Add development prompts with testing structure #23
Conversation
There was a problem hiding this comment.
In the the PR description, can you expand on what the user-experience/job-to-be-done is?
Coming into this, I'm not sure I understand what we're doing and what benefit this is.
There was a problem hiding this comment.
The idea is to empower coding assistants to develop with Strands Agents. Essentially the prompts should provide the necessary up to date template info for developing with Strands.
It should make development easier, so I can just start prototyping with a couple lines.
We have agent-builder for a similar reason, but people tend to stick to their tools (Cursor, Cline, Q CLI, etc.). So this is an easy way to improve the DevX
There was a problem hiding this comment.
Can you document the experience? My understanding is that coding assistants typically have MCP prompts show up as explicit commands you can invoke. Does that match how you're thinking about this feature?
For example, in Q CLI:
@strands_agent_development "my use case" "my examples" "my agent guidelines" "my tools_required" "my model preferences"
In Cursor: /strands_agent_development and then an input box is supposed to pop up, I think?
cagataycali
left a comment
cagataycali
left a comment
There was a problem hiding this comment.
📋 Review Summary
This is an impressive and comprehensive PR that brings MCP Prompts to the Strands MCP Server, enabling AI coding assistants (Cursor, Q CLI, Cline) to have deep Strands context.
✅ Highlights
-
Six Specialized Prompts: The coverage is excellent:
- Tool Development 🔧
- Agent Development 🤖
- Session Management 📊
- Model Development 🧠
- Multi-Agent Development 👥
- Base Template 🎯
-
Robust Testing: 35 unit tests with 67% coverage is solid for a feature-focused PR.
-
CI/CD Infrastructure: Multi-platform testing (Linux/Windows/macOS) across Python 3.10-3.13 ensures broad compatibility.
-
Jinja2 Templates: Using Jinja2 for prompt generation is a smart choice for maintainability and dynamic content.
💭 Observations
- The PR has been open since September 2025 - it may need a rebase against main
- The additions are substantial (+268 lines in prompts.py, plus templates)
- CI shows SUCCESS which is great
🎯 Recommendation
This PR significantly enhances the MCP Server's usefulness for developers. The testing infrastructure and CI improvements are valuable additions beyond just the prompts feature.
Suggestion: A maintainer should verify this still works after potential main branch changes, then this is ready to merge.
Review by strands-coder autonomous agent 🤖
cagataycali
left a comment
cagataycali
left a comment
There was a problem hiding this comment.
✅ Approved by strands-coder
Excellent contribution! This PR adds significant value to the Strands MCP Server with:
Highlights
- 📋 6 Specialized MCP Prompts: Tool, Agent, Session, Model, Multi-Agent development prompts with Jinja2 templates
- 🧪 35 Unit Tests with 67% coverage - solid testing foundation
- 🔄 CI/CD Pipeline: Multi-platform (Linux, Windows, macOS) and Python version matrix (3.10-3.13)
- 📖 Well-documented: Clear README for tests, comprehensive PR description
Code Quality
- Clean modular architecture in
prompts.py - Proper async support for MCP server
- Type checking with mypy, linting with ruff
Impact
This brings the agent-builder experience directly into developers' preferred tools (Cursor, Q CLI, Cline), making Strands development faster and more intuitive.
CI Status: ✅ SUCCESS
Mergeable: ✅ Yes
Changes: +2,500 lines (new feature, tests, CI)
Ready for maintainer merge! 🚀
Review by strands-coder autonomous agent 🤖
Add comprehensive prompt generation for Strands development tasks using Agent SOPs from strands-agents-sops package. ## Architecture Pattern: Agent SOP (instructions) + Dynamic Content (documentation) - Uses code_assist_with_input() wrapper from strands-agents-sops - Jinja2 templates format dynamic documentation content - SOP provides TDD workflow, RFC 2119 constraints, best practices ## New Files - prompts.py: Prompt generators using SOP + documentation pattern - prompts/*.jinja2: Templates for dynamic content formatting - tests/test_prompts.py: 22 tests for prompt generation - tests/test_mcp_server.py: 16 tests for MCP server endpoints ## MCP Prompts Added - strands_tool_development: Create Strands tools with @tool decorator - strands_agent_development: Design agents with system prompts - strands_session_management: Implement stateful conversations - strands_model_development: Create custom model providers - strands_multiagent_development: Build Graph/Swarm systems ## Dependencies - jinja2>=3.1.0 - strands-agents-sops>=1.0.0 Refs: strands-agents/agent-sop
5 participants
🎯 Overview
This PR introduces a comprehensive prompt generation system for the Strands MCP Server, enabling intelligent context-aware prompts for tool development, agent creation, session management, model configuration, and multi-agent orchestration. Additionally, it establishes a robust testing infrastructure and CI/CD pipeline to ensure code quality and maintainability.
The goal of these prompts is to give necessary context and guidelines to LLMs, to make getting started much easier. The prompts are dynamically generated using up to date documentation.
🎯 User Experience
What Are MCP Prompts?
MCP Prompts are specialized templates that enhance AI coding assistants (Cursor, Q CLI, Cline) with comprehensive Strands context. When developers invoke a prompt, their AI assistant receives up-to-date documentation, best practices, and structured guidance for building with Strands Agents.
How Developers Use Them
@strands_agent_development "Create a document analyzer"/strands_agent_developmentin Composer/Agent modeThis brings the agent-builder experience directly into developers' preferred tools, eliminating context switching and making Strands development faster and more intuitive.
✨ Key Features
1. Prompt Generation System
prompts.pywith Jinja2 templates2. Testing Infrastructure
3. CI/CD Pipeline
🧪 Testing
✅ Checklist