메뉴
Compose structured backlog ticket bodies using the Why/Role/Integration/Edges/Touch-points template. Use when user says "ticket authoring", "compose", "write a ticket body", or "author a backlog item". Two subcommands: interview (guided prompts) and compose (autonomous, context-driven).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | backlog-author |
| description | Compose a structured backlog ticket body from a context block, using the Why/Role/Integration/Edges/Touch-points template. Use when user says "compose a ticket", "write a ticket body", or "author a backlog item". |
| argument-hint | compose <context-block> |
Compose one ticket body per invocation from the provided context block (a caller with N pieces invokes N times). Emit only the markdown body to stdout — frontmatter belongs to cortex-create-backlog-item --body.
Emit the five-section markdown body to stdout, sections in order — ## Why, ## Role, ## Integration, ## Edges, ## Touch points — all required except ## Touch points. Prose only: no path:line or §N citations and no fenced code blocks outside ## Touch points, where those forms are the norm.
## Why — the problem in symptom-voice: what is broken, missing, or degraded, in observable terms. Not the solution. Omit this section when it collapses to a restatement of Role's lead.## Role — the job this piece does once the ticket lands that nothing did before (arc42 Responsibility), not its mechanism.## Integration — how it connects inbound and outbound, naming Interface surfaces by name (e.g. "the phase-transition contract").## Edges — structural constraints and boundary conditions: what breaks if an upstream contract changes shape, what this must not do, which non-goals keep scope tight. Each bullet names a contract surface or a non-goal.## Touch points — implementation locations: file paths with line numbers, section indices, code excerpts. Omit when none are known.If an ## Edges bullet needs a path:line to express its constraint, the path:line moves to ## Touch points and a structural summary stays in ## Edges.
Build a refined feature through plan, implement, review, and complete. Use when user says "/cortex-core:build", "build this", "implement this ticket", "plan and build", or names a ticket that already has a spec. Requires research.md and spec.md — run /cortex-core:refine first if either is missing.
Guide the user through the morning report after an overnight session. Walks Executive Summary and report sections, collects answers to deferred questions, advances completed lifecycles to Complete, and auto-closes backlog tickets. Use when the user says "/morning-review", "morning review", or "what happened overnight".
Evaluate overnight runner components against a curated inventory using a 4-question rubric to classify each as load-bearing, experiment-candidate, or likely-deprecated. Use when user says "/harness-review", "review the harness", "audit overnight components", or "check for pruning candidates".
Prepare a backlog item for execution by running it through Clarify → Research → Spec. Use when user says "/cortex-core:refine", "refine backlog item", "spec this out", or "prepare for overnight". Produces cortex/lifecycle/{slug}/research.md and spec.md, then sets status:refined on the backlog item.
Ideation research for topics not ready for implementation — checks aim, investigates the problem space, then decomposes findings into backlog tickets grouped by epic. Use when user says "/cortex-core:discovery", "discover this", "break this down into tickets", "decompose into backlog", or wants to understand a topic before committing to build. Requires a topic argument; for "what should I work on" or "next task" routing without a specific topic, use /cortex-core:dev instead.
Parallel adversarial review — dispatches reviewer agents on distinct challenge angles, then synthesizes their findings. Use when user says "critical review", "pressure test", "adversarial review", or "challenge from multiple angles". Auto-triggers in the lifecycle for Complex + medium/high/critical features before spec approval.