branch-and-pr
Create a branch from unstaged changes, commit with conventional message, and open a PR. Use when user wants to quickly ship current work.
semantic-committing
コミット時、「commit」「git add」「変更を分割」の言及時に使用。git diffを分析し、変更を論理的な意味単位に分割してコミットする。git-sequential-stageでhunk単位のステージングを行う。
mcp-filesystem-browse
Browse local workspace files via MCP filesystem tools (docker-fs).
gha-sha-reference
ユーザーがGitHub Actionsのタグ参照をSHA参照に変換するよう要求したときに発動してください。uses:フィールドのタグ参照を自動的にSHA参照（コミットハッシュ + コメント付きバージョン）に変換します。
git-commit-helper
git diff를 분석하여 설명적인 커밋 메시지를 생성합니다. 사용자가 커밋 메시지 작성이나 스테이징된 변경사항 검토를 요청할 때 사용합니다.
github-repo-skill
Guide for creating new GitHub repos and best practice for existing GitHub repos, applicable to both code and non-code projects
grafana-loki-logcli
Query and explore logs in Grafana Loki via the logcli command-line tool. Use when a user asks to pull logs for analysis.
deploying-triton
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.
helm-values
Update Helm chart values, bump versions, validate templates, or compare staging vs production config. Use when modifying deployment configuration.
infra-debug
Debug infrastructure and deployment issues. Inspect pods, check logs, view events, diagnose ingress/networking, and troubleshoot Kubernetes or Docker problems.
feature-flags-and-kill-switches
Use when implementing runtime feature toggles, emergency kill switches, or gradual rollout controls in Apex using Custom Metadata Types, Custom Permissions, or Hierarchical Custom Settings. NOT for Custom Metadata Type fundamentals — see custom-metadata-types skill for CMDT basics.
1c-bsp-registration
Добавить функцию регистрации БСП (СведенияОВнешнейОбработке) в модуль объекта обработки
mirrord-ci
Help users set up mirrord in CI pipelines for testing against real Kubernetes environments. Use when users want to run end-to-end tests, integration tests, or automated tests in CI using mirrord to connect to staging/shared clusters.
mirrord-operator
Help users install and configure the mirrord operator for team environments. Use when users ask about operator setup, Helm installation, licensing, or multi-user mirrord deployments.
prompt-injection-defense
Multi-layered security system protecting against prompt injection, secret extraction, and malicious content. Based on defense-in-depth principles.
qa-platform
通过 QA 平台 API 管理集群/工作流/发版/伸缩，并解析集群 FE 信息；用于申请集群或查询 QA 平台集群信息时使用。
sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud)
gke
Auto-activate for kubectl commands, k8s/ directory, Helm charts. Kubernetes on GCP expertise for GKE. Produces Kubernetes deployments, Helm charts, cluster configurations, GPU/TPU workloads, AlloyDB/Cloud SQL Auth Proxy sidecars, and batch job patterns for GKE on GCP. Use when: running kubectl, Helm charts, pod/node pool management, workload identity, Kubernetes deployments, cluster scaling, GPU node pools, database sidecars, or any GKE troubleshooting. Not for Cloud Run (see cloud-run), generic Kubernetes outside GCP, or local k8s (minikube/kind).
docker
Auto-activate for Dockerfile, docker-compose.yml, docker-compose.yaml, .dockerignore. Docker expertise: multi-stage builds, distroless images, Compose, BuildKit, and container optimization. Use when: writing Dockerfiles, optimizing image size, configuring docker-compose, using BuildKit features, or deploying containerized applications. Produces optimized Dockerfiles with multi-stage builds, Compose configurations, and BuildKit patterns. Not for Podman (see podman) or container orchestration (see gke/cloud-run).
managing-services
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.
qrspi-structure
Create structure outline — vertical phases with test checkpoints (QRSPI step 4 of 5)
