Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
research-cited-report
調査→論点整理→出典付きレポート化。ユーザーが「調べて」「比較して」「根拠/出典付きで」等を求めたら使う。
majiayu000/claude-skill-registry 163
-
Focus Techniques
Science-backed techniques for maintaining deep focus, managing distractions, and maximizing productive coding sessions
majiayu000/claude-skill-registry 163
-
document-runbook
Document CI/CD, deployment, and operational procedures. Use when creating runbooks, documenting deployment processes, or writing operational guides.
majiayu000/claude-skill-registry 163
-
position-sizing-action-space
7-action space with position sizing (25/50/75%) + small account simulation. Trigger when: (1) model needs sizing decisions, (2) training for <$25K accounts, (3) upgrading obs_dim 5600->5900.
majiayu000/claude-skill-registry 163
-
onboard-new-org
Complete organization onboarding wizard for LimaCharlie. Discovers local cloud CLIs (GCP, AWS, Azure, DigitalOcean), surveys cloud projects, identifies VMs for EDR installation and security-relevant log sources (IAM, audit logs, network logs). Guides EDR deployment via OS Config (GCP), SSM (AWS), VM Run Command (Azure). Creates cloud adapters for log ingestion. Confirms sensor connectivity and data flow. Use when setting up new tenants, connecting cloud infrastructure, deploying EDR fleet-wide, or onboarding hybrid environments.
majiayu000/claude-skill-registry 163
-
obsidian-recurring-expenses
Identifica y registra gastos recurrentes desde correos y adjuntos con validacion estricta y trazabilidad.
majiayu000/claude-skill-registry 163
-
staging-deployment-phase
Standard Operating Procedure for /ship-staging phase. Deploy feature to staging with auto-merge.
majiayu000/claude-skill-registry 163
-
model-pruning-helper
Model Pruning Helper - Auto-activating skill for ML Deployment.
Triggers on: model pruning helper, model pruning helper
Part of the ML Deployment skill category.
majiayu000/claude-skill-registry 163
-
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
majiayu000/claude-skill-registry 163
-
skill-aws-polly-tts-tool
AWS Polly TTS CLI for text-to-speech synthesis
majiayu000/claude-skill-registry 163
-
rls-policy-consolidator
Consolida múltiples políticas RLS permisivas redundantes en Supabase. Usa cuando hay varias policies del mismo rol/acción, warnings de múltiples permissive policies, o tarea 2.1 del PLAN_MEJORAS.md.
majiayu000/claude-skill-registry 163
-
link-deps
Discover and link related issues as dependencies. Searches for issues that should be connected and recommends dependency relationships to establish proper work order.
majiayu000/claude-skill-registry 163
-
container-deployment
Manage containerization and deployment automation using Docker, Kubernetes, and cloud platforms. Use when working with Docker images, container registries, orchestration, deployment pipelines, infrastructure as code, or environment management. Handles container builds, registry publishing, and deployment strategies.
majiayu000/claude-skill-registry 163
-
venn-diagram-generator
This skill generates interactive Venn diagram visualizations using the venn.js JavaScript library. Use this skill when users request creating Venn diagrams, set visualizations, overlap diagrams, or comparison charts for educational textbooks. The skill creates complete MicroSim packages with standalone HTML files featuring colorful circles, clear labels, and interactive tooltips, saved to /docs/sims/ following the MicroSim pattern.
majiayu000/claude-skill-registry 163
-
deployment-workflows
CI/CD pipelines, zero-downtime deployments, infrastructure as code, and production deployment strategies
majiayu000/claude-skill-registry 163
-
openshift-expert
OpenShift platform and Kubernetes expert with deep knowledge of cluster architecture, operators, networking, storage, troubleshooting, and CI/CD pipelines. Use for analyzing test failures, debugging cluster issues, understanding operator behavior, investigating build problems, or any OpenShift/Kubernetes-related questions.
majiayu000/claude-skill-registry 163
-
constraints-scheduling
Provides systematic approaches for solving multi-person scheduling problems with complex constraints. This skill should be used when finding meeting times, scheduling events, or solving optimization problems involving multiple calendars, availability windows, time-based constraints, preferences, and buffer requirements.
majiayu000/claude-skill-registry 163
-
managing-network-policies
Execute use when managing Kubernetes network policies and firewall rules. Trigger with phrases like "create network policy", "configure firewall rules", "restrict pod communication", or "setup ingress/egress rules". Generates Kubernetes NetworkPolicy manifests following least privilege and zero-trust principles.
majiayu000/claude-skill-registry 163
-
deploying-postgres-k8s
Deploys PostgreSQL on Kubernetes using the CloudNativePG operator with automated failover.
Use when setting up PostgreSQL for production workloads, high availability, or local K8s development.
Covers operator installation, cluster creation, connection secrets, and backup configuration.
NOT when using managed Postgres (Neon, RDS, Cloud SQL) or simple Docker containers.
majiayu000/claude-skill-registry 163
-
mcp-fortress
Scan MCP servers for security vulnerabilities, prompt injection attacks, and tool poisoning. Use this when the user wants to check if an MCP server is safe, analyze security risks, detect malicious tools, or verify MCP package integrity before installation.
majiayu000/claude-skill-registry 163
-
Save Thread
Save complete conversation as checkpoint. Only when user explicitly requests ("save session", "checkpoint this"). Use nmem t save to automatically import Claude Code sessions.
majiayu000/claude-skill-registry 163
-
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
majiayu000/claude-skill-registry 163
-
using-cloud-cli
Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.
majiayu000/claude-skill-registry 163
-
infra-previewer
Preview infrastructure changes - run Terraform plan to show what resources will be created, modified, or
destroyed. Generate human-readable plan summaries showing resource changes before deployment.
majiayu000/claude-skill-registry 163