claude-code-marketplace

Polish AI-written Korean documents into natural human-sounding Korean by editing files in place. Removes translation-ese (직역체) first — catalog patterns get phrase-level substitution, principle-based judgment handles sentence-level rewrites — while never touching code, identifiers, quotes, or terminology. TRIGGER when: user asks to polish, naturalize, or fix awkward Korean in a document file (e.g., "이 문서 다듬어줘", "번역투 고쳐줘", "한국어 자연스럽게 바꿔줘", "AI 말투 좀 고쳐줘", "문서 교정해줘", "이 마크다운 한국어 좀 사람답게", "polish this Korean doc", "fix the translation-ese"). Also trigger with /doctor-korean-document slash command. DO NOT TRIGGER when: user wants content changes, summarization, or translation to another language; the text is not in a file (inline/pasted text is out of scope); the document is not Korean; or the user only wants spelling/spacing lint (use a dedicated linter).

Auto-create or update GitHub Pull Requests with conventional commit-style titles. Detects base branch, generates PR title and description from branch commits, links related issues, and creates the PR via GitHub API. TRIGGER when: user asks to create a PR, open a pull request, push changes for review, or send work upstream (e.g., "PR 만들어줘", "PR 날려", "풀리퀘 생성해줘", "풀리퀘스트 올려줘", "리뷰 보내줘", "리뷰 올려줘", "이거 PR 해줘", "푸시하고 PR 만들어", "코드 리뷰 요청해줘", "이 브랜치 올려줘", "create a PR", "open a pull request", "send this for review", "push this up for review"). Also trigger with /github-pr slash command. DO NOT TRIGGER when: user is reviewing an existing PR, asking about PR status, or discussing PR workflow without intent to create one now.

End-to-end 5-phase pipeline from idea to code-ready state — analyst intake → ralplan → ralph/team → verifier-gated QA → multi-perspective validation. Artifacts land in .dt-handoff/<slug>/. Auto commit/PR PROHIBITED. TRIGGER on "/autopilot", "autopilot", "build me", "create me", "make me", "I want a/an". DO NOT TRIGGER for brainstorming, single bug fixes, or quick changes.

Interactive requirements-clarification interview that turns a vague request into a pipeline-ready spec. Delegates to the `analyst` agent to surface ambiguities, hidden assumptions, and gaps, then resolves each with the user via `AskUserQuestion` — offering concrete candidate answers (with a marked default where one clearly fits) and batching independent clarifications into one call — and writes a clarified `spec.md` that `/autopilot` and `/ralplan` can consume. TRIGGER when the user has a fuzzy idea/spec/request and wants the ambiguity resolved into clear requirements — "clarify this", "ask me what you need to build this", "interview me to nail down requirements", "이거 애매한데 질문해서 정리해줘", "요구사항 명확히 해줘", "모호한 부분 짚어서 스펙으로 만들어줘", "/interview". DO NOT TRIGGER when the request is already unambiguous (go straight to /ralplan or /autopilot), when the user wants to reach their OWN design decisions by being questioned without being handed answers (use buddy:socratic-interview), or when they just want it built ("그냥 만들어줘",

A predict-then-verify + explain-back reading partner for UNFAMILIAR code, so the structure actually lodges in your head instead of evaporating with an AI summary. Instead of summarizing the code for you, it picks a spot, makes you PREDICT what it does (or who calls it, or what happens) via one AskUserQuestion, then reveals the real code so you learn from the gap — and on the core spots it makes you EXPLAIN the module back in your own words until you can reconstruct it. The partner chooses the mode (predict vs explain-back) per spot by difficulty. You build the mental model; the partner never hands it over. TRIGGER: "grok this code", "help me understand this codebase", "read this code with me", "코드 이해 도와줘", "낯선 코드 파악 같이 해줘", "이 코드베이스 익히게 도와줘", "코드 같이 읽자", "예측하며 코드 읽기". DO NOT TRIGGER: the developer just wants a fast summary or answer ("그냥 요약해줘", "just tell me what this does"), needs to ship a fix right now, is doing a simple factual lookup (a signature, one line), or already understands the code and only needs

Socratic maieutic design interview, driven by structured multiple-choice questions. When a developer brings a vague idea, feature, or design problem, sharpen it into clear decisions by posing ONE focused AskUserQuestion at a time — each option carrying its own reasoning ("X — because …") so the choice captures both the decision and its why. The options are a frame to think against, never a verdict; the choice, and the "Other" escape hatch, are always the developer's. The pen stays in their hand. TRIGGER: "socratic", "maieutic", "deep interview", "interview me to think", "help me decide by asking", "산파법", "소크라테스식으로 물어봐줘", "설계 같이 고민해줘", "생각 정리 인터뷰". DO NOT TRIGGER: the developer just wants code or an answer fast ("just build it", "그냥 짜줘"), wants a direct verdict without being questioned, is doing a simple factual lookup, or already has a detailed spec and only needs execution.

PRD-driven persistence loop. Reads .dt-handoff/<slug>/prd.json, drives each story Red→Green→Refactor via test-engineer + executor, verifies acceptance criteria via the verifier agent on fresh evidence, runs reviewer approval, runs code-simplifier cleanup, re-verifies regression, and reports the stopping point. Auto commit/PR PROHIBITED. TRIGGER on "/ralph", "ralph", "끝까지 가줘", "keep going until done".

Consensus panel planning skill. Generates N risk-proportional candidate approaches via `architect` fan-out, then — in one parallel wave — independently evaluates them and has a SEPARATED `critic` adversarially attack each (author≠attacker enforced by dispatch topology) and a distinct `critic` synthesize a ranked consensus ADR at `.dt-handoff/<slug>/plan.md`, marked `pending approval`. Panel width and attack depth scale to risk (LOW/MEDIUM/HIGH). TRIGGER on "/ralplan", "ralplan", "plan this", "합의 계획". DO NOT TRIGGER for execution requests (those go to ralph / autopilot) or for free-form brainstorming.

5-stage parallel multi-agent orchestration. Decomposes a task into stories (team-plan via planner+architect), extracts acceptance criteria (team-prd), executes stories in parallel via test-engineer/executor waves with per-stage verifier gates (team-exec), verifies via reviewer/critic (team-verify), and fixes defects with bounded iteration (team-fix). Cleanup via code-simplifier (skip with --no-deslop). Handoffs at .dt-handoff/<slug>/. Auto commit/PR PROHIBITED — same boundary as ralph. TRIGGER on "/team", "team", "팀으로 진행". DO NOT TRIGGER for single-story tasks.

Severity-rated review of the current diff or a named file. Always delegates to the reviewer agent, and routes security-auditor + doc-writer onto the panel when the diff touches their surface (full panel in slug context), producing CRITICAL/MAJOR/MINOR findings with file:line evidence. TRIGGER when user says "review my changes", "코드 리뷰 해줘", "/code-review", or asks for severity-rated feedback. DO NOT TRIGGER for general code questions or syntax help.

Execute a cURL command and trace the response back through the codebase to find the root cause of bugs. Use this skill to debug API issues by running the actual request and reverse-tracing from the response to the responsible code. TRIGGER when: user shares a cURL command along with a question about a bug, error, or unexpected behavior (e.g., "이 curl 요청이 500 에러가 나는데 왜 그런지 봐줘", "curl로 보내면 잘못된 데이터가 오는데", "이 API가 왜 이렇게 응답하는지 코드에서 찾아줘", "이 요청 디버깅 좀 해줘", "this curl returns 500, help me debug", "why does this API return wrong data"). Also trigger with /curl-debug slash command. DO NOT TRIGGER when: user is just asking to execute a cURL without debugging intent, discussing cURL syntax, or sharing cURL for documentation purposes.

Auto-generate and execute git commits with conventional commit messages. Analyzes staged/unstaged changes, suggests commit splitting when appropriate, and generates structured commit messages following conventional commit format. TRIGGER when: user asks to commit, save changes, organize changes, or wrap up work (e.g., "커밋해줘", "커밋 날려", "변경사항 저장해줘", "변경사항 정리해줘", "작업 마무리해줘", "이거 저장해", "코드 올려줘", "지금까지 한거 커밋", "commit this", "save my work", "wrap this up"). Also trigger with /git-commit slash command. DO NOT TRIGGER when: user is asking about commit history (git log), explaining what a commit is, or discussing commit strategies without intent to act now.

Install the canonical ccstatusline-based Claude Code status line onto this machine. Installs the ccstatusline binary if missing, merges the `statusLine` block into a target settings.json (preserving all other keys), and writes the shipped widget layout (model · thinking-effort · skills · git-branch · context% · session-clock · usage rows) to the ccstatusline config. TRIGGER when: user wants to set up / replicate / install the status line or status bar (e.g. "claude status 설정 설치해줘", "상태줄 깔아줘", "statusline 설정해줘", "내 상태바 세팅 복제해줘", "install the status line", "set up ccstatusline", "replicate my status bar config"). Also trigger with /install-statusline slash command. DO NOT TRIGGER when: user wants to design a brand-new custom status line from scratch (use the built-in statusline-setup agent), is asking what the status line shows conceptually, or only wants to tweak one widget.

REPLACE: one-paragraph description. Include TRIGGER phrases (Korean + English) and explicit DO NOT TRIGGER conditions. The description drives auto-load, so invest in it.