Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
-
Updated
Apr 19, 2026
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执行图从拓扑序变成关键路径最优调度" ; 唯一把场景叙事依赖建模为 DAG、以 CPM 算法驱动并行调度的影视生成引擎
Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.
🔥 🔥 Alternative to JSON 🔥 🔥
AI-Native 开发工作流方法论:4-Phase 框架 + 空项目/已有源码两种场景 + 反模式速查。让 Claude Code 等 AI agent 在共享契约下并行干活。
FlowLLM: Simplifying LLM-based HTTP/MCP Service Development
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 450+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
Supercharge qwen-code with hybrid prompt-chaining, powered by gemini-cli integration. Performance improvements include 72% faster execution, 36-83% token efficiency gains, and 91.7% success rate verified across 5 repository benchmarks.
Force any OpenAI-compatible or Anthropic API-compatible tool (Claude Code, Qwen Code, Aider, Fabric, Interpreter) to use Gemini, Groq, Cerebras, or Ollama. Pure Bash. Zero dependencies.
LLM Framework for LLMs
Reusable agent rules, templates, subagents, and skills for AI-assisted software delivery.
A prompt-based AI project runtime for structured activation, roadmap-first execution, active-step artifacts and handoff continuity.
A battle-tested framework for AI-assisted development. Session handoffs, knowledge preservation, and structured workflows. Zero dependencies.
Structured AI coding workflow initializer for Claude Code and Codex with .ai/ task planning, reviewer roles, and model-agnostic AGENTS.md / CLAUDE.md setup.
Agent-style LLM orchestration framework for composable AI workflows
A review-gated research wiki built inside Obsidian with the Claudian plugin — turn academic papers into a self-maintaining, citable knowledge base.
CLI tool for LLM prompt pipelines. Reusable. Shareable. Scriptable.
Build polished PPT-style HTML slides with a blueprint → review → HTML → review workflow, designed for AI-assisted presentation generation instead of generic web pages.
AI-native product discovery for Cursor. Hypothesis → validation → PRD, all in your repo — so your LLM has full context when it's time to build.
ROF - RelateLang Orchestration Framework: is an orchestration framework that converts structured business logic into reliable, testable, and version-controlled LLM workflows.
Add a description, image, and links to the llm-workflow topic page so that developers can more easily learn about it.
To associate your repository with the llm-workflow topic, visit your repo's landing page and select "manage topics."