MCP HubMCP Hub
← スキル一覧に戻る

writing-plans-skill

Eibon7
更新日 Today
77 閲覧
0
GitHubで表示
メタaidesign

について

このスキルは、コードベースのコンテキストが一切ないエンジニア向けに詳細な実装計画を生成します。具体的なファイルパス、完全なコード例、検証手順を含む包括的なタスク分解を作成します。設計が完了した段階で使用し、最小限のドメイン知識を前提とした、小さな単位に分割された実装タスクを提供するために活用できます。

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/Eibon7/roastr-ai
Git クローン代替
git clone https://github.com/Eibon7/roastr-ai.git ~/.claude/skills/writing-plans-skill

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

name: writing-plans-skill description: Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge triggers:

  • "implementation plan"
  • "detailed tasks"
  • "zero context"
  • "complete plan"
  • "file paths" used_by:
  • orchestrator
  • task-assessor
  • back-end-dev
  • front-end-dev steps:
  • paso1: "Announce: Using writing-plans skill to create implementation plan"
  • paso2: "Create comprehensive plan with exact file paths, complete code examples, verification steps"
  • paso3: "Assume engineer has zero context and questionable taste"
  • paso4: "Provide bite-sized tasks (2-5 minutes each)"
  • paso5: "Start with header: Goal, Architecture, Tech Stack"
  • paso6: "For each task: Files, Steps (write test → run → implement → test → commit), Code examples"
  • paso7: "Reference skills with @ syntax when needed"
  • paso8: "Save to docs/plans/YYYY-MM-DD-<feature-name>.md"
  • paso9: "Offer execution choice: Subagent-driven or parallel session" output: |
  • Comprehensive plan saved to docs/plans/
  • Bite-sized tasks with exact paths
  • Complete code examples
  • Verification steps
  • Execution handoff granularity:
  • "Each step is 2-5 minutes"
  • "Write failing test → step"
  • "Run it → step"
  • "Implement minimal code → step"
  • "Run tests → step"
  • "Commit → step" plan_header:
  • "Goal: One sentence describing what this builds"
  • "Architecture: 2-3 sentences about approach"
  • "Tech Stack: Key technologies/libraries" task_structure:
  • "Task N: Component Name"
  • "Files: Create/Modify/Test with exact paths"
  • "Steps: With complete code examples"
  • "Commands: Exact commands with expected output" remember:
  • "Exact file paths always"
  • "Complete code in plan (not 'add validation')"
  • "Exact commands with expected output"
  • "Reference relevant skills with @ syntax"
  • "DRY, YAGNI, TDD, frequent commits" execution_handoff:
  • "After saving plan, offer execution choice"
  • "Option 1: Subagent-driven (this session) - fresh subagent per task"
  • "Option 2: Parallel session - new session with executing-plans skill" referencias:
  • "Fuente: superpowers-skills/writing-plans"
  • "Complementa: executing-plans-skill"
  • "Roastr: Útil para features complejas (AC ≥5)"

GitHub リポジトリ

Eibon7/roastr-ai
パス: .claude/skills/writing-plans-skill.md

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

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

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