MCP HubMCP Hub
スキル一覧に戻る

managing-autonomous-development

jeremylongshore
更新日 Today
83 閲覧
712
74
712
GitHubで表示
メタaiautomation

について

このスキルは、特定のコマンドを通じてClaudeがSugarの自律的開発ワークフローを管理できるようにします。タスクの作成、システムステータスの確認、保留中のタスクのレビュー、自律実行モードの開始が可能です。開発者が`/sugar-task`、`/sugar-status`、`/sugar-review`、`/sugar-run`などのコマンドでSugarと対話する必要がある場合にご利用ください。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus
Git クローン代替
git clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/managing-autonomous-development

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

Overview

This skill empowers Claude to orchestrate and monitor autonomous development processes within the Sugar environment. It provides a set of commands to create, manage, and execute tasks, ensuring efficient and automated software development workflows.

How It Works

  1. Command Recognition: Claude identifies the appropriate Sugar command (e.g., /sugar-task, /sugar-status, /sugar-review, /sugar-run).
  2. Parameter Extraction: Claude extracts relevant parameters from the user's request, such as task type, priority, and execution flags.
  3. Execution: Claude executes the corresponding Sugar command with the extracted parameters, interacting with the Sugar plugin.
  4. Response Generation: Claude presents the results of the command execution to the user in a clear and informative manner.

When to Use This Skill

This skill activates when you need to:

  • Create a new development task with specific requirements.
  • Check the current status of the Sugar system and task queue.
  • Review and manage pending tasks in the queue.
  • Start or manage the autonomous execution mode.

Examples

Example 1: Creating a New Feature Task

User request: "/sugar-task Implement user authentication --type feature --priority 4"

The skill will:

  1. Parse the request and identify the command as /sugar-task with parameters "Implement user authentication", --type feature, and --priority 4.
  2. Execute the sugar command to create a new task with the specified parameters.
  3. Confirm the successful creation of the task to the user.

Example 2: Checking System Status

User request: "/sugar-status"

The skill will:

  1. Identify the command as /sugar-status.
  2. Execute the sugar command to retrieve the system status.
  3. Display the system status, including task queue information, to the user.

Best Practices

  • Clarity: Always confirm the parameters before executing a command to ensure accuracy.
  • Safety: When using /sugar-run, strongly advise the user to use --dry-run --once first.
  • Validation: Recommend validating the Sugar configuration before starting autonomous mode.

Integration

This skill integrates directly with the Sugar plugin, leveraging its command-line interface to manage autonomous development workflows. It can be combined with other skills to provide a more comprehensive development experience.

GitHub リポジトリ

jeremylongshore/claude-code-plugins-plus
パス: backups/skills-batch-20251204-000554/plugins/devops/sugar/skills/sugar
aiautomationclaude-codedevopsmarketplacemcp

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

evaluating-llms-harness

テスト

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

スキルを見る

sglang

メタ

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る