context-preservation
について
このスキルは、ワークフローのフェーズ間やセッション間の移行時にコンテキストを維持するための構造化された要約を生成します。フェーズ引き継ぎ、進捗追跡、セッション再開のためのテンプレートを提供します。RQPIVフェーズ間またはサブエージェント間での引き継ぎ時に継続性を確保するためにご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context-preservation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
Context Preservation Skill
Purpose
Maintain context continuity across phases and sessions.
When to Use
- Transitioning between RQPIV phases
- Handing off between sub-agents
- Pausing work for later resumption
- Creating progress reports
Templates
Phase Handoff
Reference: templates/handoff-template.md
Use when transitioning from one phase to another. Captures:
- Summary of completed work
- Key findings and decisions
- Artifacts created
- Recommendations for next phase
Progress Summary
Reference: templates/progress-summary.md
Use for tracking ongoing work:
- Completed tasks
- In-progress items
- Blocked items
- Next steps
Session Resume
Reference: templates/session-resume.md
Use when resuming interrupted work:
- Last known state
- Files to reload
- Continue point
Context Preservation Process
At Phase Start
- Read previous phase handoff
- Load relevant artifacts
- Note key constraints/decisions
- Begin phase work
During Phase
- Update progress summary as work progresses
- Document significant decisions
- Note any blockers or issues
At Phase End
- Create comprehensive handoff
- List all artifacts created
- Provide recommendations
- Clear next actions
Artifact Naming Convention
{type}-{session}-{timestamp}.md
Examples:
handoff-auth-feature-20251215.mdprogress-auth-feature-20251215-1430.mdsession-resume-auth-feature.md
Storage Locations
| Artifact Type | Location |
|---|---|
| Handoffs | plans/sessions/{session}/ |
| Progress | plans/sessions/{session}/ |
| Resume | plans/sessions/{session}/ |
Best Practices
For Handoffs
- Be concise but complete
- Include file paths for referenced artifacts
- Highlight decisions that affect future phases
- Note any assumptions made
For Progress
- Update frequently (after each significant action)
- Be honest about blockers
- Include time context
For Resume
- Capture exact stopping point
- List files to re-read
- Include any temporary notes
GitHub リポジトリ
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.
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.
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.
Algorithmic Art Generation
メタThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
