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.
knowledge-synthesizer
A specialized agent for extracting insights from multi-agent interactions. It analyzes workflows, identifies patterns, and builds a knowledge graph to suggest improvements. It integrates with vector and graph databases to store and retrieve learnings.
using-git-worktrees
A skill for creating isolated git worktrees with systematic directory selection and safety checks. Automatically detects project type, runs setup commands, verifies tests pass, and ensures worktree directories are properly gitignored to prevent accidental commits.
moai-platform-clerk
Provides detailed implementation guidance for Clerk authentication in Next.js apps, covering setup, middleware, hooks, and integrations. Includes specific code examples for WebAuthn, passkeys, and third-party services like Supabase and Convex. Focuses on practical deployment steps and common use cases.
github-workflow-automation
An ambitious GitHub workflow automation concept with AI swarm coordination, offering comprehensive templates but lacking implementation details and dependency clarity.
baidu-search
百度 AI 搜索。支持网页搜索、百度百科、秒懂百科、AI 智能生成四种模式。自动包含当前日期上下文。当用户要求搜索信息、查询百科、获取最新资讯、搜索新闻、查找资料时使用。
context-degradation
This skill helps diagnose and fix context degradation in AI agents. It identifies patterns like lost-in-middle effects and context poisoning, provides monitoring tools, and suggests recovery strategies for long-running conversations.
model-registry-maintainer
Guide for maintaining the MassGen model and backend registry. This skill should be used when adding new models, updating model information (release dates, pricing, context windows), or ensuring the registry stays current with provider releases. Covers both the capabilities registry and the pricing/token manager.
using-git-worktrees
A well-structured skill for creating isolated Git worktrees with smart directory selection, safety verification, and automated project setup for parallel feature development.
dispatching-parallel-agents
This skill provides a pattern for dispatching multiple AI agents to investigate independent test failures concurrently. It includes clear trigger conditions, decision flow, and prompt templates for creating focused agent tasks. The approach reduces investigation time when dealing with unrelated bugs across different files or subsystems.
mcp
This Skill provides documentation and guidance for Splitrail's MCP server implementation, which exposes usage statistics and analytics tools to AI assistants. It clearly explains available tools like get_daily_stats and get_model_usage, shows how to run the server, and provides concrete steps for extending the system with new tools and resources.
defense-in-depth
Provides a systematic approach to data validation across four layers: entry points, business logic, environment guards, and debug instrumentation. Includes concrete TypeScript examples and a real bug case study showing how multiple validation points prevent data corruption issues.
claude-code-agents
Provides a reference framework for creating Claude Code agents with YAML frontmatter configuration. Defines agent structure, tool permissions, model selection, and includes hook system for pre/post-processing. Offers templates for different agent types like analyzers, implementers, and orchestrators.
performance-monitor
A comprehensive performance monitoring expert skill with extensive coverage of monitoring concepts, tools, and workflows, well-structured for system observability and optimization tasks.
startup-review-mining
This skill provides structured templates and methodologies for extracting actionable insights from customer reviews across multiple platforms. It focuses on identifying pain points, feature gaps, and competitive weaknesses, with specific guidance for B2B software, B2C apps, and tech communities. Includes bias hygiene checks and frameworks for turning insights into product experiments.
ethicist-analyst
This skill analyzes ethical dilemmas and decisions using established moral frameworks like deontology and consequentialism, providing structured reasoning for technology, policy, and professional conduct issues.
executive-data-storytelling
Provides a structured framework for converting data into executive narratives using Gartner's What/Why/Next method. Includes specific examples, slide design principles, and alignment with CEO priorities like growth and technology. Helps avoid common presentation pitfalls like jargon overload and missing action items.
fact-check
Verify technical accuracy of JavaScript concept pages by checking code examples, MDN/ECMAScript compliance, and external resources to prevent misinformation
zapier-workflows
This skill bridges Zapier's MCP tools with webhook-triggered Zaps, providing persistent memory for workflow preferences. It solves the gap between one-off actions and multi-step automations by storing trigger phrases, webhook URLs, and tool patterns in editable reference files. Users can trigger complex Zaps via curl commands and maintain consistent tool usage across sessions.
fda-consultant-specialist
Senior FDA consultant and specialist for medical device companies including HIPAA compliance and requirement management. Provides FDA pathway expertise, QSR compliance, cybersecurity guidance, and regulatory submission support. Use for FDA submission planning, QSR compliance assessments, HIPAA evaluations, and FDA regulatory strategy development.
repo-research-analyst
This skill systematically analyzes code repositories to identify structure, conventions, and contribution patterns. It follows a four-step research process examining documentation, templates, and code patterns, then generates a detailed markdown handoff with findings. It helps developers understand unfamiliar codebases quickly.
software-manual
Generates interactive single-file HTML software manuals with automated screenshot capture and API documentation extraction. Uses a multi-phase agent architecture to explore codebases, create structured content, and assemble TiddlyWiki-style documents with embedded resources.
parallel-workflows
This skill identifies independent tasks in Claude Code and runs them concurrently using the Task tool. It provides clear patterns for parallel analysis, testing, and component development, with practical examples and performance metrics showing 55-67% speed improvements.
home-assistant
Provides Python scripts to interact with Home Assistant instances via API. Queries entities, services, and automations, generates YAML configurations, and debugs automation traces. Helps users manage smart home setups through direct CLI access to their HA installation.
implementation-phase
Executes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project)