AI builds workshop → You learn how → You build your own
nnn → gogogo → rrr
| Code | Action | Result |
|---|---|---|
nnn | วางแผน | GitHub Issue |
gogogo | ลงมือทำ | Code + Commits |
rrr | สรุป | Retrospective |
Plan → Execute → Reflect → Repeat
วันนี้ใช้จริง:
nnn → สร้าง issue #8 (plan slides)
gogogo → สร้าง slides + PR
/trace → หา context ข้าม repos
ผลลัพธ์: 6 issues, 3 PRs, 34+ slides
# /trace [project-name]
Launch 5 subagents simultaneously:
1. Current Repo Files → grep/find
2. Git History → git log --grep
3. GitHub Issues → gh issue list
4. Other Repos → find ~/Code
5. Retrospectives → grep ψ/memory/
5 agents = 5x faster search
---
description: ตามรอย Project ที่หายไป
allowed-tools:
- Bash
- Grep
- Glob
- Task
---
# /trace - ตามรอย Project ที่หายไป
## Step 0: Timestamp (REQUIRED)
date "+🕐 %H:%M (%A %d %B %Y)"
ARGUMENTS: $ARGUMENTS
allowed-tools = security boundary
### Agent 1: Current Repo Files
subagent_type: context-finder
model: haiku
prompt: |
รัน bash แล้วสรุป:
# Root files ที่ mention project
grep -il "[PROJECT]" *.md 2>/dev/null
# Files + Folders ที่ชื่อตรง
find . -iname "*[PROJECT]*" -type f | head -20
find . -iname "*[PROJECT]*" -type d | head -10
# Content mentions ใน subfolders
grep -ril "[PROJECT]" --include="*.md" \
tools/ projects/ ψ/ .claude/ | head -20
Return: list ของ paths ที่เจอ
### Agent 2: Git History
subagent_type: context-finder
model: haiku
prompt: |
รัน bash แล้วสรุป timeline:
# Commits ที่ mention project
git log --all --oneline --grep="[PROJECT]" | head -15
# Files created/deleted
git log --all --oneline \
--diff-filter=A -- "*[PROJECT]*" | head -10
git log --all --oneline \
--diff-filter=D -- "*[PROJECT]*" | head -10
Return: timeline (Date | Action | Commit)
### Agent 3: GitHub Issues
gh issue list --state all --limit 30 \
--search "[PROJECT]" --json number,title,createdAt
### Agent 4: Other Repos
find ~/Code/github.com -maxdepth 3 \
-iname "*[PROJECT]*" -type d | head -10
### Agent 5: Retrospectives & Docs
grep -ril "[PROJECT]" ψ/memory/retrospectives/ | head -10
grep -ril "[PROJECT]" ψ/memory/learnings/ | head -5
grep -ril "[PROJECT]" ψ/writing/ | head -5
All 5 agents run in parallel!
## 🔍 /trace: [PROJECT]
### 📍 Locations Found
| Source | Path | Status |
### 📅 Timeline (from git)
| Date | Action | Commit | Details |
### 🎫 GitHub Issues
| # | Date | Title |
### 📂 Files (current state)
| Type | Path | Repo |
---
**Current Location**: [where code lives now]
**Recommended Action**: [what to do next]
Issue → Branch → Code → PR → Merge
| Step | Command |
|---|---|
| 1. Issue | gh issue create |
| 2. Branch | git checkout -b feat/xxx |
| 3. Code | Edit files |
| 4. PR | gh pr create |
| 5. Merge | Review → Merge |
ไม่ commit ตรงไป main
v1 (27 slides) → "too detail!" → v2 (12 slides)
| Version | Slides | Feedback |
|---|---|---|
| v1 | 27 | Too tight, too detail |
| v2 | 12 | Good! Overview style |
Lesson: Overview > Detail
// wrangler.jsonc
{
"name": "claude-code-workshops",
"assets": {
"directory": "./public"
}
}
npx wrangler deploy
No worker.js needed for static sites
vault/
├── 00-MOC.md # Map of Content
├── 1x-concepts/ # 10, 11, 12...
├── 2x-short-codes/ # 20, 21, 22...
├── 3x-workflows/ # 30, 31...
└── 4x-slides/ # 40, 41, 42...
Numbered prefixes = ordering
| Don't | Do Instead |
|---|---|
| Detail first | Overview first, iterate |
| Commit to main | Branch → PR → Merge |
| Guess user wants | Ask, get feedback |
| Manual search | Use /trace parallel agents |
---
description: Your command description
allowed-tools:
- Bash
- Task
---
# /your-command
## Step 1: Do something
...
## Step 2: Launch agents
subagent_type: context-finder
prompt: |
Your prompt here
Save to: .claude/commands/your-command.md
nnn → gogogo → rrr = structured workPlan before doing.
Search in parallel.
Learn from feedback.