MCP HubMCP Hub
スキル一覧に戻る

create-portfolio

majiayu000
更新日 2 days ago
22 閲覧
58
9
58
GitHubで表示
メタword

について

`create-portfolio`スキルは、開発者のための専門的で実績重視のポートフォリオ項目を生成します。プロジェクトの文書化や実務経験の紹介に最適です。このスキルは、力強い行動動詞と定量化可能な指標を備えたコンテンツを作成し、出力をMarkdownファイルとして保存します。新規プロジェクトの追加や、技術的インパクトを強調するケーススタディを作成する際にご利用ください。

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

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

Portfolio Project Creation

Creates portfolio entries at content/portfolio/project-slug/index.md with professional, achievement-focused messaging.

When to Use

Activate when users ask to:

  • Add a new project to their portfolio
  • Showcase professional work or accomplishments
  • Document a completed project with technical details
  • Create a case study for client work

Required Information

Gather before generating content:

FieldFormatExample
titleString"E-commerce Platform Redesign"
clientString"Acme Corporation"
descriptionString (SEO)"Full-stack redesign increasing conversions 40%"
technologiesArray["React", "Node.js", "PostgreSQL"]
completion_dateYYYY-MM"2024-11"
categorySee categories"Web Development"

Optional Information

FieldFormatNotes
github_urlURLMust be valid GitHub URL
live_urlURLMust be valid HTTP/HTTPS URL
challengesArrayProblems faced during project
solutionsArrayHow challenges were addressed
outcomesArrayResults and achievements
metricsArrayQuantifiable impact data

Categories

Use one of these standard categories:

  • Web Development
  • Mobile Development
  • Backend Development
  • DevOps
  • Data Engineering
  • Software Development

Writing Style

Action Verbs (Required)

Start achievement statements with strong verbs:

PrimarySecondary
LedArchitected
DevelopedDesigned
ImplementedBuilt
AchievedOptimized
DeliveredScaled

Quantify Impact

Transform vague statements into measurable achievements:

AvoidUse Instead
"Improved performance""Reduced load time by 40%"
"Many users""Served 10,000+ users"
"High volume""Processed 1M+ transactions daily"
"Faster delivery""Reduced deployment time from 2 hours to 15 minutes"

Tone Guidelines

Do:

  • Highlight impact and technical depth
  • Use metrics and quantifiable results
  • Showcase problem-solving skills
  • Demonstrate value delivered to clients
  • Write with professional confidence

Avoid:

  • Being overly modest or downplaying achievements
  • Vague statements without specifics
  • Listing responsibilities without outcomes
  • Excessive technical jargon for non-technical audiences

Generation Process

Step 1: Gather Requirements

Ask for all required fields. For optional fields, prompt:

  • "Were there specific challenges you overcame?"
  • "What measurable outcomes did you achieve?"
  • "Do you have a GitHub repository or live demo?"

Step 2: Create Hugo Bundle

Generate content/portfolio/{slug}/index.md:

---
title: "{title}"
date: {YYYY-MM-DD}  # Today's date
draft: true         # Always start as draft
description: "{description}"
client: "{client}"
technologies:
  - Technology1
  - Technology2
completion_date: "{YYYY-MM}"
category: "{category}"
github_url: "{optional}"
live_url: "{optional}"
---

Step 3: Generate Content Sections

Structure the markdown body:

  1. Opening paragraph - Achievement-focused overview using action verbs
  2. Project Overview - Context and scope
  3. Challenges (if provided) - Problems addressed
  4. Technical Solution (if provided) - How challenges were solved
  5. Technical Implementation - Technologies and architecture
  6. Outcomes - Results with metrics
  7. Technologies - Bulleted list of tech stack

Step 4: Validate

Run validation:

node scripts/validate-portfolio-frontmatter.js

Validation checks:

  • All required frontmatter fields present
  • Date format: YYYY-MM-DD
  • Completion date format: YYYY-MM
  • Technologies is an array
  • Category is a string
  • URLs are valid format (if provided)
  • No use of deprecated demo_url (use live_url instead)

Step 5: Review

Never auto-publish. Always:

  1. Present the complete draft to the user
  2. Get explicit approval before changing draft: false
  3. Offer to make revisions based on feedback

Example Output

---
title: "Analytics Dashboard Platform"
date: 2024-12-26
draft: true
description: "Real-time analytics platform processing 1M+ events daily with sub-second query performance"
client: "DataTech Solutions"
technologies:
  - React
  - TypeScript
  - PostgreSQL
  - Redis
completion_date: "2024-11"
category: "Web Development"
github_url: "https://github.com/example/analytics-dashboard"
live_url: "https://demo.example.com"
---

**Led** the development and delivery of a high-performance analytics dashboard for DataTech Solutions, achieving sub-second query response times while processing over 1 million events daily.

## Project Overview

Delivered a comprehensive real-time analytics platform enabling stakeholders to visualize key business metrics through interactive dashboards with customizable widgets.

## Challenges

- **Challenge 1:** Legacy system processed queries in 15+ seconds - implemented comprehensive analysis and strategic planning.
- **Challenge 2:** Data pipeline bottlenecks during peak hours - developed scalable ingestion architecture.

## Technical Solution

- **Implemented** Redis caching layer reducing database load by 70%
- **Architected** event-driven pipeline handling 10x traffic spikes
- **Designed** materialized views for complex aggregations

## Technical Implementation

This project leverages modern technologies and architectural patterns:

- **React** - Component-based dashboard UI
- **TypeScript** - Type-safe frontend development
- **PostgreSQL** - Time-series data storage
- **Redis** - Real-time caching layer

## Outcomes

- **Achieved** sub-second query performance (down from 15+ seconds)
- **Delivered** 99.9% uptime over 6 months of production use
- **Implemented** self-service dashboard creation reducing support tickets by 60%

### Key Metrics

- **Query Performance:** 15s to 200ms - 98% improvement
- **Daily Events:** 1M+ processed with zero data loss
- **User Adoption:** 500+ active users within first month

## Technologies

- **React**
- **TypeScript**
- **PostgreSQL**
- **Redis**

Voice Learning

Record user feedback to improve future content generation:

# Update style documentation
# Location: .cody/project/library/style-docs/portfolio-style.json

# Fields to update based on feedback:
# - vocabulary: Add effective action verbs
# - dos: Add successful patterns
# - donts: Add patterns to avoid

File Locations

PurposePath
Portfolio contentcontent/portfolio/
Validation scriptscripts/validate-portfolio-frontmatter.js
Style documentation.cody/project/library/style-docs/portfolio-style.json
Portfolio Agentsrc/agents/portfolio/portfolio-agent.ts
Agent configsrc/agents/config/agent-config.ts

Common Validation Errors

ErrorResolution
Missing required fieldAdd the field to frontmatter
Invalid date formatUse YYYY-MM-DD for date
Invalid completion_dateUse YYYY-MM format
technologies not arrayConvert to YAML array format
Use demo_urlReplace with live_url

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/create-portfolio

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

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

llamaindex

メタ

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

スキルを見る

canvas-design

メタ

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

スキルを見る