인프라·DevOps 스킬

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apache Airflow DAGs, operators, SLA monitoring, and workflow orchestration. Activate on: Airflow, DAG, operator, sensor, scheduler, task dependency, SLA, backfill, XCom. NOT for: dbt transformations (use dbt-analytics-engineer), streaming pipelines (use streaming-pipeline-architect).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use jury_rig-architect), specific tool implementation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and scaffold new skills, subagents, and MCP surfaces. Use when choosing which primitive to create. NOT for invoking existing agents, generic coding help, or deployment work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design RL simulation sandboxes, trajectory datasets, QLoRA/LoRA adaptation plans, eval harnesses, and rollback unhooks for agents learning specific coding behaviors beyond the base model. Use when building or reviewing tool-use training loops, offline trajectories, reward functions, self-improvement harnesses, or Port Daddy agent behavior curricula. NOT for generic ML tutorials, full model training operations, or production deployment without eval gates and safety unhooks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan, evaluate, and adopt agent infrastructure for a named workload. Use for agent runtime/framework selection, agent evaluation or observability plans, memory and tool boundaries, infrastructure cost controls, and organizational adoption. Covers workload-first comparison, risk and recovery planning, held-out evaluation, cost accounting, and staged rollout. Not a vendor ranking or a production certification. NOT for implementing a specific agent behavior (agentic-patterns), building a specific agent (ai-engineer), prompt optimization (prompt-engineer), or conventional ETL workflow design (jury_rig-architect).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Recommend, create, preview, and attach Coval trace-based metrics from OpenTelemetry spans. Use when a user has Coval traces and wants custom trace metrics, trace-aware LLM judge metrics with include_traces, latency, token usage, provider failures, tool behavior, vertical-specific workflow signals, or production monitoring based on trace attributes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Improve Coval trace quality after basic ingestion works. Use when traces are sparse, missing useful STT/LLM/TTS/tool spans, missing attributes needed for Coval built-in metrics, or when a customer wants maximum debugging and observability value from agent traces.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deploy applications and websites to Vercel using the bundled `scripts/deploy.sh` claimable-preview flow. Use when the user asks to deploy to Vercel, wants a preview URL, or says to push a project live on Vercel.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "sandboxの互換性をチェックして", "sandbox設定を確認して", "このプロジェクトでsandboxが使えるか調べて", "sandboxでコマンドが失敗する", "check sandbox compatibility", "verify sandbox settings", "sandbox is blocking my commands", or wants to ensure their development workflow works within Claude Code's sandbox restrictions — either proactively before starting work or reactively after encountering sandbox-related failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Clone a GitHub repository and automatically build a Docker environment for local verification. Creates a verification workspace in WS/, sets up Docker files, launches the environment, and performs health checks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Cloudflareでの新規アプリ設計や大規模移行に先立ち、構成の選定理由と制約を短い設計メモにまとめる。通常のコード修正には使わない。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ローカル開発向けのDockerおよびDocker Composeパターン、コンテナセキュリティ、ネットワーキング、ボリューム戦略、マルチサービスオーケストレーション。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Webアプリケーションのためのデプロイメントワークフロー、CI/CDパイプラインパターン、Dockerコンテナ化、ヘルスチェック、ロールバック戦略、プロダクションレディネスチェックリスト。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle detection, or any "when / how long ago / how long did that take" question. Required for autonomous, parallel, or long-running agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Track and analyze portfolio company performance against plan. Ingests monthly/quarterly financial packages (Excel, PDF), extracts KPIs, flags variances to budget, and produces summary dashboards. Use when reviewing portfolio company financials, preparing board materials, or monitoring covenant compliance. Triggers on "review portfolio company", "monthly financials", "how is [company] performing", "covenant check", or "portfolio update".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a deal involves a cloud consumption commit, a marketplace private offer, or a multi-year enterprise agreement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conventions for docker

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and push multi-platform Docker images to Google Artifact Registry. Use when user asks to build, push, or deploy a Docker image with a tag. Triggers: "build and push", "push docker image", "build with tag", "deploy image".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Align explicit requirements, implicit expectations, non-goals, observable acceptance, evidence, and decision authority before OpenSpec specs and executable tasks finalize. Use when authoring or updating a proposal, design, specs, or tasks, or when a request hides a material product choice. Do not use for routine implementation of an already-authorized task, unrelated conversation, or facts the repository can answer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Finds where every credential on the machine lives, without showing a value. Trigger to list where keys, tokens and passwords are stored (Credential Manager, gh, .env, settings, .mcp.json, Docker); to cut a gh token to least privilege or switch gh accounts; to rotate a key and update its users; after a key was printed, pasted or committed; to check a command that uses a token before it runs; or say keywarden (inventory, scope, rotate, leak, preflight, refresh). Drives op or bw when present. Leak scans and commit email are shieldwarden's; rules and hooks gatewarden's; routine credentials agentwright's; vetting a vault MCP trustwarden's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs Docker Desktop and its WSL2 layer, checking RAM and disk before container work. Trigger when Docker Desktop or a container won't start, vmmem eats RAM or the Docker disk keeps growing; to set a WSL memory cap in .wslconfig; to list or install WSL distros; to bring a compose stack up or down; to prune images and build cache; to run a command in a container; to log in to a registry; or say dockerrunner (audit, check, up, down, prune, status, refresh). Local LLMs (Docker Model Runner too) are lmstudiorunner's; images comfyrunner's; VMs and sandboxes hypervrunner's; Docker's MCP catalog its MCP Toolkit's; registry tokens keywarden's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up, resume or troubleshoot cmail custom-domain email (domain at any registrar → Cloudflare Email Routing → any inbox; optional GoDaddy automation and Gmail send-as): runs cmail setup itself, asking only for missing input, secrets or risky approvals. Don't use for mail migrations or campaigns.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.