Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
foundational-principles
基础原则 - AI 助手的核心思维原则和指令框架概述。包含系统思维、辩证思维、创新思维和批判思维四大核心原则。
majiayu000/claude-skill-registry 163
-
treasury-administrator
Constitutional Treasury Administrator for UBOS Republic.
Manages all financial operations, grant applications, revenue
optimization, and marketing strategy. Operates under Trinity
Lock governance with Hydraulic Governor safeguards. Handles
REAL money only: actual bank accounts, crypto wallets, DeFi
positions, and EU grant wire transfers.
majiayu000/claude-skill-registry 163
-
consider
Selects and applies mental models for structured problem analysis. Triggers when user asks "why", "what if", "how should we", needs systematic problem-solving, or mentions analyzing a situation. MUST BE USED when comparing options, making decisions, or evaluating trade-offs.
majiayu000/claude-skill-registry 163
-
ops-devops-platform
Production-grade DevOps patterns with Kubernetes 1.34+, Terraform 1.9+, Docker 27+, ArgoCD/FluxCD GitOps, SRE, eBPF-based observability, AI-driven monitoring, CI/CD security, and cloud-native operations (AWS, GCP, Azure, Kafka).
majiayu000/claude-skill-registry 163
-
expo-router
Patterns for Expo Router including Stack configuration, native tabs, and file-based routing best practices. Apply when working with navigation, routing, or screen configuration.
majiayu000/claude-skill-registry 163
-
startupO-lite
RAG-first ORCHESTRATOR startup. Minimal context (~500 tokens), queries RAG on-demand. Token-efficient alternative to startupO.
majiayu000/claude-skill-registry 163
-
ci-cd-pipeline
Set up and maintain continuous integration and continuous deployment pipelines with GitHub Actions, GitLab CI, Jenkins, or similar tools to automate testing, building, and deployment. Use when configuring automated builds, setting up test automation, implementing deployment automation, creating release workflows, managing environment deployments, configuring build caching, implementing blue-green deployments, setting up rollback strategies, or automating the entire software delivery pipeline.
majiayu000/claude-skill-registry 163
-
straight-ahead-pose-mastery
Use when planning animation workflows, deciding between spontaneous vs controlled approaches, or balancing creative freedom with structural precision.
majiayu000/claude-skill-registry 163
-
kubernetes-debugger
Kubernetes debugging and troubleshooting best practices using MCP kubernetes tools.
Use when: (1) Pods are failing, pending, or in CrashLoopBackOff/ImagePullBackOff states,
(2) Services are unreachable or DNS resolution fails, (3) Deployments aren't rolling out,
(4) Nodes are unhealthy or unschedulable, (5) Resource issues (OOM, CPU throttling),
(6) Any "why isn't my Kubernetes workload working?" questions.
Provides systematic debugging workflows using kubectl_get, kubectl_describe, kubectl_logs,
exec_in_pod, and other MCP kubernetes tools.
majiayu000/claude-skill-registry 163
-
agent-kubernetes-specialist
Expert Kubernetes specialist mastering container orchestration, cluster management, and cloud-native architectures. Specializes in production-grade deployments, security hardening, and performance optimization with focus on scalability and reliability.
majiayu000/claude-skill-registry 163
-
optimization-load-balancer
Dynamic task distribution, work-stealing algorithms, queue management, and adaptive load balancing. Use for optimizing task execution across agents, preventing overload, and maximizing throughput.
majiayu000/claude-skill-registry 163
-
managing-prompts
Creates, analyzes, updates, and optimizes prompts using Claude 4.5 best practices, guardrails, context management, and prompt engineering patterns. Use when user asks how to write effective prompts, explaining prompt engineering techniques, understanding Claude 4.5 best practices, describing prompt patterns and structures, creating new prompts, evaluating existing prompts for improvements, determining if current logic should be extracted to prompts, identifying outdated prompt techniques, optimizing context usage, implementing guardrails, or when user mentions "prompt engineering", "hallucinations", "context optimization", "prompt caching", "chain-of-thought", or asks if logic should become a prompt.
majiayu000/claude-skill-registry 163
-
Railway CLI Management
Deploy, manage services, view logs, and configure Railway infrastructure. Use when deploying to Railway, managing environment variables, viewing deployment logs, scaling services, or managing volumes.
majiayu000/claude-skill-registry 163
-
ansible-playbook
Write and review Ansible playbooks following best practices. Use when the user says "write ansible", "ansible playbook", "review playbook", "automate with ansible", or asks to configure servers with Ansible.
majiayu000/claude-skill-registry 163
-
configuring-github-actions
Use when setting up GitHub Actions CI/CD for pull request checks - provides workflow templates for Python, JavaScript, and polyglot projects that run quality gates on every PR
majiayu000/claude-skill-registry 163
-
agent-dx-cli
This skill provides patterns for designing command-line tools that agents can use effectively. Use when designing new CLIs, reviewing existing CLIs for agent compatibility, or adding agent-friendly features. Covers minimal ceremony, JSON output, context injection, batch operations, and error handling.
majiayu000/claude-skill-registry 163
-
cloud-cost-management
Optimize and manage cloud costs across AWS, Azure, and GCP using reserved instances, spot pricing, and cost monitoring tools.
majiayu000/claude-skill-registry 163
-
reviewing-type-safety
最大の型カバレッジのためのTypeScript型安全パターンとベストプラクティス。 トリガー: 型安全, type safety, any, unknown, 型推論, 型ガード, type guard, discriminated union, 判別可能なUnion, strictNullChecks, 型定義, 型カバレッジ, TypeScript, 暗黙のany, implicit any, 型アサーション, type assertion.
majiayu000/claude-skill-registry 163
-
serverless-recommender
Intelligent serverless platform recommendation expert. Detects project context (pet-project, startup, enterprise), analyzes workload suitability, ranks platforms (AWS Lambda, Azure Functions, GCP Cloud Functions, Firebase, Supabase), and provides comprehensive recommendations with cost estimates. Activates for serverless recommendations, platform selection, AWS vs Azure vs GCP, Firebase vs Supabase, serverless architecture, should I use serverless, which serverless platform, serverless cost, serverless free tier, Lambda vs Functions, cloud functions comparison.
majiayu000/claude-skill-registry 163
-
validator-expert
Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices. Generates weighted scores (0-100%) with actionable recommendations. Use when asked to "validate deploymen... Trigger with phrases like 'validate', 'check', or 'verify'.
majiayu000/claude-skill-registry 163
-
context-engineering
majiayu000/claude-skill-registry 163
-
therapy-content-generator
Generate YMYL-compliant therapy page content with E-E-A-T signals, schema markup, and Ontario-specific elements. Creates 2000+ word pages following pillar/cluster architecture. Includes author byline (Jesse Cynamon, RP CRPO
majiayu000/claude-skill-registry 163
-
detecting-performance-regressions
Automatically detect performance regressions in CI/CD pipelines by comparing metrics against baselines. Use when validating builds or analyzing performance trends. Trigger with phrases like "detect performance regression", "compare performance metrics", or "analyze performance degradation".
majiayu000/claude-skill-registry 163
-
gcp-project-auditor
Expert in auditing GCP projects for security, compliance, and best practices. **Use this skill when the user asks to audit a GCP project, review GCP project security, scan GCP resources, or check GCP project compliance.** Scans resources, IAM policies, service accounts, and detects excessive permissions in production environments.
majiayu000/claude-skill-registry 163