引入Strands Agent SOPs——AI智能体的自然语言工作流 | AWS开源博客

1

pip install strands-agents-sops

1
2
3
4
5
6
7
8

{
  "mcpServers" : {
    "strands-agents-sops" : {
      "command" : "strands-agents-sops",
      "args" : []
    }
  }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

[strands-agents-sop] > /prompts

Usage: You can use a prompt by typing '@<prompt name> [...args]'

Prompt                               Description                              Arguments (* = required)
▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔▔
strands-agents-sop (MCP):
- code-assist                        This sop guides the implementation of... user_input
- code-task-generator                This sop generates structured code ta... user_input
- codebase-summary                   This sop analyzes a codebase and gene... user_input
- pdd                                This sop guides you through the proce... user_input

1

@codebase-summary

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22

> I'll help you run the codebase summary SOP. Let me gather the required parameters first.

Please provide the following parameters for the codebase analysis:

Required Parameters:
• **codebase_path**: Path to the codebase to analyze (default: current directory)

Optional Parameters:
• **output_dir**: Directory where documentation will be stored (default: ".sop/summary")
• **consolidate**: Whether to create a consolidated documentation file (default: false)

• **consolidate_prompt**: Description of how to structure the consolidated content
• **check_consistency**: Whether to check for inconsistencies across documents (default: true)
• **check_completeness**: Whether to identify areas lacking sufficient detail (default: true)
• **update_mode**: Whether to update existing documentation based on recent commits (default: false)

You can provide these parameters in any of these ways:
• Direct input in your response
• File path containing the configuration
• Just specify what you want to change from defaults

What parameters would you like to use for this codebase analysis?

1
2

[strands-agents-sop] > codebase_path: ~/github/agent-sop/python
consolidate: true

1
2
3
4
5
6
7

## Step 1: Setup and Directory Structure

...

> ✅ Validated codebase path exists and is accessible
✅ Created directory .summary/
✅ Full analysis will be performed (not in update mode)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

## Step 6: Summary and Next Steps

## Summary

✅ Documentation generation complete!

### What Was Accomplished

• **Analyzed** Python package with 4 core modules and 5 SOP files
• **Generated** comprehensive documentation ecosystem in .summary/ directory:
  • index.md: Knowledge base index with AI assistant instructions
  • codebase_info.md: Project overview and structure
  • architecture.md: System design and patterns
  • components.md: Module responsibilities and functionality
  • interfaces.md: APIs, CLI, and integration points
  • data_models.md: SOP format and data structures
  • workflows.md: Build process and operational procedures
  • dependencies.md: External requirements and usage
  • review_notes.md: Quality assessment and recommendations

• **Identified** system as modular CLI tool with MCP server capabilities

### Key Findings

• **Architecture**: Clean modular design with dynamic SOP loading
• **Integration**: Multiple interfaces (Python imports, MCP protocol, CLI, Anthropic skills)
• **Content Management**: File-based SOP storage with build-time synchronization
• **Dependencies**: Minimal external requirements (only MCP library)
• **Extensibility**: Easy to add new SOPs without code changes

<summary continues...>

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

from strands import Agent
from strands_tools import editor, shell
from strands_agents_sops import code_assist

agent = Agent(
  system_prompt=code_assist,
  tools=[editor, shell]
)

agent("Start code-assist sop")

while(True):
  agent(input("\nInput: "))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17

I'll help you implement a code task using the test-driven development workflow. Let me gather the required parameters to get started.

Please provide the following information:

**Required:**
- **task_description**: What would you like to implement? (You can provide a detailed specification, requirements, acceptance criteria, or even a rough idea that we'll refine together. You can also provide a file path or URL if the description is in a document)

**Optional:**
- **additional_context**: Any supplementary information that would help with understanding the implementation context (can also be a file path or URL)
- **documentation_dir**: Directory for planning documents (default: ".sop/planning")
- **repo_root**: Root directory of the repository (default: current working directory)
- **task_name**: A short, descriptive name for the task (I'll generate one if not provided)
- **mode**: Interaction mode:
  - "interactive" (default): I'll collaborate with you and ask for confirmation at each step
  - "auto": I'll execute autonomously after setup with no further interaction required

Please provide these details so we can begin the implementation process.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

from strands import Agent
from strands_tools import editor, shell, git
from strands_agents_sops import codebase_summary

doc_agent = Agent(
 system_prompt=codebase_summary,
 tools=[editor, shell, git]
)

# Run in update mode to refresh docs based on recent commits
doc_agent("Run codebase-summary with update_mode: true")

1
2
3
4
5

# Generate Skills format from SOPs
strands-agents-sops skills

# Or specify custom output directory
strands-agents-sops skills --output-dir my-skills

1
2
3
4
5
6
7
8
9

skills/
├── code-assist/
│   └── SKILL.md
├── codebase-summary/
│   └── SKILL.md
├── code-task-generator/
│   └── SKILL.md
└── pdd/
    └── SKILL.md

1
2
3
4

[strands-agents-sop] > Run `strands-agents-sops rule`
...
> The command executed successfully and displayed the Agent SOP format specification.
...

1

[strands-agents-sop] > I want to create an Agent SOP that takes meeting notes and generates action items, decisions made, and follow-up tasks with assigned owners and deadlines.