Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
negotiation-expert-infrastructure
Property owner negotiations for acquisitions (specialized from negotiation-expert). Calculates BATNA, ZOPA, optimal settlement range, assesses holdout risk (0-30 scale), generates concession strategies. Use for utility easements, transit corridors, land assembly, expropriation settlements. Key terms include BATNA, ZOPA, holdout risk, settlement range, owner psychology
majiayu000/claude-skill-registry 163
-
git-conventional-commits
Apply when writing commit messages to maintain consistent, readable git history that enables automated changelog generation.
majiayu000/claude-skill-registry 163
-
page-and-route
Helps create and configure pages and routes in the OneKey app-monorepo. Use when creating new pages, configuring routes, setting up deep links, handling QR codes, or understanding navigation patterns. Page, route, navigation, deep link, universal link, QR code, modal, tab, onboarding.
majiayu000/claude-skill-registry 163
-
Packages Devtools
Your approach to handling packages devtools. Use this skill when working on files where packages devtools comes into play.
majiayu000/claude-skill-registry 163
-
help-skill
majiayu000/claude-skill-registry 163
-
pr-prep-athola-claude-night-market
majiayu000/claude-skill-registry 163
-
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
majiayu000/claude-skill-registry 163
-
define-opportunity-tree
majiayu000/claude-skill-registry 163
-
DB Migration Generator
Generator สำหรับสร้าง database migration files พร้อม up/down scripts, validation และ rollback safety
majiayu000/claude-skill-registry 163
-
creating-claude-rules
Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like alwaysApply
majiayu000/claude-skill-registry 163
-
ai-sdk-best-practices
Production best practices for building AI agents with Vercel AI SDK v5. Covers security, performance, error handling, testing, deployment patterns, and real-world implementation guidelines.
majiayu000/claude-skill-registry 163
-
commit-prepare
Prepare git commit messages following conventional commits. Activates on: commit, prepare commit, commit this, commit message, ready to commit, stage and commit
majiayu000/claude-skill-registry 163
-
configuring-nginx
Configure nginx for static sites, reverse proxying, load balancing, SSL/TLS termination, caching, and performance tuning. When setting up web servers, application proxies, or load balancers, this skill provides production-ready patterns with modern security best practices for TLS 1.3, rate limiting, and security headers.
majiayu000/claude-skill-registry 163
-
api-design
majiayu000/claude-skill-registry 163
-
implementing-gitops
Implement GitOps continuous delivery for Kubernetes using ArgoCD or Flux. Use for automated deployments with Git as single source of truth, pull-based delivery, drift detection, multi-cluster management, and progressive rollouts.
majiayu000/claude-skill-registry 163
-
unsloth-core
majiayu000/claude-skill-registry 163
-
methylation-variability-analysis
This skill provides a complete and streamlined workflow for performing methylation variability and epigenetic heterogeneity analysis from whole-genome bisulfite sequencing (WGBS) data. It is designed for researchers who want to quantify CpG-level variability across biological samples or conditions, identify highly variable CpGs (HVCs), and explore epigenetic heterogeneity.
majiayu000/claude-skill-registry 163
-
cicd-expert
Expert-level CI/CD with GitHub Actions, Jenkins, deployment pipelines, and automation
majiayu000/claude-skill-registry 163
-
deploying-machine-learning-models
This skill enables Claude to deploy machine learning models to production environments. It automates the deployment workflow, implements best practices for serving models, optimizes performance, and handles potential errors. Use this skill when the user requests to deploy a model, serve a model via an API, or put a trained model into a production environment. The skill is triggered by requests containing terms like "deploy model," "productionize model," "serve model," or "model deployment."
majiayu000/claude-skill-registry 163
-
Retrieval Playbook for AI
กลยุทธ์การ retrieve context ให้ AI อย่างมีประสิทธิภาพ - เลือกอะไร ไม่เลือกอะไร และจัดลำดับอย่างไร
majiayu000/claude-skill-registry 163
-
bedrock
AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.
majiayu000/claude-skill-registry 163
-
web-frameworks
Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.
majiayu000/claude-skill-registry 163
-
validate-skill
Validate skill directories against AgentSkills spec
majiayu000/claude-skill-registry 163
-
linear-webhooks-events
Configure and handle Linear webhooks for real-time event processing.
Use when setting up webhooks, handling Linear events,
or building real-time integrations.
Trigger with phrases like "linear webhooks", "linear events",
"linear real-time", "handle linear webhook", "linear webhook setup".
majiayu000/claude-skill-registry 163