Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Use when: user wants to optimize a Dockerfile, create or improve docker-compose configurations, implement multi-stage builds, audit container…
Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template…
Use when the user asks to design database schemas, create ERD diagrams, normalize schemas, plan data migrations, add multi-tenancy or row-level security, generate seed data, optimize queries, choose between SQL and NoSQL, or model data relationships.
Use when the user asks to write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma, Drizzle, TypeORM, or SQLAlchemy.
Produce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, computing the next semantic version from commits, automating…
Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature…
Use when the user asks to review pull requests or merge requests end-to-end on GitHub/GitLab (gh/glab CLI recipes), assess a diff's blast radius, check breaking changes and coverage delta, or run a structured PR review checklist. For deterministic static analysis of files/diffs (secrets, SQLi, complexity scoring)…
Comprehensive incident response framework from detection through resolution and post-incident review. Battle-tested SRE/DevOps practices: severity classification, timeline reconstruction, structured post-incident analysis. Use when declaring an incident, coordinating multi-team response during an outage, leading a…
Generate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows. Templated structure customizable per environment. Use when documenting on-call procedures for a new service, standardizing incident response across teams, or producing runbooks before launching to…
Use when defining, reviewing, or operating SLOs/SLIs/error budgets. Triggers on "define an SLO", "what should our SLO be", "error budget", "burn rate", "SLI", "service level objective", "Google SRE workbook", "multi-window burn-rate alert", or any reliability-target question. Ships SLO designer, error-budget…
Use when building a Kubernetes Operator — custom controllers that reconcile CRD state. Triggers on "build an operator", "CRD design", "reconcile loop", "controller-runtime", "kubebuilder", "operator-sdk", "metacontroller", "KOPF", "operator capability levels", or "custom resource". Ships CRD validator, reconcile-loop…
Design production-ready observability strategies combining metrics, logs, and traces. Includes SLI/SLO design, golden-signals monitoring, alert optimization. Use when adding observability to a new service, refactoring alerting that is too noisy, or designing an SLO program before scaling production load.
Terraform infrastructure-as-code agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Covers module design patterns, state management strategies, provider configuration, security hardening, policy-as-code with Sentinel/OPA, and CI/CD plan/apply workflows. Use when: user wants to design…
Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraphs, analyzes bundle sizes, optimizes database queries, runs load tests with k6 and Artillery. Always measures before and after. Use when investigating a slow endpoint, planning a…
Manage environment-variable hygiene and secrets safety across local development and production. Practical auditing, drift awareness, rotation readiness. Use when auditing .env files for committed secrets, planning a credential rotation, debugging missing-env-var production incidents, or hardening a new project against…
Use when the user asks to set up secret management infrastructure, integrate HashiCorp Vault, configure cloud secret stores (AWS Secrets Manager, Azure Key Vault, GCP Secret Manager), implement secret rotation, or audit secret access patterns.
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline/sequential/parallel/router/orchestrator/evaluator), scaffold a multi-step agent workflow config, choose between single-agent vs multi-agent approaches, generate tool schemas for agents, or evaluate agent…
Produce viral "AI baby podcast / talking baby" entertainment shorts: character design, script with adult-voice contrast, TTS audio, lip-sync generation, and platform-compliant publishing. Use when the user asks to 做宝宝播客 / AI奶娃视频 / 会说话的宝宝 / baby podcast video / 婴儿主播 / 搞笑AI小孩短视频, or wants meme-style talking-character…
Clean, analyze, and summarize spreadsheet data: inspect structure, fix common defects (encoding, merged cells, dates-as-text), compute answers, and deliver a cleaned file plus findings. Use when the user asks to 处理Excel / 清洗数据 / 表格分析 / 这个表怎么回事 / summarize this spreadsheet / fix my csv / 汇总统计. Do NOT use for building…
Generate images from text prompts or reference images through a local generation gateway (text-to-image and image-to-image with polling and download). Use when the user asks to 生成图片 / 画一张 / 文生图 / 图生图 / 改图 / generate an image of / create a picture / edit this photo, or wants AI artwork, illustrations, covers, or…
Turn raw meeting transcripts or rough notes into structured minutes: decisions, action items with owners and deadlines, open questions, and a circulation-ready summary. Use when the user asks to 整理会议纪要 / 会议记录 / notes from this transcript / summarize this meeting / 把录音转的文字整理一下. Do NOT use for live transcription…
Generate music tracks from a text brief through a local generation gateway (style, instruments, mood, duration; polling and download included). Use when the user asks to 生成音乐 / 做首曲子 / 配乐 / background music / generate a song / make BGM / 写段旋律. Do NOT use for text-to-speech, audio editing, trimming MP3s, or…
Produce "大笑奶龙"-style laughing dragon meme videos: generate the chubby yellow dragon character image, animate belly-laugh actions or swap actions from human footage, add processed giggle audio, batch skin variants, and publish with probability-bait captions. Use when the user asks to 做奶龙视频 / 大笑奶龙 / 捧腹奶龙 / 奶龙表情包成精 /…
Build presentation decks: structured outline, per-slide content spec, and a real .pptx file via bundled script (with graceful markdown fallback). Use when the user asks to 做 PPT / 做个演示文稿 / 写个幻灯片 / create slides / make a deck / prepare a presentation about X. Do NOT use for Word documents, spreadsheets, or PDF forms.