agent-skills

Runs an explicit pointer-document-driven review, plan, work, and feedback loop with multiple agents, scheduling independent review, verification, and implementation work concurrently and pipelining revision-fenced read-only preparation between cycles until the living plan or policy converges or 128 cycles are reached. Safe for concurrent runs from different tools against one pointer. Use only when the user explicitly invokes `$rpf`; never trigger implicitly for ordinary review, planning, implementation, commit, or deployment requests.

Open AIR Workbench to discover local Agent Skills, visualize and round-trip a Skill workflow as AIR (Agent Intermediate Representation), review a native Codex or Claude plan, inspect observable execution evidence, or promote a reviewed plan or trace into a Skill draft. Use only when the user explicitly asks for AIR Workbench, the legacy Workflow Studio, Skill-to-graph or graph-to-Skill conversion, visual workflow editing, plan approval, observable tracing, or plan/trace promotion. Do not trigger for ordinary Skill execution, general planning, or routine Codex/Claude requests.

기존 한국어 초안을 의미·사실·수치·인용·문서 구조와 작성자의 목소리를 보존하며 자연스럽게 퇴고한다. 사용자가 한국어 글의 윤문, 퇴고, 교정, 번역투 완화, 기계적이거나 AI 같은 문체 완화, 간결화, 톤 정리를 명시적으로 요청할 때 사용한다. 빈 문서에서 새 글을 쓰는 요청, 번역·요약·사실 확장, 코드 수정에는 사용하지 않는다. PR·Linear·Slack·Notion 문서는 해당 문서의 내용을 작성하는 일반 요청이 아니라 문체 편집을 명시적으로 요청한 경우에만 사용한다.

Retrieves and stores credentials in the user's self-hosted Vaultwarden via the `bw` CLI. Use whenever a task needs a credential the environment does not already provide — npm/PyPI publish tokens, API keys, DB passwords, registry logins — and before ever telling the user a credential is missing. Triggers on "vault 조회", "API 키 가져와", "비밀번호 저장", "secret 등록", "토큰 어디", "npm token", "publish token", "배포 토큰", "credentials", "401 unauthorized".

Synthetic AIR example with no private session content

Run bounded parallel implementation with isolated workers (native worktrees or Codex), respect a dependency DAG, and verify each worker's diff before integrating. Use only when the user explicitly requests background, parallel, or multi-agent implementation, such as "백그라운드 구현", "bg impl", or "병렬 구현". Do not trigger for ordinary implementation or code-writing requests.

Run bounded parallel planning with independent planner personas and optional multi-LLM workers, then synthesize a single plan via stance-steered consensus with explicit conflicts and open questions. Use only when the user explicitly requests background, parallel, or multi-agent planning, such as "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", or "N명이 기획". Do not trigger for ordinary planning or design requests.

Run bounded parallel code reviews with independent persona reviewers, verify findings adversarially, merge and prioritize by root cause, and optionally repeat a review-fix-verify cycle. Use only when the user explicitly requests a background, parallel, multi-agent, persona, multi-LLM, or iterative review such as "bg review", "멀티 리뷰", "페르소나 리뷰", "리뷰 루프", or "keep reviewing". Do not trigger for an ordinary code review.

Save project context and articles to the configured Obsidian Vault, and publish Markdown to docs.jiun.dev through the Vault sync workflow. Use for "obsidian 업로드", "옵시디언 저장", "vault 업로드", "아티클 저장", "문서 공개", "docs 업로드", "외부 공유", or "publish" requests. Use direct server maintenance only when the user explicitly asks to inspect, temporarily push, or delete a docs.jiun.dev document.

Creates and manages incident reports for jiun.dev/status with consistent formatting. Generates frontmatter, timeline, and body sections based on severity. Use for "인시던트 작성", "장애 보고서", "incident report", "status 작성", "장애 기록" requests.

Discovers relevant project context in Markdown documentation by matching the current task to plans, architecture, guides, and operations notes. Use when a request depends on existing project decisions or explicitly asks to inspect project context. Do not trigger for simple questions or tasks that already have sufficient context.

Locates existing global context files under ~/.agents without assuming that optional files exist. Use when a task needs the user's profile, security rules, IaC conventions, service registry, Notion/Obsidian/Vault configuration, personas, or a direct "내 정보" or "글로벌 설정" lookup. Do not use it to enumerate installed skills.

Capture reproducible real-app App Store screenshots for iOS, iPadOS, and macOS; compose marketing frames; upload screenshot assets; and perform authenticated App Store Connect API inspection for apps, builds, and beta groups. Use for "App Store 스크린샷", "앱스토어 스크린샷", "스토어 이미지 업로드", "ASC API 조회", "TestFlight 빌드 조회", "screenshot capture", or "store screenshots" requests. Do not use for generic browser automation.

Guides local Git commit preparation and pull-request drafting with staged-diff and secret checks. Use when the user asks to commit changes, prepare a conventional commit, or draft a PR. When a dedicated GitHub publishing workflow is available, use it for pushing and opening the PR after these local checks.

Manages Discord servers/channels via REST API. Supports channel CRUD, permissions, messaging, and webhooks. Use for "Discord", "디스코드", "채널 관리", "discord bot" requests.

Manages Kubernetes clusters via kubectl. Supports pod/deployment/service management, log viewing, port-forwarding, and debugging. Use for "k8s", "kubectl", "파드", cluster management tasks.

Uploads Claude session summaries or markdown reports to Notion. Use for "노션 업로드", "결과 저장", "notion 정리", "세션 요약", "리포트 업로드", "보고서 작성" requests.

Centrally manages Docker containers and services. Supports service registration, listing, status updates, and port conflict detection. Use for "서비스 등록", "서비스 목록", "포트 확인", "컨테이너 관리", "docker 상태" requests.

Develops Slack apps and API integrations. Supports Bolt framework, Block Kit UI, event handling, and slash commands. Use for "Slack", "슬랙", "봇", "webhook" requests or Slack app development.

Audits and maintains a local skill collection, including discovery, Codex compatibility, trigger scope, installation paths, bundled resources, and validation. Use for "스킬 분석", "스킬 현황", "스킬 점검", "스킬 개선", or skill ecosystem maintenance. Use the built-in skill creator for new skills and substantial rewrites.

Converts and processes audio files using ffmpeg. Supports format conversion, sample rate changes, mono/stereo conversion, and segment splitting. Use for "오디오 변환", "wav 변환", "샘플레이트", "ffmpeg" requests.

Audits repository security by analyzing current code and commit history for sensitive information leaks. Detects API keys, passwords, and credentials. Use for "보안 점검", "보안 감사", "security audit", "민감 정보 검사" requests.

Prepares IaC project deployment by analyzing the current project and generating K8s manifests, Dockerfiles, CI/CD workflows, Prometheus metrics, Grafana dashboards, Gitea mirror, webhooks, and secrets. Use for "배포 준비", "IaC 설정", "k8s 매니페스트", "deploy prep" requests.

Interviews the user relentlessly about a plan or design until you both reach a shared understanding, resolving each branch of the decision tree before any code is written. Use when the user wants to stress-test a plan, pressure-test a design, or says "grill me", "계획 검증", "그릴미", "설계 압박 질문".

Provides Playwright-based browser automation and E2E testing. Supports screenshots, web scraping, and form automation. Use for "브라우저", "스크린샷", "E2E 테스트", "웹 스크래핑" requests.

Synchronizes ML model files across servers. Supports rsync-based transfer with bandwidth control and checksum verification. Use for "모델 동기화", "모델 배포", "rsync 모델", "서버로 전송" requests.

Reads and manages tasks from Obsidian Vault's TaskManager. Supports Board.md (Kanban), Table.md (Dataview), Notes/*, with automatic workspace project sync. Use for "작업 목록", "할일 조회", "task 읽기", "obsidian 작업" requests.

Analyzes the current repository's service from a business model perspective. Multiple BM expert agents (revenue strategist, market analyst, user value analyst, growth strategist) analyze in parallel and suggest monetization strategies. Use for "BM 분석", "수익화 분석", "비즈니스 모델 분석" requests.

Analyzes business proposals and RFP documents, evaluating pricing, deadlines, and technical specifications for feasibility. Generates go/no-go reports. Use for proposal analysis, RFP review, bidding assessment, or business feasibility evaluation.

Evaluates context similarity between new and existing work, automatically creating git worktree on a new branch when tasks differ. Activates on task start, new feature implementation, or switching to different issues.

Runs ML model benchmarks and evaluations. Measures inference speed, memory usage, and accuracy metrics. Use for "벤치마크", "모델 평가", "성능 테스트", "inference 속도" requests.

Deploys and manages NVIDIA Triton Inference Server containers. Automates model repository setup, config generation, and health checks. Use for "triton 서버", "triton 실행", "모델 서빙", "inference server" requests.