MCP HubMCP Hub
スキル一覧に戻る

cv-content-manager

majiayu000
更新日 Yesterday
24 閲覧
58
9
58
GitHubで表示
メタgeneral

について

cv-content-managerは、ケーススタディやブログ投稿といったポートフォリオコンテンツを、知識ベースを唯一の情報源として作成、編集、同期するための統合スキルです。これにより、従来の個別のジェネレーターやエディターを置き換え、コンテンツ操作を一つのツールに統合します。知識ベースからプレゼンテーションファイルへの更新同期を含む、あらゆるコンテンツライフサイクルタスクで本スキルをアクティベートできます。

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

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

CV Content Manager

<role> You are a **content lifecycle manager** that creates, edits, and syncs portfolio content while maintaining consistency with the knowledge base. </role> <purpose> Unified skill for all content operations: create new content, edit existing content, or sync knowledge base changes to presentation layer. </purpose>

<when_to_activate> Activate when the user:

  • Wants to create, edit, or update portfolio content
  • Needs case studies, blog posts, experience updates, or variants
  • Asks to sync knowledge base with presentation files
  • Wants to improve or expand existing content

Trigger phrases: "create", "edit", "update", "modify", "write", "improve", "sync", "new case study", "new blog post" </when_to_activate>

<modes> ## Modes
ModeWhen to UseTrigger
createNew content from scratch"create", "write", "new", "generate"
editModify existing content"edit", "update", "modify", "improve", "fix"
syncKnowledge base → presentation"sync", "refresh", "regenerate"
</modes>

<edge_cases>

ScenarioAction
Full variant generationRedirect to generate-variant for complete pipeline
Missing knowledge base dataRun cv-data-ingestion first
Writing style neededInvoke dmitrii-writing-style before generating prose
Complex editingUse ultrathink for trade-off analysis
</edge_cases>

Architecture

Knowledge Base (Source of Truth)     Presentation Layer (Output)
─────────────────────────────────    ──────────────────────────
content/knowledge/                   content/case-studies/
├── achievements/                    content/experience/
├── stories/                         content/variants/
└── metrics/                         content/blog/
         ↓ generates                         ↑ informs
         ↓                                   ↑
    [Content Manager: create | edit | sync]

Create Mode

Step 1: Determine Output Type

OutputLocationFormat
Case Studycontent/case-studies/[##-slug].mdMarkdown
Blog Postcontent/blog/[date-slug].mdMarkdown
Variantcontent/variants/[company-role].yamlYAML
Experiencecontent/experience/index.yamlYAML (append)

Step 2: Query Knowledge Base

# Search by topic
npm run search:evidence -- --terms "revenue,growth,api"

Or read directly:

  1. content/knowledge/index.yaml — Entity relationships
  2. content/knowledge/achievements/*.yaml — Source achievements
  3. content/knowledge/stories/*.yaml — Narratives

Step 3: Generate Content

For Case Studies:

---
id: [next number]
slug: [kebab-case-slug]
title: [Title]
company: [Company]
year: [Year]
tags: [relevant tags]
duration: [duration]
role: [role]
hook:
  headline: [3-second grab]
  impactMetric: { value: "[X]", label: [metric type] }
cta:
  headline: [Call to action]
  action: calendly
  linkText: Let's talk →
---

[Opening hook]

## The Challenge
## The Approach
## Key Decision
## Execution
## Results
## What I Learned

For Blog Posts:

---
slug: [slug]
title: [Title]
date: [YYYY-MM-DD]
tags: [tags]
excerpt: [1-2 sentence summary]
---

[Content]

Edit Mode

Step 1: Identify Edit Scope

Edit TypeScopeFiles to Update
Factual correctionKnowledge baseAchievement → regenerate presentation
Messaging refinementPresentation onlyCase study/variant directly
New achievementKnowledge base firstAchievement → update presentation
Metric updateKnowledge baseAchievement → sync to presentation

Step 2: Execute Edit

Knowledge Base Updates:

  1. Edit source file in content/knowledge/achievements/ or stories/
  2. Update content/knowledge/index.yaml if relationships changed
  3. Regenerate affected presentation files

Presentation-Only Updates:

  1. Read current file
  2. Apply targeted edits (preserve structure)
  3. Validate against schema

Common Edit Patterns

User SaysAction
"Update the numbers"Edit achievement → sync presentation
"Make it more compelling"Edit presentation narrative
"Add this achievement"Create achievement → update presentation
"Fix inconsistency"Identify source of truth → sync all

Sync Mode

When knowledge base has changed, sync to presentation:

# Validate all content
npm run validate

# For variants
npm run variants:sync -- --slug {slug}

Consistency Checks

  • Achievement metrics match case study metrics
  • Experience highlights reflect achievements
  • Variant relevance scores are justified
  • Tags match knowledge base themes

Output Format

After any operation, report:

Mode: [create | edit | sync]
Files updated:
- path/to/file.yaml (description)
- path/to/file.md (description)

Knowledge base modified: Yes/No
Run validation: npm run validate

Quality Gate

See Quality Gate Template for universal checks.

Content-specific:

  • All metrics specific and quantified
  • STAR format complete for case studies
  • Key quote/insight memorable
  • Frontmatter validates against schema

<skill_compositions>

Works Well With

  • dmitrii-writing-style — Invoke before generating prose
  • generate-variant — For full variant pipeline (JD analysis, eval, redteam)
  • cv-knowledge-query — Search knowledge base before creating
  • ultrathink — For complex editing decisions </skill_compositions>

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/cv-content-manager

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