Aiops

aiops — Flow Conductor

Single entry for the bundle. Ordinary users only need this command; experts can still /aiops <agent> ….

Invocation

/aiops <what you want>           # Conductor — infer, narrate, dispatch
/aiops 继续 / resume             # Resume from .scratch/<slug>/flow.state.yaml
/aiops <agent-name> <task>       # Expert — direct agent; still update journey if in a flow

Agents: architect, design-reviewer, planner, prototyper, builder, ui-designer, code-reviewer, quality-auditor, gitops

Conductor loop (every turn)

1. Resume or start — Read .scratch/<slug>/flow.state.yaml if user resumes or slug known. If current_phase_id is done, inform user the journey is complete. Else infer slug (kebab-case from description; user may override). See journey.md.
2. Bootstrap — If docs/agents/ missing, run bootstrap inline:
   • No aiops.yaml → silent defaults: local markdown issues + 1:1 triage labels (aiops-setup/aiops-yaml.md).
   • aiops.yaml with issue_tracker.kind: github|gitlab → seed GitHub/GitLab tracker docs from yaml; do not prompt for tracker unless yaml incomplete.
   • Do not ask user to run another command.
3. Plan — Build FlowState from journey + repo signals (see journey.md). Default delivery_mode: single_session unless user confirms multi or heuristics clearly warrant multi. Use flow_cli.py plan to generate the phase list.
4. Narrate — One block from narration.md: Chinese title_zh, body_zh, artifact_zh; English only in title_en. Hide skill/agent names unless user asks.
5. Dispatch — Load agents/<agent>.md when agent set; invoke skill for the phase. Gather .scratch/<slug>/ inputs per agent Inputs.
6. Gate — Before advancing: run flow_cli.py validate --slug <slug> to verify gate artifacts. If validation fails, do not advance. On success, append gate name to gates_satisfied.
7. Advance — Run flow_cli.py advance --slug <slug> to update current_phase_id and phases_done. On handoff, advance journey before writing temp handoff doc.
8. Delivery — When phase is delivery, hand off to /aiops-implement (owns lean → tdd → prune → review). Do not interleave those gates from the conductor.

Task types → phase tail (after bootstrap if needed)

Dispatch rows for AGENTS.md live in skills/manifest.json → dispatch. Phase order detail: skills/aiops/scripts/phases.py.

Explore (opt-in): when explore_requested, insert explore phase after bootstrap (if any) and before task-specific phases.

Multi-session: after design_review → planning_prd → planning_issues → issue_session → delivery per issue. Single-session: after design_review → task_breakdown → delivery.

Prototype branch (optional): handoff → /prototype → handoff back; require VERDICT.md before planner/builder.

Lean is not active during grill/alignment phases.

Multi-session heuristic

Recommend multi-session when: 3+ modules, multiple slices, near smart zone, or AFK per-issue. Default single-session — single-session still includes task_breakdown (lightweight tasks.md); multi-session uses full planning_prd → planning_issues → issue_session.

New personal skill checklist

1. Purpose and trigger scenarios
2. User-invoked vs model-invoked
3. Steps vs reference files (progressive disclosure)
4. Author SKILL.md — Cursor create-skill (External; docs/skill-registry.md)

Reference

• Journey file format: journey.md
• User narration keys: narration.md
• State operations: python3 <aiops-root>/skills/aiops/scripts/flow_cli.py {plan,init,advance,validate,satisfy-gate,phase-gates}
• Project config yaml: aiops-setup/aiops-yaml.md
• Vocabulary: target CONTEXT.md; skill registry: docs/skill-registry.md