MCP HubMCP Hub
スキル一覧に戻る

agenta-1-prompt-versioning-and-management

vamseeachanta
更新日 Today
65 閲覧
3
2
3
GitHubで表示
その他general

について

このスキルは、AIプロンプトのバージョン管理と管理を可能にし、開発者が変更を追跡し、反復を比較し、プロンプト履歴を維持できるようにします。スタイルや長さ制約などのパラメータを含むバージョン管理されたプロンプトテンプレートを作成するツールを提供します。異なるモデルバージョンやチームコラボレーションにわたって再現可能で監査可能なプロンプトワークフローが必要な場合に使用してください。

クイックインストール

Claude Code

推奨
メイン
npx skills add vamseeachanta/workspace-hub
プラグインコマンド代替
/plugin add https://github.com/vamseeachanta/workspace-hub
Git クローン代替
git clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agenta-1-prompt-versioning-and-management

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

1. Prompt Versioning and Management

1. Prompt Versioning and Management

Creating Versioned Prompts:

"""
Create and manage versioned prompts with Agenta.
"""
import agenta as ag
from agenta import Agenta
from typing import Optional, Dict, Any

# Initialize Agenta
ag.init()

@ag.entrypoint
def generate_summary(
    text: str,
    max_length: int = 100,
    style: str = "professional"
) -> str:
    """
    Generate a summary with versioned prompt.

    Args:
        text: Text to summarize
        max_length: Maximum summary length
        style: Writing style (professional, casual, technical)

    Returns:
        Generated summary
    """
    # Define prompt template (this becomes versioned)
    prompt = f"""Summarize the following text in a {style} tone.
Keep the summary under {max_length} words.

Text: {text}

Summary:"""

    # Call LLM (Agenta tracks this)
    response = ag.llm.complete(
        prompt=prompt,
        model="gpt-4",
        temperature=0.3,
        max_tokens=max_length * 2
    )

    return response.text


# Example usage
text = """
The company reported strong Q3 results with revenue up 25% year-over-year.
Operating margins improved to 18% from 15% in the prior year.
The CEO highlighted expansion into new markets and product launches.
"""

summary = generate_summary(text, max_length=50, style="professional")
print(summary)

Managing Prompt Versions:

"""
Manage multiple prompt versions programmatically.
"""
import agenta as ag
from agenta import Agenta
from dataclasses import dataclass
from typing import List, Dict, Optional
from datetime import datetime

@dataclass
class PromptVersion:
    """Represents a prompt version."""
    version_id: str
    name: str
    template: str
    parameters: Dict[str, Any]
    created_at: datetime
    is_active: bool = False


class PromptManager:
    """
    Manage prompt versions with Agenta.
    """

    def __init__(self, app_name: str):
        self.app_name = app_name
        self.client = Agenta()

    def create_version(
        self,
        name: str,
        template: str,
        parameters: Dict[str, Any] = None
    ) -> PromptVersion:
        """
        Create a new prompt version.

        Args:
            name: Version name
            template: Prompt template
            parameters: Default parameters

        Returns:
            Created PromptVersion
        """
        # Create variant in Agenta
        variant = self.client.create_variant(
            app_name=self.app_name,
            variant_name=name,
            config={
                "template": template,
                "parameters": parameters or {}
            }
        )

        return PromptVersion(
            version_id=variant.id,
            name=name,
            template=template,
            parameters=parameters or {},
            created_at=datetime.now(),
            is_active=False
        )

    def list_versions(self) -> List[PromptVersion]:
        """List all prompt versions."""
        variants = self.client.list_variants(app_name=self.app_name)

        versions = []
        for v in variants:
            versions.append(PromptVersion(
                version_id=v.id,
                name=v.name,
                template=v.config.get("template", ""),
                parameters=v.config.get("parameters", {}),
                created_at=v.created_at,
                is_active=v.is_default
            ))

        return versions

    def set_active_version(self, version_id: str) -> None:
        """Set a version as the active/default version."""
        self.client.set_default_variant(
            app_name=self.app_name,
            variant_id=version_id
        )

    def get_version(self, version_id: str) -> PromptVersion:
        """Get a specific version."""
        variant = self.client.get_variant(variant_id=version_id)

        return PromptVersion(
            version_id=variant.id,
            name=variant.name,
            template=variant.config.get("template", ""),
            parameters=variant.config.get("parameters", {}),
            created_at=variant.created_at,
            is_active=variant.is_default
        )

    def compare_versions(
        self,
        version_ids: List[str],
        test_input: str
    ) -> Dict[str, str]:
        """
        Compare outputs from multiple versions.

        Args:
            version_ids: List of version IDs to compare
            test_input: Input to test with

        Returns:
            Dictionary mapping version_id to output
        """
        results = {}

        for vid in version_ids:
            version = self.get_version(vid)

            # Format prompt with test input

*Content truncated — see parent skill for full reference.*

GitHub リポジトリ

vamseeachanta/workspace-hub
パス: .claude/skills/ai/prompting/agenta/1-prompt-versioning-and-management

関連スキル

algorithmic-art

メタ

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

スキルを見る

subagent-driven-development

開発

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

スキルを見る

executing-plans

デザイン

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

スキルを見る

cost-optimization

その他

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

スキルを見る