메뉴
Use when requesting or receiving code review, dispatching review subagents, running CodeRabbit, deep reviews, simplification/cleanup passes, local branch review, ready-for-PR/finalize intent, finalizer workflow, or preparing work for merge.
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
Use when managing per-project backlog folders, feature queues, async agent work items, lifecycle status updates, PR/done/blocked transitions, or status reviews inside an Obsidian vault.
Use when prototyping, authoring agent skills, or asking the agent to zoom out and map unfamiliar code before acting.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Use when reviewing architecture boundaries, hexagonal architecture, clean architecture layers, dependency direction, trust boundaries, uploads, parsers, redirects, or web security risks.
Use when configuring or running hexcheck in a Go repo for hexagonal architecture boundaries, adapter business-logic warnings, and mock discipline.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
| name | code-review-release |
| description | Use when requesting or receiving code review, dispatching review subagents, running CodeRabbit, deep reviews, simplification/cleanup passes, local branch review, ready-for-PR/finalize intent, finalizer workflow, or preparing work for merge. |
Universal rule for every review path: apply code-review-release/subskills/thermo-nuclear-code-quality-review/SKILL.md as the first-priority maintainability baseline. Language-specific, security, correctness, release, CodeRabbit, finalizer, and simplification reviews add extra lenses; they do not replace the thermo-nuclear code-quality bar.
Hooks: if documented behavior changed, run documentation-pass. If work starts/pauses/opens PR/completes, update project-backlog when present.
Ready-for-PR hook: when work is complete, fully committed, and the working tree is clean, resolve the default branch from origin/HEAD with main/master fallback, then autonomously run wrap-up-review first. Only after wrap-up finishes and findings are handled, run coderabbit against the same base. If critical/major/minor findings are applied, recommit, confirm clean tree, then rerun both before declaring ready.
Finalize-intent hook: near PR time, approval + finalize wording (e.g. LGTM lets finalize, good for me, finalize) means the ready-for-PR hook above; do not start CodeRabbit until wrap-up subagents finish.
Load only the matching sub-skill:
| Trigger | Read |
|---|---|
| CodeRabbit, cr review, coderabbit CLI, review my changes | code-review-release/subskills/coderabbit/SKILL.md |
| thermo-nuclear review, thermonuclear review, harsh maintainability review, deep code quality audit | code-review-release/subskills/thermo-nuclear-code-quality-review/SKILL.md |
| deep review, security audit, thorough review, pre-merge review | code-review-release/subskills/deepreview/SKILL.md |
| simplify changed code, cleanup after implementation, reuse/quality/efficiency review, or dispatching parallel review subagents with simplification lenses | code-review-release/subskills/simplify/SKILL.md |
| finalizer workflow, finalize branch through finalizer subagent | code-review-release/subskills/finalizer/SKILL.md |
| ready for PR, approval + finalize intent, LGTM lets finalize, good for me finalize, wrap up review, finishing an implementation or plan phase, adaptive final review before done | code-review-release/subskills/wrap-up-review/SKILL.md |
