design-tracker

This skill manages the project's design documentation (.claude/docs/DESIGN.md ). It automatically tracks:

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "design-tracker" with this command: npx skills add del-taiseiozaki/claude-code-orchestra/del-taiseiozaki-claude-code-orchestra-design-tracker

Design Tracker Skill

Purpose

This skill manages the project's design documentation (.claude/docs/DESIGN.md ). It automatically tracks:

  • Architecture decisions

  • Implementation plans

  • Library choices and their rationale

  • TODO items and open questions

When to Activate

  • User discusses architecture or design patterns

  • User makes implementation decisions (e.g., "let's use ReAct pattern")

  • User says "record this", "add to design", "document this"

  • User asks "what's our current design?" or "what have we decided?"

  • Important technical decisions are made during conversation

Workflow

Recording Decisions

  • Read existing .claude/docs/DESIGN.md

  • Extract the decision/information from conversation

  • Update the appropriate section

  • Add entry to Changelog with today's date

Sections to Update

Conversation Topic Target Section

Overall goals, purpose Overview

System structure, components Architecture

Patterns (ReAct, etc.) Implementation Plan > Patterns

Library choices Implementation Plan > Libraries

Why we chose X over Y Implementation Plan > Key Decisions

Things to implement later TODO

Unresolved questions Open Questions

Output Format

When recording, confirm in Japanese:

  • What was recorded

  • Which section was updated

  • Brief summary of the change

Language Rules

  • Thinking/Reasoning: English

  • Code examples: English

  • Document content: English (technical terms) + Japanese (descriptions OK)

  • User communication: Japanese

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

context-loader

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

update-design

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

simplify

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

codex-system

No summary provided by upstream source.

Repository SourceNeeds Review