메뉴
Use when the user says: "ship it" or "commit push and PR". Commits, pushes, and creates a PR in one step.
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 the user says: "clean code check", "style review", "LLM smell check", "code hygiene", "nitpick this", "style check", "find style sins", "nitpicker review", "anal retentive review", "exhaustive style review", "no-filter style report". Dispatches three parallel stylistic checkers — llm-checker (training-bias patterns), lazy-checker (deferred debt), and nitpicker (style hygiene) — and consolidates findings into a report organized by checker with a Summary section for orchestration consumption.
Use when the user says: "review my changes", "run the reviewers", "code and integration review", "readability review", "maintainability review", "sniff test this", "WTF check", "code smells", "is this code any good", "fresh eyes on this branch", "review this directory", "check this module", "review this skill", "review these instructions". Dispatches three parallel reviewers — code, integration, and a readability pass for code; consistency, instruction quality, and writing quality for instruction files — and consolidates findings into one prioritized report.
Use when the user says: "spec this out", "help me define what I want to build", "interview me about this idea", "design this change", "write a design doc", or needs to define WHAT and HOW to build something. Proportional discovery interview + codebase investigation → design.md.
Use when the user says: "draft a plan", "create work packages", "generate WPs", "review this plan", or "check the plan". Turns a design doc into task files and validates them against a traceability-focused checklist.
Use when the user says: 'close gaps in this design', 'fill gaps in the spec', 'lightweight design review', 'gap-close this doc', 'completeness review', or wants to verify a doc has all required content before implementation.
Use when the user says: "execute the plan", "orchestrate implementation", or "start executing". Runs tasks task-by-task with implementer + reviewer subagent loop.
| name | mine-ship |
| description | Use when the user says: "ship it" or "commit push and PR". Commits, pushes, and creates a PR in one step. |
| user-invocable | true |
git statusgit diff HEADgit branch --show-currentgit-default-branchgit remote get-url origin 2>/dev/nullShip the current changes: commit, push, and open a PR. Follow each phase in order.
Follow all steps in mine-commit-push exactly (read ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/mine-commit-push/SKILL.md and execute its full workflow — commit quality gates included). When that phase completes successfully — changes committed and pushed — continue to Phase 2 below.
Skip this phase if the branch diff contains only instruction files (.md). Clean-code checkers are for code, not prose. Instruction files are already covered by mine-review's instruction-mode reviewers in Phase 1.
After Phase 1 completes (changes committed and pushed), check for a prior clean-code run:
find /tmp -maxdepth 2 -name 'clean-code-summary.md' -path '*/claude-mine-orchestrate-*' 2>/dev/null | xargs -r ls -t 2>/dev/null | head -5
git rev-parse --short HEAD). If any match, skip this phase with a note: "Stylistic review already completed."/mine-clean-code on the branch diff. Note: prior-run detection only applies when mine-orchestrate ran mine-clean-code. Manual mine-clean-code runs are not detected.When mine-clean-code presents its own next-steps prompt ("What would you like to do with these findings?"), choose "Note and move on" — this phase handles the fix/skip/stop decision.
If mine-clean-code produces findings, present:
AskUserQuestion:
question: "Stylistic review found findings. What next?"
header: "Clean code"
multiSelect: false
options:
- label: "Address findings"
description: "Apply fixes top-to-bottom, then proceed to PR creation"
- label: "Ship anyway"
description: "Proceed to PR creation with findings noted"
- label: "Stop here"
description: "Pause; I'll address findings manually"
refactor: address clean-code findings), and push before proceeding to Phase 2 — mine-create-pr verifies the branch is fully pushedIf mine-clean-code produces no findings, proceed to Phase 2 automatically.
If any checker subagent fails to complete, skip that checker's findings and note "unavailable" in the gate question — do not block PR creation for checker failures.
Follow all steps in mine-create-pr exactly (read ${CLAUDE_CONFIG_DIR:-~/.claude}/skills/mine-create-pr/SKILL.md and execute its full workflow — platform detection, draft PR, changelog entry + PR-number annotation, ready transition). Phase 1 already committed and pushed (so create-pr's push check passes) and already archived task files (so its archival step finds nothing and skips silently). Return the PR URL it produces.