AI-Driven Specification-Driven Development (SDD) workflow orchestrator - guides skill selection and general SDD methodology
Develop Ruby on Rails applications with models, controllers, views, Active Record ORM, authentication, and RESTful routes. Use when building Rails applications, managing database relationships,...
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.
Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM...
Modern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices. Covers project structure, tech stack selection, and best practices based on Go standards.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity...
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity...
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs...
Build TypeScript MCP servers with composable code snippets from the official Everything reference server. Use the add script to selectively copy tool, resource, or prompt modules. Use when...
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs...
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture,...
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture,...
Comprehensive test implementation across all domains including unit, integration, e2e, security, infrastructure, data pipelines, and ML models. Covers TDD/BDD workflows, test architecture, flaky...
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities,...
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with...
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with...
Modular orchestration of agent patterns from Anthropic's engineering guide. Intelligently selects and implements prompt chaining, routing, parallelization, orchestrator-workers,...
Create a Platform Strategy Pack (platform-as-product charter, interface map, lifecycle stage, ecosystem/moat model, governance, metrics, roadmap). Use for platform strategy, developer platforms,...
Run Claude Code CLI with GLM-4.7 model for AI code generation. Use when you need to generate code, debug, analyze files, or get AI programming assistance. Requires: Claude Code CLI + GLM-4.7 API...