Menü
Break a plan or PRD into vertical-slice issues on the project issue tracker.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | to-issues |
| description | Break a plan or PRD into vertical-slice issues on the project issue tracker. |
| disable-model-invocation | true |
Break work into tracer-bullet vertical slices — each cuts all layers end-to-end, demoable alone.
Run /aiops-setup if tracker config is missing.
issues/*.md published to tracker.task_breakdown phase): lightweight → single tasks.md in .scratch/<slug>/, no tracker publish.docs/agents/issue-tracker.md. For single-session, use tech-spec.md + NOTES.md as input.ready-for-agent unless told otherwise. Don't close parent. For single-session, write tasks.md to .scratch/<slug>/.When in task_breakdown phase (single-session), run as two sub-phases with a human checkpoint between:
Phase 1 — parent tasks (3–5 items)
tech-spec.md + NOTES.mdPhase 2 — sub-task expansion (only after user confirms parent tasks)
blocked_by dependenciestasks.md with YAML frontmatterParent — link if applicable.
What to build — end-to-end behavior, not layer checklist.
Acceptance criteria — checkboxes.
Blocked by — issue refs or "None".
Include YAML frontmatter for structured dependency tracking:
---
tasks:
- id: t1
title: "Add WorkspacePaths dataclass"
blocked_by: []
- id: t2
title: "Wire workspace_paths() resolver"
blocked_by: [t1]
- id: t3
title: "Update path helpers to use WorkspacePaths"
blocked_by: [t1]
- id: t4
title: "Integration tests"
blocked_by: [t2, t3]
waves:
- [t1]
- [t2, t3]
- [t4]
---
# Tasks: <slug>
## Wave 1
- [ ] **t1**: Add WorkspacePaths dataclass — <end-to-end behavior>. Blocked by: None
## Wave 2
- [ ] **t2**: Wire workspace_paths() resolver — <end-to-end behavior>. Blocked by: t1
- [ ] **t3**: Update path helpers to use WorkspacePaths — <end-to-end behavior>. Blocked by: t1
## Wave 3
- [ ] **t4**: Integration tests — <end-to-end behavior>. Blocked by: t2, t3
Group tasks by wave in the body. Waves are computed from blocked_by via topological sort.
Delivery overlay — orchestrates lean ladder, tdd, prune, review with sub-phase gates; commits only on user approval.
Flow Conductor for the aiops bundle. One entry — infers task type, shows plain-language steps, tracks journey in flow.state.yaml, dispatches skill + agent per phase.
Structured design process for the architect agent. Guides from grill conclusions to complete NOTES.md + tech-spec.md plus needed domain documentation updates through constraint gathering, module identification, interface design, alternative exploration, and risk analysis. Use when the architect needs to produce design decisions and technical specifications.
Build and query a persistent code graph for the target project. Uses graphify (Tree-sitter + Louvain clustering) for deterministic structural extraction, then the model adds semantic annotations. Use when the user says build graph, code graph, dependency graph, impact analysis, or when other skills need structured code understanding before proceeding.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Use when the user says architecture review, codebase health, deepening, refactor suggestions, or complains about architectural friction.
Review in three modes — code (diff vs standards/spec), design (NOTES + tech-spec before planning), drift (implementation vs tech-spec before ship). Pick mode from Flow Conductor phase or user intent; do not mix artifact types.