Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
check-cluster-health
Checks comprehensive health check for a Kubernetes Cluster.
majiayu000/claude-skill-registry 163
-
clean-architecture
Apply Clean Architecture layering and dependency rules (Domain, Application, Infrastructure, Presentation layers). Use when structuring applications or ensuring dependencies point inward.
majiayu000/claude-skill-registry 163
-
wcdb
Use when working with wcdb
majiayu000/claude-skill-registry 163
-
correcting-mistakes
Self-corrects skill and command instructions after resolving errors. Use when Claude errors during skill/command execution and finds a solution, or when user indicates a mistake was made. Finds the relevant instruction file and applies succinct fixes.
majiayu000/claude-skill-registry 163
-
agentdb-vector-search-optimization
Skill guidance for agentdb vector search optimization.
majiayu000/claude-skill-registry 163
-
critical-peer
Professional skepticism with pattern enforcement. Verify before agreeing, challenge violations, propose instead of asking. Concise output, research before asking, answer questions literally.
majiayu000/claude-skill-registry 163
-
deep-reading-analyst
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materials, (4) create study notes or learning summaries, (5) compare multiple sources, (6) transform knowledge into practical applications, or (7) apply specific thinking frameworks. Triggered by phrases like 'analyze this article,' 'help me understand,' 'deep dive into,' 'extract insights from,' 'use [framework name],' or when users provide URLs/long-form content for analysis.
majiayu000/claude-skill-registry 163
-
ancient-greek
Master Ancient Greek philosophical methods, vocabulary, and debates. Use for: Socratic method, Platonic dialogues, Aristotelian analysis, Stoic ethics, Epicurean philosophy, pre-Socratic thought. Triggers: 'Socrates', 'Plato', 'Aristotle', 'Stoic', 'Epicurean', 'eudaimonia', 'virtue ethics', 'elenchus', 'four causes', 'Forms', 'nous', 'logos', 'phronesis', 'ataraxia', 'apatheia', 'dialectic', 'maieutic', 'pre-Socratic', 'Heraclitus', 'Parmenides', 'the Good', 'unmoved mover'.
majiayu000/claude-skill-registry 163
-
global-installer
Install global dependencies to the system. These are typically installing using `brew`
majiayu000/claude-skill-registry 163
-
harness-cd
Harness NextGen CD for continuous deployment including pipeline YAML structure, deployment strategies (rolling, blue-green, canary), GitOps workflows, approval gates, triggers, environments, services, manifests, Kubernetes deployments, Terraform integration, and secrets management. Activate for Harness pipeline creation, deployment automation, and GitOps configuration.
majiayu000/claude-skill-registry 163
-
agent-machine-learning-engineer
Expert ML engineer specializing in production model deployment, serving infrastructure, and scalable ML systems. Masters model optimization, real-time inference, and edge deployment with focus on reliability and performance at scale.
majiayu000/claude-skill-registry 163
-
agent-search-specialist
Expert search specialist mastering advanced information retrieval, query optimization, and knowledge discovery. Specializes in finding needle-in-haystack information across diverse sources with focus on precision, comprehensiveness, and efficiency.
majiayu000/claude-skill-registry 163
-
performance-budget-enforcer
Monitors Lighthouse scores and JavaScript bundle sizes across deployments with automated alerts when performance thresholds are exceeded. This skill should be used when setting up performance monitoring, enforcing bundle size limits, tracking Lighthouse metrics, or adding performance regression detection. Use for performance budgets, bundle size, Lighthouse CI, performance monitoring, regression detection, or web vitals tracking.
majiayu000/claude-skill-registry 163
-
agent-performance-monitor
Expert performance monitor specializing in system-wide metrics collection, analysis, and optimization. Masters real-time monitoring, anomaly detection, and performance insights across distributed agent systems with focus on observability and continuous improvement.
majiayu000/claude-skill-registry 163
-
aws-sdk-java-v2-s3
Amazon S3 patterns and examples using AWS SDK for Java 2.x. Use when working with S3 buckets, uploading/downloading objects, multipart uploads, presigned URLs, S3 Transfer Manager, object operations, or S3-specific configurations.
majiayu000/claude-skill-registry 163
-
fiduciary-duty-negligence
Clerk for Crown fiduciary breaches, fund mismanagement, conflicts of interest, and failure to protect reserve lands; use for Fiduciary_Duty_Negligence queue.
majiayu000/claude-skill-registry 163
-
devcontainer-workflow
DevContainer configuration for consistent development environments with Docker, multi-stage builds, non-root users, environment management, Docker-in-Docker support, and Python with uv. Activate when working with .devcontainer/, devcontainer.json, Dockerfile, or container-based development workflows.
majiayu000/claude-skill-registry 163
-
docker-and-kubernetes-pro
Container orchestration expert for Docker, Kubernetes, and cloud-native deployments
majiayu000/claude-skill-registry 163
-
k8s-troubleshoot
Debug Kubernetes pods, services, and cluster issues. Use when the user says "pod not starting", "CrashLoopBackOff", "service not reachable", "kubectl debug", "pod stuck pending", or asks about Kubernetes problems.
majiayu000/claude-skill-registry 163
-
validation-report-generator
Generate structured 8-section validation reports with verdict (GOOD/BAD/NEEDS MAJOR WORK), strengths, critical flaws, blindspots, and concrete path forward. Use after strategic-cto-mentor has completed validation analysis and needs to produce final deliverable.
majiayu000/claude-skill-registry 163
-
executive-briefs
Use to craft concise revenue updates for executives and boards.
majiayu000/claude-skill-registry 163
-
Swift Optionals Patterns
Use when swift's optional handling patterns including optional binding, chaining, nil coalescing, and modern approaches to safely working with optional values while avoiding common pitfalls and force unwrapping.
majiayu000/claude-skill-registry 163
-
packaging-framework
Use to structure pricing/packaging proposals with clear fences and value pillars.
majiayu000/claude-skill-registry 163
-
using-cipherpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
majiayu000/claude-skill-registry 163