debug-council

Files (1)

• SKILL.md

SKILL.md (first lines)

# Debug Council: Research-Aligned Self-Consistency

Pure implementation of self-consistency (Wang et al., 2022). Each agent receives the **raw user prompt** and explores/debugs **independently**. No pre-processing, no shared context. Majority voting selects the answer.

**Use this for bugs and problems with ONE correct answer.**

## Step 0: Ask User How Many Agents

Before doing anything else, **ask the user how many solver agents to use**:

```
How many debug agents would you like me to use? (3-10)

Recommendations:
- 3 agents: Faster, still reliable
- 5 agents: Good balance
- 7 agents: High confidence
- 10 agents: Maximum confidence (critical bugs)

Note: Each agent will independently explore the codebase and find the bug.
This takes longer but provides true independence per the research.
```

Wait for the user's response. If they specified a number (e.g., "debug council of 5"), use that.

**Minimum: 3 agents** | **Maximum: 10 agents**

---

## CRITICAL: Pure Research Alignment

### What This Means

1. **NO orchestrator exploration** - Do NOT read files or gather context before spawning agents
2. **Raw user prompt to all agents** - Each agent gets the user's original request, unchanged
3. **Each agent explores independently** - Agents discover the codebase themselves
4. **True independence** - No shared context, no cross-contamination

### Why This Matters

The research shows that **independent samples** converge on correct answers. If we pre-process or share context, we:
- Introduce orchestrator bias
- Reduce independence
- May miss what individual agents would discover

---

## Workflow

### Step 1: Capture the Raw User Prompt

Take the user's request **exactly as stated**. Do NOT:
- ❌ Read files first
- ❌ Explore the codebase
- ❌ Add context
- ❌ Rephrase or enhance the prompt

Just capture what the user said.

### Step 2: Spawn Agents IN PARALLEL with RAW PROMPT

Spawn ALL agents simultaneously. Each gets the **exact same raw prompt**:

```
Task(agent: "debug-solver-1", prompt: "[USER'S EXACT WORDS]")
Task(agent: "debug-solver-2", prompt: "[USER'S EXACT WORDS]")
Task(agent: "debug-solver-3", prompt: "[USER'S EXACT WORDS]")
... (all in the SAME batch - parallel execution)
```

**DO NOT modify the prompt. DO NOT add context. Raw user words only.**

### Step 3: Agents Work Independently

Each agent will:
1. Read and understand the user's request
2. Explore the codebase using their tools (Read, Grep, Glob, LS)
3. Identify the root cause
4. Reason through solutions (chain-of-thought)
5. Generate a complete fix

**Each agent works in complete isolation** - they cannot see what other agents are doing or have found.

### Step 4: Track Progress & Collect Solutions

As agents complete, **show progress to the user**:

```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
                     AGENT PROGRESS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
☑ Agent 1 - Complete
☑ Agent 2 - Complete  
☑ Agent 3 - Complete
☐ Agent 4 - Working...
☐ Agent 5 - Working...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

Update this display as each agent finishes. When all complete:

```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
                     AGENT PROGRESS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
☑ Agent 1 - Complete ✓
☑ Agent 2 - Complete ✓
☑ Agent 3 - Complete ✓
☑ Agent 4 - Complete ✓
☑ Agent 5 - Complete ✓

All agents finished! Analyzing solutions...
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

Collect all outputs for voting.

### Step 5: Majority Voting

From michaelboeding/skills, MIT.

More from michaelboeding/skills