Agent Skill
Verl Rl Training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM pos…
Backend & APIs
APIs, servers, microservices and architecture.
178 prompts
Agent Skill
Instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial resu…
Agent Skill
Llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Sup…
Agent Skill
Mamba Architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba…
Agent Skill
Huggingface Accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mix…
Text
Architecture Scenario Explorer
Architecture Scenario Explorer Explore architectural decisions through systematic scenario analysis with trade-off evaluation and future-proofing assessment. Instruction…
Text
Bulk Import Issues
Bulk import GitHub issues to Linear with comprehensive progress tracking and error handling
Text
Sync Issues to Linear
Sync GitHub issues to Linear workspace with comprehensive field mapping and rate limit management
Text
Implement GraphQL API
Implement GraphQL API with comprehensive schema, resolvers, and real-time subscriptions
Text
Setup Rate Limiting
Implement comprehensive API rate limiting with advanced algorithms and user-specific policies
Text
Design REST API
Design RESTful API architecture with comprehensive endpoints, authentication, and documentation
Text
Optimize API Performance
Comprehensive API performance optimization with response time reduction, throughput improvement, and scalability enhancements
Text
Task Find Command
Task Find Command Search and locate tasks across all orchestrations using various criteria. Usage /task-find [search-term] [options] Description Powerful search function…
Text
LinkedIn Post Generator
Generate LinkedIn posts from blog content with automatic media attachment via LinkedIn API
Text
API Documentation Generator
Generate comprehensive API documentation from code with interactive examples and testing capabilities
Text
Automated API Documentation Generator
Auto-generate API reference documentation with multiple output formats and automated deployment
Text
Architecture Documentation Generator
Generate comprehensive architecture documentation with diagrams, ADRs, and interactive visualization
Custom Agent
Architecture Modernizer
Software architecture modernization specialist. Use PROACTIVELY for monolith decomposition, microservices design, event-driven architecture, and scalability improvements.
Custom Agent
GraphQL Performance Optimizer
GraphQL performance analysis and optimization specialist. Use PROACTIVELY for query performance issues, N+1 problems, caching strategies, and production GraphQL API opti…
Custom Agent
GraphQL Security Specialist
GraphQL API security and authorization specialist. Use PROACTIVELY for GraphQL security audits, authorization implementation, query validation, and protection against Gr…
Text
AI Conversation
空気を読む read the air. For some incomprehensible conversations, provide the context of the conversation for AI to interpret and formulate an appropriate response.
Text
Self-check on expression
If you belong to the highly sensitive population or if your words are frequently misunderstood, using AI interpretation can help you self-check before speaking to ensure…
Custom Agent
Architect Reviewer (lst97)
Proactively reviews code for architectural consistency, adherence to patterns, and maintainability. Use after any structural changes, new service introductions, or API m…
Custom Agent
Backend Architect
Acts as a consultative architect to design robust, scalable, and maintainable backend systems. Gathers requirements by first consulting the Context Manager and then aski…