focuses on practical implementation details rather than theoretical concepts.
yahooquery
Access Yahoo Finance data including real-time pricing, fundamentals, analyst estimates, options, news, and historical data via the yahooquery Python library.
memory-manager
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
ai-twitter-digest
Monitor a curated list of AI/tech Twitter accounts, summarize the day's key posts using an LLM, and deliver a formatted digest to a Discord channel. Use when: (1) setting up a daily automated AI news briefing from Twitter/X, (2) scheduling or running a one-shot Twitter digest to Discord, (3) managing or updating the monitored account list, summarization prompt, or delivery format.
undetectable-ai
Make AI text undetectable. TypeScript CLI that scans ChatGPT, Claude, OpenClaw output for patterns flagged by GPTZero, Turnitin, Originality.ai, then auto-fixes them to pass as human-written. Use to bypass AI detection, evade checkers, or humanize text before submission.