checklist（checklist 搜索）

Checklist 📋

Collaborative task checklist manager for AI agents with advanced execution modes.

🎯 When to Use

Use this skill when:

• Multi-agent collaboration - Multiple AI agents need to coordinate
• Sequential tasks - Steps must execute in order
• Parallel tasks - Steps can run simultaneously
• Looping workflows - Repeat until condition is met
• Complex coordination - Avoid deadlocks and infinite loops

🌐 Execution Modes

1. Sequential (串行)

Steps execute one after another:

A → B → C → D

2. Parallel (并行)

Steps execute simultaneously:

A
B ← Branch together
C

3. Loop (循环)

Repeat until exit condition:

while condition:
    A → B
    if exit_condition:
        break

⚡ Quick Commands

Execution Control

# Set execution mode
checklist mode sequential   # 串行
checklist mode parallel    # 并行
checklist mode loop       # 循环

# Configure loop
checklist loop set 5                 # Set max 5 iterations
checklist loop condition "<expr>"   # Set exit condition
checklist loop count                 # Show current loop count

# Run checklist
checklist run                        # Execute with current mode
checklist run --dry-run             # Preview without executing

# Safety
checklist check                      # Check for deadlocks
checklist validate                   # Validate entire workflow

Agent Commands

checklist agent register <name>
checklist agent use <name>
checklist assign <item> <agent>
checklist claim
checklist status

Task Commands

checklist create <template>
checklist done <item>
checklist depend <item> <dep>
checklist tree

🔄 Execution Modes Detail

Sequential Mode

✅ Sequential: Items execute in order
   1 → 2 → 3 → 4 → 5

✅ Item 3 can only start after Item 2 completes

Parallel Mode

✅ Parallel: Items in same "group" run together
   Group 1: [1, 2] (parallel)
         ↓
   Group 2: [3, 4] (parallel)
         ↓
   Group 3: [5] (final)

Loop Mode

✅ Loop: Repeat until exit condition

Loop Config:
  - Max iterations: 5 (default, configurable)
  - Exit conditions:
    - All items done
    - Custom condition met
    - Manual break

Loop Example:
  Iteration 1: [1, 2, 3] → Check exit → Continue
  Iteration 2: [1, 2, 3] → Check exit → Continue
  Iteration 3: [1, 2, 3] → Exit condition met → Stop

🛡️ Safety Features

1. Loop Protection

# Default: Max 5 iterations
checklist loop set 5

# After 5 loops, automatically exits
# Even if not all items complete

2. Exit Conditions

# Exit when specific item done
checklist loop condition "item.5.done == true"

# Exit when all required items done
checklist loop condition "all_required_done"

# Exit when iteration count reached
checklist loop condition "count >= 5"

3. Deadlock Prevention

# Check for potential deadlocks
checklist check

🔍 Deadlock Detection:
   - Circular dependencies: NONE
   - Unreachable items: NONE
   - Agent conflicts: NONE
   ✅ Workflow is safe to execute

4. Validation

# Validate entire workflow
checklist validate

🔍 Validation:
   - All items have valid references: ✅
   - No circular dependencies: ✅
   - Agents assigned: 3/15
   - Max loop iterations: 5
   - Exit condition: defined
   ✅ Checklist is valid

📋 Usage Examples

Example 1: Sequential Deployment

User: Deploy app sequentially

AI: [Execute: checklist create deploy]
[Execute: checklist mode sequential]

✅ Mode: Sequential

Execution Order:
  ⏳ 1. Run tests
  ⏳ 2. Build
  ⏳ 3. Deploy to staging
  ⏳ 4. Verify
  ⏳ 5. Deploy to prod

Example 2: Parallel Testing

User: Run tests in parallel

AI: [Execute: checklist create test-suite]
[Execute: checklist mode parallel]

✅ Mode: Parallel

Parallel Groups:
  Group 1 (concurrent):
    🔄 Unit tests
    🔄 Integration tests  
    🔄 Lint checks
    ↓ All complete →
  Group 2:
    ✅ Generate report

Example 3: Loop with Exit

User: Poll API until successful, max 5 times

AI: [Execute: checklist create api-poll]
[Execute: checklist mode loop]
[Execute: checklist loop set 5]
[Execute: checklist loop condition "item.3.done == true"]

Loop Config:
  - Max iterations: 5
  - Exit: item #3 (API success)
  - Current: 0/5

Iteration 1:
  ⏳ 1. Send request
  ⏳ 2. Check response
  ⏳ 3. Verify success
  → Not done, continue...

Iteration 3:
  ⏳ 1. Send request
  ⏳ 2. Check response
  ✅ 3. Verify success ← Exit condition met!
  
🔄 Loop exited at iteration 3
✅ Exit condition satisfied

Example 4: Deadlock Prevention

User: Create conflicting dependencies

AI: [Execute: checklist add "Task A"]
[Execute: checklist add "Task B"]
[Execute: checklist depend 1 2]
[Execute: checklist depend 2 1]

[Execute: checklist check]

🔍 Deadlock Detection:
   ⚠️  WARNING: Circular dependency detected!
   
   1 → 2 → 1
   
   Resolution suggestions:
   - Remove one dependency
   - Merge into single item
   
✅ Checklist NOT safe - fix before running

🔧 Implementation

Loop State

{
  "loop": {
    "enabled": true,
    "mode": "sequential|parallel|loop",
    "max_iterations": 5,
    "current_iteration": 0,
    "exit_condition": "item.3.done == true",
    "exit_reason": "condition_met|max_reached|manual"
  }
}

Safety Checks

Before Execution:
1. Validate all references ✓
2. Check circular dependencies ✓
3. Verify agents available ✓
4. Check loop config ✓
5. Confirm exit condition ✓

During Execution:
- Monitor for infinite loops
- Track iteration count
- Check exit conditions

After Execution:
- Final validation
- Generate completion report

🎯 Best Practices

1. Always Set Exit Conditions

# Good
checklist loop condition "item.success.done == true"

# With timeout
checklist loop set 10

2. Use Sequential for Dependent Tasks

checklist mode sequential
checklist depend 2 1
checklist depend 3 2

3. Use Parallel for Independent Tasks

checklist mode parallel
# Items in same group run together

4. Check Before Running

checklist check   # Deadlock check
checklist validate   # Full validation

5. Monitor Loop Count

checklist loop count   # Show current iteration

⚠️ Important Notes

Loop Safety

Maximum Limits

🦞 Summary

One line: Complex task → Choose mode (sequential/parallel/loop) → Set safety limits → Run with confidence → Automatic exit