Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
slo-sli-error-budget
Use when defining SLOs, selecting SLIs, or implementing error budget policies. Covers reliability targets, SLI selection, and error budget management.
majiayu000/claude-skill-registry 163
-
production-deployment-phase
Standard Operating Procedure for /ship-prod phase. Automated staging→production promotion.
majiayu000/claude-skill-registry 163
-
confighub-usage-guide
A comprehensive guide for using ConfigHub to manage Kubernetes configuration across multiple environments using Configuration as Data principles. This rulebook covers installation, configuration management, variant handling, and operational workflows.
majiayu000/claude-skill-registry 163
-
nda-review
Reviews incoming one-way (unilateral) commercial NDAs in a jurisdiction-agnostic way, from either a Recipient or Discloser perspective (user-selected), producing a clause-by-clause issue log with preferred redlines, fallbacks, rationales, owners, and deadlines.
majiayu000/claude-skill-registry 163
-
docker-expert
Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges.
majiayu000/claude-skill-registry 163
-
choosing-pattern
Use when deciding which pgdbm pattern to use (standalone, dual-mode library, or shared pool) - provides decision tree based on deployment context without requiring doc exploration
majiayu000/claude-skill-registry 163
-
universal-practitioner
Use when applying animation principles in any context, for any role, or when a general understanding of Disney's 12 principles is needed.
majiayu000/claude-skill-registry 163
-
deploy
Execute the complete TestFlight deployment workflow for this Flutter iOS app. Use when the user asks to deploy, release, publish, or upload the app to TestFlight, or says things like "deploy to testflight", "release a new build", "push to beta testers", or "upload to app store connect".
majiayu000/claude-skill-registry 163
-
ci
Diagnoses and fixes CI/CD pipeline failures. Use when user mentions 'CI', 'GitHub Actions', 'GitLab CI', 'ビルドエラー', 'テスト失敗', 'パイプライン', 'CIが落ちた', or asks to analyze build/test failures. Do NOT load for: ローカルビルド, 通常の実装作業, レビュー, セットアップ.
majiayu000/claude-skill-registry 163
-
figma-prototyping
Use when implementing Disney's 12 animation principles in Figma prototypes and Smart Animate
majiayu000/claude-skill-registry 163
-
training-archive-gating
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.
majiayu000/claude-skill-registry 163
-
hetzner-provisioner
Provisions infrastructure on Hetzner Cloud with Terraform/Pulumi. Generates IaC code for CX11/CX21/CX31 instances, managed Postgres, SSL configuration, Docker deployment. Activates for deploy on Hetzner, Hetzner Cloud, budget deployment, cheap hosting, $10/month hosting.
majiayu000/claude-skill-registry 163
-
actions-cicd-practices
GitHub Actions and CI/CD best practices for automated testing, building, and deployment.
majiayu000/claude-skill-registry 163
-
cloud-tasks-queue-setup
Cloud Tasks Queue Setup - Auto-activating skill for GCP Skills.
Triggers on: cloud tasks queue setup, cloud tasks queue setup
Part of the GCP Skills skill category.
majiayu000/claude-skill-registry 163
-
rancher-troubleshooter
Diagnose and troubleshoot Rancher Desktop on WSL2, focusing on Kubernetes/K3s issues including slow API operations, etcd health problems, cluster component failures, and pod networking issues. Use when encountering Rancher Desktop errors, timeouts, or performance degradation.
majiayu000/claude-skill-registry 163
-
contextual-chunking
Contextual Retrieval implementation for RAG - chunks clinical notes with LLM-generated context prepended to each chunk before embedding. Improves citation accuracy by 49% per Anthropic research.
majiayu000/claude-skill-registry 163
-
feature-specification
Guide iterative specification and CDC (Cahier Des Charges) creation through deep questioning, context analysis, and proactive proposals. Use this skill BEFORE feature-research to clarify requirements, identify prerequisites, define scope, and document complete specifications. Triggers when starting a new feature, task, bug fix, or refactoring and requirements need clarification.
majiayu000/claude-skill-registry 163
-
fly
Deploy and manage the photography portfolio backend on fly.io. Use when deploying the app, checking logs, checking status, scaling machines, or managing the fly.io deployment.
majiayu000/claude-skill-registry 163
-
vulnerability-scanner
Comprehensive guide for automated vulnerability scanning tools and techniques. Covers DAST, SAST, SCA, network scanning, and CI/CD integration.
majiayu000/claude-skill-registry 163
-
storage-networking
Master Kubernetes storage management and networking architecture. Learn persistent storage, network policies, service discovery, and ingress routing.
majiayu000/claude-skill-registry 163
-
constitution-reader
Read and summarize constitution principles for the AI-Native Robotics Textbook project. Use when checking project rules, validating compliance, or understanding constraints.
majiayu000/claude-skill-registry 163
-
backup-etcd
Create and manage etcd backups for OpenShift control plane disaster recovery, including automated backup procedures and verification.
majiayu000/claude-skill-registry 163
-
ln-115-devops-docs-creator
Creates runbook.md for DevOps setup. L3 Worker invoked CONDITIONALLY when hasDocker detected.
majiayu000/claude-skill-registry 163
-
direct-spend-visualizer
Visualize FeedMob direct spend data as ASCII line charts. Use this skill when users request to view, display, chart, or visualize direct spend metrics for one or more click URL IDs. Trigger when users ask to "show direct spend," "visualize spend data," "chart the spending," or similar requests involving FeedMob direct spend visualization.
majiayu000/claude-skill-registry 163