Menu
Use /cortex-core:requirements to gather requirements or define project scope. Thin orchestrator that routes to /requirements-gather then /requirements-write; disable-model-invocation:true — invoked only by explicit slash command.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Structured feature development lifecycle with phases for research, specification, planning, implementation, review, and completion. Use when user says "/cortex-core:lifecycle", "start a lifecycle", "lifecycle research/specify/plan/implement/review/complete", "start a feature lifecycle", or wants to build a non-trivial feature with structured phases.
Development entry point that analyzes requests and routes to the appropriate workflow. Use when user says "/cortex-core:dev", "what should I work on", "start working on", "dev hub", "where do I start", "next task", "what's next", or describes a feature without naming a specific skill.
Prepare a backlog item for execution by running it through Clarify → Research → Spec. Use when user says "/cortex-core:refine", "refine backlog item", "prepare for overnight", or "prepare feature for execution". Produces cortex/lifecycle/{slug}/research.md and cortex/lifecycle/{slug}/spec.md, then sets status:refined on the backlog item.
Parallel research orchestrator. Use when the user says "/cortex-core:research", "research this topic", "investigate this feature", or when /cortex-core:refine delegates its research phase. Dispatches 3–10 parallel agents across independent angles, synthesizes into research.md or conversation output.
Create git commits with consistent, well-formatted messages. Use when user says "commit", "/cortex-core:commit", "make a commit", "commit these changes", or asks to save/checkpoint their work as a git commit.
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".
| name | requirements |
| description | Use /cortex-core:requirements to gather requirements or define project scope. Thin orchestrator that routes to /requirements-gather then /requirements-write; disable-model-invocation:true — invoked only by explicit slash command. |
| disable-model-invocation | true |
| argument-hint | [area|project|list] |
| inputs | ["$ARGUMENTS: optional — empty or 'project' for project scope; an area kebab-case slug for area scope; 'list' to enumerate existing requirements docs"] |
| outputs | ["cortex/requirements/project.md (project scope) OR cortex/requirements/{area}.md (area scope) — written by /requirements-write"] |
Routing surface for the v2 requirements workflow: parse $ARGUMENTS, then sequence /requirements-gather → /requirements-write.
/cortex-core:requirements — bare invocation; project scope./cortex-core:requirements project — explicit alias of the bare form./cortex-core:requirements {area} — area scope; {area} is a kebab-case slug (e.g. multiplayer, observability)./cortex-core:requirements list — read-only enumeration of cortex/requirements/*.md; skips the gather/write pipeline. Excludes glossary.md — a producer-managed vocabulary artifact (per-term append lifecycle), not a scope-level requirements doc.If $ARGUMENTS == "list": run the inventory verb (excludes glossary.md itself — see above) and act on state, then exit either way:
cortex-list-requirements
absent → report "No requirements documented yet. Run /cortex-core:requirements to start with project-level requirements." ok → render rows as a table (file, scope, last_gathered, requirement_count).
Otherwise resolve scope: empty or project → project; any other single token → that token as the area slug.
Invoke /requirements-gather with the resolved scope and, when cortex/requirements/{scope}.md already exists, pass its path as existing-doc so the interview refines rather than rewrites.
Invoke /requirements-write with the same scope, the returned Q&A block, and the same existing-doc (if any); surface the written artifact path to the user for approval.
After user approval, stage cortex/requirements/ and commit via /cortex-core:commit. Requirements are passive artifacts: do not auto-dispatch any consumer here — downstream skills load them on their own schedule. The glossary is the producer-managed exception (/requirements-gather appends terms inline; consumers still read it passively, no consumer-driven writes).