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.
BrowserBridge
Provides real-time browser interaction through a local WebSocket bridge server. Enables JavaScript execution, DOM inspection, and screenshot capture from Claude Code. Useful for debugging web applications without switching contexts.
agentdb-memory-patterns
Provides memory management patterns for AI agents using AgentDB's persistent storage. Offers session memory, long-term storage, pattern learning, and context management with 150x-12,500x performance improvements over traditional solutions. Includes CLI tools, API examples, and integration with reasoning agents.
n8n-automation
Provides n8n workflow templates and patterns for integrating SkySpark building analytics with multi-agent systems. Includes FastAPI tool server templates, mock data generation, and a phased roadmap from foundation to production deployment.
github-issue-breakdown
Automates creation of official GitHub sub-issues from task lists in parent issues using GraphQL API. Parses markdown checkboxes and lists, shows previews, creates proper parent-child relationships, and inherits metadata like labels and assignees.
skill-creator
Provides structured guidance for creating Claude Skills with clear templates and progressive disclosure patterns. Includes practical examples for scripts, references, and assets organization. Helps developers extend Claude's capabilities with specialized workflows and tool integrations.
smart-rules
Automatically loads relevant project documentation based on task keywords. Scans project files to create category mappings, then matches user prompts to load only needed rules. Triggers after TodoWrite or before implementation tasks to ensure developers have proper context.
parties
This skill provides a structured reference for parallel agent deployment patterns in Claude. It documents three party protocols (search, QA, planning) with specific team structures, probe counts, and invocation commands. The documentation includes organizational hierarchies, D&D-themed probe lenses, and IDE crash prevention warnings.
update-migration-log
A focused tool for logging file migration details to a dedicated markdown log. It provides a detailed template for recording changes, issues, and verification steps after moving code files, ensuring a consistent audit trail for refactoring projects.
cloudflare
Provides detailed guidance for building applications on Cloudflare's edge platform, covering Workers, D1, KV, R2, Durable Objects, and AI features. Includes setup steps, code examples, and configuration details for each service.
cfn-cerebras-coordinator
Coordinates fast code generation using Z.ai glm-4.6 with RuVector pattern learning. Tracks successful prompts for improvement, automatically tests generated code, and provides metrics on prompt effectiveness. Best for repetitive boilerplate, test generation, and agent offloading tasks.
cfn-marketing-social-publishing
This skill provides shell scripts to manage social media posts through n8n workflows. It handles post creation, scheduling, media uploads, stats retrieval, and deletion across Facebook, Twitter, LinkedIn, and Instagram. The scripts pass parameters to n8n endpoints and return JSON responses with success/error codes.
cfn-marketing-crm-contacts
Provides shell scripts to manage CRM contacts through n8n workflows. Handles basic CRUD operations and segment management with clear parameter validation and error codes. Integrates with existing n8n instances via HTTP calls.
2_skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
feedback-handler
Manages human feedback requests within automated workflows by posting structured questions to GitHub issues and tracking responses. Handles six feedback types with clear state management and event emission.
session-start-hook
Configures automatic setup scripts for Claude Code web sessions. Installs dependencies, sets environment variables, and prepares development environments when remote sessions start. Includes templates for Node.js, Python, Ruby, Go, and full-stack projects with environment detection.
android-testing
Comprehensive testing strategy involving Unit, Integration, Hilt, and Screenshot tests.
literature-engineer
Multi-route literature expansion + metadata normalization for evidence-first surveys. Produces a large candidate pool (`papers/papers_raw.jsonl`, target ≥200) with stable IDs and provenance, ready for dedupe/rank + citation generation. **Trigger**: evidence collector, literature engineer, 文献扩充, 多路召回, snowballing, cited by, references, 200篇, 元信息增强, provenance. **Use when**: 需要把候选文献扩充到 ≥200 篇并补齐可追溯 meta（survey pipeline 的 Stage C1，写作前置 evidence）。 **Skip if**: 已经有高质量 `papers/papers_raw.jsonl`（≥200 且每条都有稳定标识+来源记录）。 **Network**: 可离线（靠 imports）；雪崩/在线检索需要网络。 **Guardrail**: 不允许编造论文；每条记录必须带稳定标识（arXiv id / DOI / 可信 URL）和 provenance；不写 output/ prose。
create-skill
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends CoPilot's capabilities with specialized knowledge, workflows, or tool integrations.
beautiful-mermaid
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.
farm-monitor
Provides setup and configuration guidance for Braiins Farm Monitor, a free Prometheus/Grafana stack for Bitcoin mining fleet monitoring. Includes Docker commands, config examples, and troubleshooting notes. Documentation is sourced from GitHub README.
ORCHESTRATION_DEBUGGING
Provides structured debugging workflows for AI orchestration systems, specifically targeting MCP tool failures, agent communication issues, and database problems. Includes phase-based investigation methods, log analysis templates, and concrete commands for checking backend, MCP server, and database status.
task-add
A specialized MCP skill that automatically adds structured tasks with mandatory subtasks to markdown documents. It enforces strict formatting rules for parallel development, preventing file conflicts by ensuring tasks are independent and properly decomposed.
llm-evaluation
A comprehensive and well-structured LLM evaluation skill covering automated metrics, human evaluation, and LLM-as-judge patterns with practical code examples.
frontend-dev-guidelines
A comprehensive and well-structured frontend development guide that provides clear patterns, practical checklists, and modern React/TypeScript best practices for team consistency.