DevOps
CI/CD、基礎設施和雲端部署技能
16146 skills in this category
Subcategories
machine-learning
Supervised/unsupervised learning, model selection, evaluation, and scikit-learn. Use for building classification, regression, or clustering models.
Background Build Monitor
Use this skill when applying home-manager or darwin configurations that require long-running builds. Automatically runs builds in background, monitors progress with appropriate polling intervals, and reports status updates without overwhelming the user. Triggered by "apply changes", "rebuild", "make home", or "switch configuration".
explore-codebase
Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.
runbook
Generate operational runbooks for services, procedures, or incident response
educational-lab-ui
Educational Lab UI Design System - A polished, approachable design aesthetic for educational and learning applications. Combines scientific precision with warmth and accessibility for student-facing interfaces (ages 13+).
cloud-deployment
Provides guidance and resources for deploying applications to various cloud platforms like Vercel, Railway, Render, and Fly.io. Use this skill when a user asks to deploy an application, set up a cloud environment, or needs help with cloud configuration, CI/CD, custom domains, and rollbacks for these platforms.
create-specs
Transform reverse-engineering documentation into GitHub Spec Kit format. Initializes .specify/ directory, creates constitution.md, generates specifications from reverse-engineered docs, and sets up for /speckit slash commands. This is Step 3 of 6 in the reverse engineering process.
universal-timing
Use when learning animation timing fundamentals - principles that apply regardless of duration, the foundational rules that scale across all time ranges
artifact-aggregator
Create tiered reports (micro/standard/comprehensive) based on task complexity. Tier 1 (200-500 words) for Level 1 tasks, Tier 2 (500-1500 words) for Level 2, Tier 3 (1500-5000 words) for Level 3 epics. Synthesizes agent outputs into concise, scannable reports without duplication. Uses density over volume, actionable over descriptive. Triggers ONLY after multi-agent completion (2+ agents) or complex investigations. NOT for single-agent trivial tasks.
frontend-htmx
Axum + Askama + HTMX stack for single-binary web apps. Use when: building server-rendered UI, lightweight frontends, single deployable binary. Triggers: "htmx", "askama", "templates", "server-rendered", "single binary frontend".
training-designer
This skill should be used when designing training programs, individual workshop sessions, or learning modules using evidence-based frameworks. Use this skill to structure sessions with TBR 4Cs (Connection, Concepts, Concrete Practice, Conclusion), create learning objectives, apply brain-friendly principles, and design session flow.
sound-engineer
Expert in spatial audio, procedural sound design, game audio middleware, and app UX sound design. Specializes in HRTF/Ambisonics, Wwise/FMOD integration, UI sound design, and adaptive music systems. Activate on 'spatial audio', 'HRTF', 'binaural', 'Wwise', 'FMOD', 'procedural sound', 'footstep system', 'adaptive music', 'UI sounds', 'notification audio', 'sonic branding'. NOT for music composition/production (use DAW), audio post-production for film (linear media), voice cloning/TTS (use voice-audio-engineer), podcast editing (use standard audio editors), or hardware design.
Specification-Driven Development
This skill should be used when the user asks about "spec methodology", "specification workflow", "spec-driven development", "how to write specs", "spec best practices", "specification templates", or needs guidance on creating, validating, decomposing, or executing specifications for software development.
moai-workflow-testing
Comprehensive development workflow specialist combining TDD, debugging, performance optimization, code review, and quality assurance into unified development workflows
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Creating Claude Code Skills
This skill guides the process of creating new Claude Code skills, covering skill anatomy, frontmatter format, naming conventions, organization patterns, and when to use personal vs company-specific skills. Use this skill when you want to create a new skill or understand skill structure.
collaborating-with-codex
Collaborates with OpenAI Codex as an external AI agent for second opinions on complex decisions. Provides guidelines for brainstorming, plan validation, and code review workflows. Use when making architectural decisions, validating implementation plans, reviewing code after significant changes, or consulting codex, codex-reply, or codex-review MCP tools.
inbox-processing-example
EXAMPLE - Workflow for processing large Things3 inboxes using LLM-driven confidence matching and intelligent automation. This is a genericized example - create your own version in inbox-processing/ for personal use.
learning-discussion-designer
Design discussion prompts, Socratic questions, debate structures, and facilitation guides for meaningful learning conversations. Use for discussion-based learning. Activates on "discussion questions", "debate design", "Socratic method", or "forum prompts".
dramatic-2000ms-plus
Use when building extended animation sequences over 2000ms - cinematic intros, story sequences, premium experiences where animation IS the product