MCP HubMCP Hub
スキル一覧に戻る

create-tech-radar

majiayu000
更新日 Today
22 閲覧
58
9
58
GitHubで表示
メタworddesign

について

このClaudeスキルは、BYORフォーマットに準拠した構造化されたテックレーダーエントリーを作成し、ツールやフレームワークに対するバランスの取れた技術分析を提供します。開発者が技術の採用、試用、評価、保留ステータスについて推奨事項を文書化し評価するために設計されています。本スキルは、技術のタイトル、説明、象限を入力することで、実践的なガイダンスを生成します。

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/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/create-tech-radar

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

Tech Radar Entry Creation

Creates opinionated tech radar entries that provide actionable guidance on technology adoption decisions.

When to Use

Activate this skill when users ask to:

  • Add a technology to the radar
  • Assess or evaluate a tool, framework, or platform
  • Document technology recommendations
  • Compare technologies for adoption decisions
  • Update an existing radar entry's ring position

Required Information

Gather these before generating:

  1. Title - Technology name (e.g., "Bun", "htmx", "Kubernetes")
  2. Description - Brief description (1-2 sentences)
  3. Quadrant - Technology category (see below)
  4. Ring - Recommendation level (see below)

Optional Information

  • Tags - Technology categorization tags
  • Date - Assessment date (defaults to today)
  • Context - Specific context for the recommendation

Ring Definitions

Rings represent adoption recommendations with specific implications:

RingMeaningUser ActionContent Tone
adoptProduction-ready, provenUse confidently for new projectsConfident, encouraging
trialPromising, worth pilotingEvaluate for specific use casesCautiously optimistic
assessEmerging, worth watchingResearch and experiment onlyExploratory, measured
holdAvoid or migrate fromPlan migration, no new adoptionDirect but fair

Ring-Specific Analysis Focus

ADOPT:

  • Implementation best practices
  • Production deployment guidance
  • Long-term maintenance considerations
  • Team training resources
  • Success patterns from the ecosystem

TRIAL:

  • When and where to pilot
  • Success criteria for evaluation
  • Comparison with established alternatives
  • Risk mitigation strategies
  • Fallback plan recommendations

ASSESS:

  • Key questions to answer before adoption
  • Evaluation criteria and metrics
  • Community and ecosystem health indicators
  • Research and prototyping guidance
  • Timeline for reassessment

HOLD:

  • Reasons for the hold recommendation
  • Migration path to alternatives
  • Risk assessment for existing usage
  • Security and maintenance concerns
  • Recommended replacements

Quadrant Examples

QuadrantDescriptionExamples
techniquesDevelopment practices and methodologiesTDD, pair programming, GitOps, IaC, trunk-based development
toolsDevelopment and operations toolsBun, Vite, Webpack, CI/CD platforms, linters
platformsInfrastructure and deployment platformsAWS, Kubernetes, serverless, edge computing
languages-and-frameworksProgramming languages and frameworksRust, TypeScript, React, Next.js, htmx

Generation Process

Step 1: Gather Requirements

Ask the user for the required information. If they provide a technology name without other details, research and propose appropriate values.

Step 2: Generate Opinionated Analysis

Create content that is:

  • Opinionated - Take a clear position on the technology
  • Balanced - Acknowledge both strengths and weaknesses
  • Evidence-based - Support opinions with ecosystem signals
  • Actionable - Provide concrete next steps

Content Sections to Generate:

  1. Overview (ring-specific framing)
  2. Key Features (factual capabilities)
  3. Strengths (what it does well)
  4. Weaknesses (honest limitations)
  5. Use Cases (where it shines)
  6. Ring Recommendation (with justification)
  7. Ecosystem Assessment (community health)
  8. Adoption Considerations (practical guidance)
  9. Conclusion (maturity + future outlook)

Step 3: Create Hugo Bundle

Create content at content/tools/technology-slug/index.md:

Frontmatter (BYOR-compatible):

---
title: "Technology Name"
date: YYYY-MM-DD
draft: true
description: "Brief description for SEO and radar display"
quadrant: "quadrant-slug"
ring: "ring-slug"
tags:
  - tag1
  - tag2
---

Step 4: Review

Present the draft to the user for review. Never auto-publish - always keep draft: true until explicit approval.

Writing Guidelines

Tone: Opinionated but balanced and informed

Do:

  • Provide technical depth and context
  • Consider practical adoption implications
  • Assess maturity and ecosystem support
  • Be forward-looking but realistic
  • Use evidence from real-world usage
  • Acknowledge when context matters

Don't:

  • Be purely opinionated without evidence
  • Use hype-driven language
  • Ignore potential drawbacks or limitations
  • Be overly negative about technologies
  • Make absolute statements without qualification
  • Dismiss legitimate use cases

Vocabulary:

  • adopt, trial, assess, hold
  • maturity, ecosystem, production-ready
  • trade-offs, considerations, implications
  • community, governance, long-term viability

Example Frontmatter

---
title: "htmx"
date: 2025-12-26
draft: true
description: "Lightweight library for AJAX, CSS transitions, and WebSockets directly in HTML"
quadrant: "languages-and-frameworks"
ring: "trial"
tags:
  - javascript
  - html
  - hypermedia
  - ajax
---

Validation

After generation, verify:

  • Required frontmatter fields present
  • Quadrant is valid value
  • Ring is valid value
  • Description is concise but informative
  • Content has all required sections
  • No H1 heading in content (title comes from frontmatter)

Voice Learning

Record user feedback to improve future analysis:

Feedback location: .cody/project/library/style-docs/tech-radar-style.json

Record positive feedback for good patterns.
Record negative feedback for issues to avoid.

File Locations

  • Tech radar entries: content/tools/{technology-slug}/index.md
  • Style guidelines: .cody/project/library/style-docs/tech-radar-style.json
  • Agent implementation: src/agents/tech-radar/tech-radar-agent.ts

Example Interaction

User: Add Bun to the tech radar

Response Flow:

  1. Acknowledge the request
  2. Ask which ring (or propose one with justification)
  3. Confirm quadrant (likely "tools")
  4. Ask for any specific context or tags
  5. Generate the entry
  6. Present for review with explanation of the analysis

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/create-tech-radar

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

polymarket

メタ

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

スキルを見る

langchain

メタ

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

スキルを見る