using-agentops

# AgentOps Workflow

You have access to the AgentOps skill set for structured development workflows.

## The RPI Workflow

```
Research → Plan → Implement → Validate
    ↑                            │
    └──── Knowledge Flywheel ────┘
```

### Research Phase

```bash
/research <topic>      # Deep codebase exploration
/knowledge <query>     # Query existing knowledge
```

**Output:** `.agents/research/<topic>.md`

### Plan Phase

```bash
/pre-mortem <spec>     # Simulate failures before implementing
/plan <goal>           # Decompose into trackable issues
```

**Output:** Beads issues with dependencies

### Implement Phase

```bash
/implement <issue>     # Single issue execution
/crank <epic>          # Autonomous single-agent execution
/farm [--agents N]     # Parallel multi-agent execution
```

**Output:** Code changes, tests, documentation

### Validate Phase

```bash
/vibe [target]         # Code validation (security, quality, architecture)
/post-mortem           # Extract learnings after completion
/retro                 # Quick retrospective
```

**Output:** `.agents/learnings/`, `.agents/patterns/`

## Phase-to-Skill Mapping

| Phase | Primary Skill | Supporting Skills |
|-------|---------------|-------------------|
| **Research** | `/research` | `/knowledge`, `/inject` |
| **Plan** | `/plan` | `/pre-mortem` |
| **Implement** | `/implement` | `/crank` (single-agent), `/farm` (multi-agent) |
| **Validate** | `/vibe` | `/retro`, `/post-mortem` |

## Available Skills

| Skill | Purpose |
|-------|---------|
| `/research` | Deep codebase exploration |
| `/pre-mortem` | Failure simulation before implementing |
| `/plan` | Epic decomposition into issues |
| `/implement` | Execute single issue |
| `/crank` | Autonomous single-agent execution |
| `/farm` | Parallel multi-agent execution (Agent Farm) |
| `/vibe` | Code validation |
| `/retro` | Extract learnings |
| `/post-mortem` | Full validation + knowledge extraction |
| `/beads` | Issue tracking operations |
| `/