Loading...
Loading...
Meta skill explaining the AgentOps workflow. Auto-injected on session start. Covers RPI workflow, Knowledge Flywheel, and skill catalog.
npx skill4agent add boshu2/agentops using-agentopsResearch → Plan → Implement → Validate
↑ │
└──── Knowledge Flywheel ────┘/research <topic> # Deep codebase exploration
/knowledge <query> # Query existing knowledge.agents/research/<topic>.md/pre-mortem <spec> # Simulate failures before implementing
/plan <goal> # Decompose into trackable issues/implement <issue> # Single issue execution
/crank <epic> # Autonomous epic loop (uses swarm for waves)
/swarm # Parallel execution (fresh context per agent)/vibe [target] # Code validation (security, quality, architecture)
/post-mortem # Extract learnings after completion
/retro # Quick retrospective.agents/learnings/.agents/patterns/| Phase | Primary Skill | Supporting Skills |
|---|---|---|
| Research | | |
| Plan | | |
| Implement | | |
| Validate | | |
/implement/crank/swarm/ratchet| Skill | Purpose |
|---|---|
| Deep codebase exploration |
| Failure simulation before implementing |
| Epic decomposition into issues |
| Execute single issue |
| Autonomous epic loop (uses swarm for each wave) |
| Fresh-context parallel execution (Ralph pattern) |
| Code validation |
| Extract learnings |
| Full validation + knowledge extraction |
| Issue tracking operations |
| Root cause analysis |
| Query knowledge artifacts |
| Code complexity analysis |
| Documentation generation |
| Trace artifact lineage to sources |
| Trace design decisions through history |
/post-mortem/research.agents/learnings/.agents/patterns/| Say This | Runs |
|---|---|
| "I need to understand how auth works" | |
| "Check my code for issues" | |
| "What could go wrong with this?" | |
| "Let's execute this epic" | |
| "Spawn agents to work in parallel" | |
| "How did we decide on this?" | |
| "Where did this learning come from?" | |
bd ready # Unblocked issues
bd show <id> # Issue details
bd close <id> # Close issue
bd sync # Sync with git