design-tracker
Skill18 starsChanged 9 months agoMITView on GitHub
PROACTIVELY track and document project design decisions without being asked. Activate automatically when detecting architecture discussions, implementation decisions, pattern choices, library selections, or any technical decisions. Also use when user explicitly says "記録して", "設計どうなってる", "record this". Do NOT wait for user to ask - record important decisions immediately.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Update the appropriate section
- Distinctive: line 31
Add entry to Changelog with today's date
- Distinctive: line 47
When recording, confirm in Korean:
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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 Korean:
- 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) + Korean (descriptions OK)
- User communication: Korean
Other versions2 projects use a version of this.
Word for word · 1
- ilhae-ai/claude-code-orchestrator★ 18100% same
Edited · 0
None found.
Wrote their own version · 1
- DeL-TaiseiOzaki/claude-code-orchestra★ 194same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- checkpointingSkill
- codex-systemSkill
- gemini-systemSkill
- initSkill
- planSkill
- research-libSkill
- simplifySkill
- startprojectSkill
- tddSkill
- update-designSkill
- update-lib-docsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.