Menu
Start or continue a spec-driven development workflow. Orchestrates plan → implement → verify cycle with approval gates.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | spec |
| description | Start or continue a spec-driven development workflow. Orchestrates plan → implement → verify cycle with approval gates. |
| user-invocable | true |
| argument-hint | [task description] |
Orchestrate structured development through three phases: plan, implement, verify.
/next-level:spec <task description>
~/.next-level/specs/For each status, Read the corresponding reference file and follow its process.
| Status | Phase | Reference |
|---|---|---|
| No spec / PLANNING | Plan | references/spec-plan.md |
| APPROVED / IMPLEMENTING | Implement | references/spec-implement.md |
| COMPLETE / VERIFYING | Verify | references/spec-verify.md |
| VERIFIED | Done | — (report success) |
| FAILED | Implement | references/spec-implement.md (with feedback) |
~/.next-level/specs/<slug>.json:{
"name": "<slug>",
"description": "$ARGUMENTS",
"status": "PLANNING",
"created": "<ISO timestamp>",
"plan": null,
"feedback": []
}
references/spec-plan.md and follow the process with the description~/.next-level/specs/*.jsonBefore starting any phase, estimate context usage. If above 80%, write handoff notes to ~/.next-level/sessions/{session}/continuation.md instead of starting a new phase. Include the spec name, current status, and what phase to resume.
Primary review entrypoint for plans, diffs, commits, subagent results, and pre-submit checks. Selects quick, standard, or deep mode by scale and risk.
Planner-led repo improvement loops with subagents, review gates, Mermaid DAGs, and workflow-aware commits. Use for improve, refactor, audit, or continue-loop requests.
Triage and apply code review feedback with technical verification. Use when a human, reviewer subagent, CI, or adversarial reviewer returns findings or requested changes.
Heavy review mode normally invoked by request-code-review for risky checkpoints, pre-submit stacks, OpenSpec/cflx acceptance, security-sensitive work, or explicit deep review, audit, or red-team requests.
Post-implementation cleanup for recent changes using parallel reuse, quality, and efficiency reviewers. Use after building a feature or fix, before commit, PR, or submit.
End-of-workflow learning loop for skill-guided work. Use at session/checkpoint closeout to classify GitHub/CodeRabbit/human/CI findings, log missed-review patterns, and propose skill improvements only when evidence justifies them.