Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
backend-development
Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
majiayu000/claude-skill-registry 163
-
create-github-pull-request-from-specification
Create GitHub Pull Request for feature request from specification file using pull_request_template.md template.
majiayu000/claude-skill-registry 163
-
review
Cross-cutting artifact review using a two-file filesystem protocol. Works across windows without copy-paste.
majiayu000/claude-skill-registry 163
-
1k-architecture
OneKey monorepo architecture, project structure, package relationships, and import hierarchy rules.
majiayu000/claude-skill-registry 163
-
agentic-systems-design
Use when designing tool-use agents, multi-step reasoning systems, planning loops, multi-agent architectures, or agent evaluation frameworks.
majiayu000/claude-skill-registry 163
-
azure-health-data-services
Expert knowledge for Azure Health Data Services development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using FHIR, DICOM, MedTech, de-identification APIs, bulk data flows, or Synapse/ADF/Logic Apps integrations, and other Azure Health Data Services related development tasks. Not for Azure Health Bot (use azure-health-bot), Azure Data Factory (use azure-data-factory), Azure Synapse Analytics (use azure-synapse-analytics), Azure Machine Learning (use azure-machine-learning).
majiayu000/claude-skill-registry 163
-
planning-design
Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.
majiayu000/claude-skill-registry 163
-
ck:preview
View files/directories OR generate visual explanations, slides, diagrams.
majiayu000/claude-skill-registry 163
-
azure-keyvault-secrets-ts
Manage secrets using Azure Key Vault Secrets SDK for JavaScript (@azure/keyvault-secrets). Use when storing and retrieving application secrets or configuration values.
majiayu000/claude-skill-registry 163
-
deel-automation
Automate Deel tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
V3 MCP Optimization
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.
majiayu000/claude-skill-registry 163
-
claude-routing
Skills for the Claude Code model routing system — managing persistent subagents (haiku/sonnet/opus).
majiayu000/claude-skill-registry 163
-
biogeochemical-cycles
Carbon, nitrogen, phosphorus, sulfur, and water cycles — pools, fluxes, residence times, and anthropogenic perturbations. Covers the fast and slow carbon cycles, the Haber-Bosch disruption of the nitrogen cycle, the phosphorus bottleneck, the hydrological cycle, ocean acidification, and the planetary boundaries framework. Use when tracking chemical elements through atmosphere, hydrosphere, biosphere, and lithosphere; computing pool sizes and fluxes; or evaluating anthropogenic perturbations to global cycles.
majiayu000/claude-skill-registry 163
-
accessibility-patterns
Accessibility patterns including WCAG 2.2 compliance, ARIA correctness, keyboard navigation, and screen reader compatibility. Use when writing or reviewing UI code with interactive elements, forms, or dynamic content.
majiayu000/claude-skill-registry 163
-
typescript-pro
Use when building TypeScript applications requiring advanced type systems, generics, or full-stack type safety. Invoke for type guards, utility types, tRPC integration, monorepo setup.
majiayu000/claude-skill-registry 163
-
sequential-thinking
Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.
majiayu000/claude-skill-registry 163
-
create-issues
Convert an implementation plan into tracked issues with proper dependencies. Generates commands for issue trackers like Beads or GitHub Issues.
majiayu000/claude-skill-registry 163
-
e2e-webapp-testing
Create resilient E2E tests using Playwright/Cypress
majiayu000/claude-skill-registry 163
-
deep-analysis
Deep exploration and synthesis workflow using dynamic planning and hub-and-spoke coordination. Use when asked for "deep analysis", "deep understanding", "analyze codebase", "explore and analyze", or "investigate codebase".
majiayu000/claude-skill-registry 163
-
bash-script-generator
Generates production-ready bash 5.2+/5.3 scripts with strict mode, immutable locals, dispatch tables, and functional patterns. Use when creating new .sh scripts, CLI tools, cron jobs, deployment automation, text processing workflows, or log analyzers.
majiayu000/claude-skill-registry 163
-
worktree-clean
Use when removing a git worktree and cleaning up its associated local branch from the main repository.
majiayu000/claude-skill-registry 163
-
knowledge-base
Shared foundation for Oracle & Corrector agents. Establishes the source hierarchy for resolving conflicts between documentation, code, and specs. Load this skill first when investigating how the system works.
majiayu000/claude-skill-registry 163
-
ml-pipeline
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for training orchestration, builds feature store schemas with Feast, deploys model registries, and automates retraining and validation workflows. Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, managing experiment tracking systems, setting up DVC for data versioning, tuning hyperparameters, or configuring MLOps tooling like Kubeflow, Airflow, MLflow, or Prefect.
majiayu000/claude-skill-registry 163
-
jira-automation
Automate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for current schemas.
majiayu000/claude-skill-registry 163