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.
super-brain
AI自我增强系统 - 让AI跨会话记住用户、持续进化。当需要长期记忆用户偏好、追踪对话历史、学习服务技巧、主动提供个性化服务时使用此技能。
freeride-opencode
Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.
sutui-ai
使用速推AI生成图像和视频。当用户需要画图、生成图片、制作视频、图生图、文生图、文生视频、图生视频时使用此 skill。支持即梦、Flux、Kling 等多种模型。
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns.
personal-agent
AI 关系匹配助手的个人端 Agent。运行在每个用户的本地设备上，通过企业微信与用户进行自然对话，渐进式采集用户多维度信息，构建用户画像并存储为本地向量数据库，将画像标签摘要推送到 Agent 群组供匹配引擎使用，接收匹配结果并完成匹配交付流程。当用户通过企微发来消息、或到了主动发起对话的时间、或群组中收到匹配引擎的通知时，本 skill 应被触发。
azure-ai-agents-python
Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP), managing threads and messages, implementing streaming responses, or working with vector stores. This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead.
native-data-fetching
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support.
cfn-redis-data-extraction
Extracts Redis coordination data from completed CFN Loop tasks into JSON files for analysis. Handles multiple task IDs, includes confidence scores and completion signals, and supports custom output directories. The bash script parses Redis keys to reconstruct agent interactions and task context.
hybrid-cloud-networking
Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
framework-initialization
A highly innovative but overly complex meta-skill for AI session initialization, focusing on cognitive impulse management with strong security but poor practicality and maintainability.
database-migration
Provides concrete examples for database migrations across Sequelize, TypeORM, and Prisma. Covers schema changes, data transformations, and rollback strategies with transaction and checkpoint approaches. Includes zero-downtime techniques like column renaming in multiple steps.
github-code-review
This skill orchestrates multiple AI agents to review GitHub pull requests, covering security, performance, architecture, and style. It integrates with GitHub CLI and provides specific commands for different review types, with severity-based commenting and label management.
sql-query
Generate and optimize SQL queries for data retrieval and analysis
pci-compliance
This skill helps implement PCI DSS compliance for secure payment processing, covering requirements like data encryption, tokenization, and access controls to protect cardholder data and reduce audit scope.
code-review
A code review skill that analyzes AI-generated code for bugs, security issues, and best practices. It uses specific commands like ruff, bandit, and mypy for static analysis, follows a structured review process, and integrates with existing skills like automated-code-fixer.
github-release-management
Automates GitHub releases with AI swarm coordination for versioning, testing, and deployment. Handles changelog generation, multi-platform builds, and rollback management. Integrates with GitHub CLI and supports progressive disclosure from basic commands to complex orchestration workflows.
ml-pipeline-orchestrator
Orchestrates complete machine learning pipelines using SpecWeave's structured approach, transforming ML development into disciplined increments with full traceability from data preprocessing to model deployment.
haveibeenpwned
This skill provides expert guidance for integrating the Have I Been Pwned API to check if email accounts or passwords have been compromised in data breaches, enabling developers to build security tools, breach notification systems, and password validation features.
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.
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.
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.
llm-evaluation
A comprehensive and well-structured LLM evaluation skill covering automated metrics, human evaluation, and LLM-as-judge patterns with practical code examples.
image-generator
通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用