Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
xml-context-engineering
Structure LLM context using XML tags for maximum attention efficiency. Use when writing system prompts, organizing complex instructions, or engineering context for Claude agents. Produces semantically meaningful XML that creates clear attention anchors.
majiayu000/claude-skill-registry 163
-
wgpu-shader-specialist
Expert on wgpu GPU rendering, WGSL shaders, and GPU pipeline configuration. Use when discussing rendering, shaders, GPU, textures, or graphics pipeline.
majiayu000/claude-skill-registry 163
-
wolf-verification
Three-layer verification architecture (CoVe, HSP, RAG) for self-verification, fact-checking, and hallucination prevention
majiayu000/claude-skill-registry 163
-
file-type-defaults
Set default applications for file types on macOS using utiluti. Use when setting file type associations, changing default apps for extensions, or managing macOS file handlers.
majiayu000/claude-skill-registry 163
-
query-victorialogs
Query and analyze logs from VictoriaLogs using LogsQL via HTTP API. Use when the user asks to "query logs", "search logs", "check VictoriaLogs", "find errors in logs", "tail logs", "get log stats", "search VictoriaLogs", "check dev/prod logs", or any log investigation task involving VictoriaLogs. Also triggers on mentions of LogsQL, VictoriaLogs, or log troubleshooting.
majiayu000/claude-skill-registry 163
-
cross-disciplinary-ideation
Field connection mapping and systematic ideation for method transfer
majiayu000/claude-skill-registry 163
-
linear-issue-handler
Comprehensive workflow for managing Linear issues using the linearis CLI tool. Handles issue creation, status tracking, commenting, and file downloads with clear decision trees for when to ask for approval vs. acting autonomously.
majiayu000/claude-skill-registry 163
-
admin-infra-digitalocean
Deploys infrastructure on DigitalOcean with Droplets (VMs), Firewalls, and VPCs.
Includes Kasm Workspaces auto-scaling integration for dynamic agent provisioning.
Use when: setting up DigitalOcean infrastructure, deploying Droplets, configuring firewalls, integrating with Kasm auto-scaling, looking for US/global cloud with good API.
Keywords: digitalocean, doctl, droplet, VPS, firewall, VPC, kasm autoscale, cloud infrastructure
majiayu000/claude-skill-registry 163
-
pyroscope
Guide for Grafana Pyroscope continuous profiling. Use for Kubernetes Helm deployment, Go/Java/Python/.NET/Ruby/Node.js profiling, storage backends, trace-to-profile linking, and troubleshooting.
majiayu000/claude-skill-registry 163
-
foreclosure-analysis
Expert skill for analyzing Florida foreclosure auction properties using The Everest Ascent™ 12-stage methodology. Use when analyzing properties, calculating max bids, researching liens, or making bid/skip decisions for Brevard County foreclosure auctions.
majiayu000/claude-skill-registry 163
-
Cabinet Meeting
Conduct a Cabinet meeting when User asks for "Cabinet meeting", "convene the Cabinet", "get perspectives from [agents]", or needs multi-agent consultation on complex decisions. Can be ad-hoc for specific decisions or weekly review format.
majiayu000/claude-skill-registry 163
-
docusaurus-setup
This skill use to deploy the Docusaurus site on github pages, deploy site to GitHub Pages using a CI/CD pipeline with the GitHub CLI.
majiayu000/claude-skill-registry 163
-
docs
majiayu000/claude-skill-registry 163
-
analyzing-dependencies
Analyze dependencies for known security vulnerabilities and outdated versions. Use when auditing third-party libraries. Trigger with 'check dependencies', 'scan for vulnerabilities', or 'audit packages'.
majiayu000/claude-skill-registry 163
-
draft-section
Incremental content drafting skill that writes specific sections within existing scaffolds. Supports drafting 1 section at a time or batch-drafting multiple sections with user control. Each operation stays under 10k tokens to avoid context compacting.
majiayu000/claude-skill-registry 163
-
pm2-ecosystem-config
PM2エコシステム設定の専門スキル。
Node.jsプロセス管理のためのecosystem.config.js設計、実行モード選択、環境変数管理、パフォーマンス最適化を提供します。
Anchors:
• PM2 Documentation (Keymetrics) / 適用: プロセス管理設定 / 目的: 運用自動化
• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: DRY原則・保守性 / 目的: 品質向上
• Node.js Design Patterns (Mario Casciaro, Luciano Mammino) / 適用: スケーリング戦略 / 目的: パフォーマンス最適化
Trigger:
Use when configuring PM2 ecosystem.config.js, deploying Node.js applications with PM2, optimizing PM2 cluster mode, managing PM2 environment variables, or troubleshooting PM2 process issues
majiayu000/claude-skill-registry 163
-
cloudflare-dns
Comprehensive guide for managing Cloudflare DNS with Azure integration. Use when configuring Cloudflare as authoritative DNS provider for Azure-hosted applications, managing DNS records via API, setting up API tokens, configuring proxy settings, troubleshooting DNS issues, implementing DNS security best practices, or integrating External-DNS with Cloudflare for Kubernetes workloads.
majiayu000/claude-skill-registry 163
-
cloudinary-cdn
Video CDN yonetimi. Use when uploading videos for Instagram Reels.
majiayu000/claude-skill-registry 163
-
k8s-manifests
Create, validate, and manage Kubernetes and OpenShift YAML manifests. Use this skill when:
(1) Creating any K8s/OCP resources: Deployments, StatefulSets, DaemonSets, Jobs, CronJobs, Pods
(2) Creating networking resources: Services, Ingress, NetworkPolicies, OCP Routes
(3) Creating config/storage: ConfigMaps, Secrets, PVCs, PVs, StorageClasses
(4) Creating RBAC: ServiceAccounts, Roles, RoleBindings, ClusterRoles, ClusterRoleBindings
(5) Creating OCP-specific: DeploymentConfigs, BuildConfigs, ImageStreams, SCCs, Templates
(6) Validating or reviewing existing manifests for best practices
(7) Converting between K8s and OCP resource types
(8) Generating Helm charts or Kustomize overlays
majiayu000/claude-skill-registry 163
-
AILANG Release Manager
Create new AILANG releases with version bumps, changelog updates, git tags, and CI/CD verification. Use when user says "ready to release", "create release", mentions version numbers, or wants to publish a new version.
majiayu000/claude-skill-registry 163
-
ai-llm-engineering
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
majiayu000/claude-skill-registry 163
-
production-deploy
Production deployment checklist and procedures for Medellin Spark. Use when deploying to production, performing releases, or setting up production infrastructure.
majiayu000/claude-skill-registry 163
-
dependency-graph-generator
生成GOAL/SubPlan依赖DAG和关键路径分析，并执行SubPlan划分。当需要分析技术依赖、业务依赖、识别关键路径、发现并行执行机会、执行SubPlan分配时使用。基于GOAL的dependencies字段和业务逻辑分析生成Mermaid依赖图和SubPlan划分方案。
majiayu000/claude-skill-registry 163
-
Predictive Skill Loading
Anticipates and pre-loads optimal skills before task execution based on pattern matching and historical success rates
majiayu000/claude-skill-registry 163