Phoenix Loop

# Phoenix Loop

Rise from failures. Complete tasks persistently.

When the agent encounters blockers, failures, or repeated friction, this skill starts a self-healing loop: Diagnose -> Extract -> Crystallize -> Verify.

## Core Mechanism

### 1. Diagnose

```powershell
# Read recent blocked items
Get-Content memory/blocked-items.md | Select-String "Blocker" -Context 3

# Extract failure patterns
Get-Content memory/tasks.md | Select-String "Status: failed" -Context 5
```

**Diagnosis Checklist**:
- [ ] Is the failure cause clearly stated?
- [ ] Were at least 2 solution paths attempted?
- [ ] Is minimum unblock input defined?

### 2. Extract

Extract reusable patterns from failures:

```markdown
## Failure Pattern: {pattern_name}
- Trigger: {when_this_happens}
- Root Cause: {root_cause}
- Solution: {fix_steps}
- Verification: {verification_criteria}
```

### 3. Crystallize

Write the lesson to a local skill:

```
skills/local/{pattern_name}-recovery.md
```

**Skill Template**:
```markdown
# {Pattern Name} Recovery

## Trigger
When {condition} happens

## Steps
1. {step_1}
2. {step_2}
3. {step_3}

## Verification
- [ ] {check_1}
- [ ] {check_2}

## Fallback
If failed, execute {fallback_action}
```

### 4. Verify

Next time a similar issue occurs:
1. Search `skills/local/` for matching skills
2. Execute recovery steps
3. Log result to `memory/{date}.md`
4. Update skill if needed

## Privacy Security

**All data stored locally**:
- NO external logging of failure data
- NO API keys or tokens in skill files
- NO upload of user task content
- Only pattern names and solution steps recorded
- Skills stored in `skills/local/` local directory

**Sensitive Data Filter**:
Before writing to any memory or skill, check and remove:
- `apiKey`, `token`, `secret`, `password`
- `Bearer `, `sk-`, `OPENCLAW_`
- Personal emails, phones, addresses

## Executable Completion Criteria

A phoenix-loop task is complete if and only if:

| Criteria | Verification Command |
|----------|------------...