Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
review-severity-format
Shared severity levels, issue ID format, and verdict criteria for all code reviewers. Use when performing code reviews or generating review reports. Do NOT use when writing or modifying code -- this is for review output formatting only.
majiayu000/claude-skill-registry 163
-
design-system-patterns
Use when building component libraries, choosing headless UI primitives, designing component APIs, or implementing theming and design tokens.
majiayu000/claude-skill-registry 163
-
zenn-context-driven-writing
Use when preparing context and drafts for experience-based Zenn articles. Parallel research + context file pattern.
majiayu000/claude-skill-registry 163
-
text-content
Create high-performing text posts for social media using framework fitting method. 360+ proven templates across LinkedIn, X, Facebook, and Instagram. Progressive disclosure loads only relevant templates based on platform and content type.
majiayu000/claude-skill-registry 163
-
cloudflare-r2
Cloudflare R2 object storage with S3-compatible API and zero egress fees
majiayu000/claude-skill-registry 163
-
agent-identity
Register and manage on-chain AI agent identity via ERC-8004.
majiayu000/claude-skill-registry 163
-
springboot-tdd
Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.
majiayu000/claude-skill-registry 163
-
tiktok-video-scripts
Write TikTok affiliate video scripts using HOOK→PROBLEM→SOLUTION→DEMO→CTA formula. 5 formats (Unboxing, Review, Before/After, Tutorial, Storyline) with production notes, text overlays, hashtags, trending sounds. Vietnamese market focus. Use when creating scripts, improving hooks, choosing hashtags, or planning video content for TikTok Shop products.
majiayu000/claude-skill-registry 163
-
workos-integration
Patterns for WorkOS SSO integration in Battery. Use this skill when implementing authentication, organization management, directory sync, or session handling.
majiayu000/claude-skill-registry 163
-
work-loop
Queue-driven work orchestrator. Processes requests from do-work/requests/ using isolated sub-agents. Use to start or resume the work loop.
majiayu000/claude-skill-registry 163
-
hls-cpp-to-rtl
Expert skill for C/C++ to RTL conversion using High-Level Synthesis tools
majiayu000/claude-skill-registry 163
-
varlock
Secure-by-default environment variable management for Claude Code sessions.
majiayu000/claude-skill-registry 163
-
spring-boot-data-ddd
Spring Boot 4 data layer implementation for Domain-Driven Design. Use when implementing JPA or JDBC aggregates, Spring Data repositories, transactional services, projections, or entity auditing. Covers aggregate roots with AbstractAggregateRoot, value object mapping, EntityGraph for N+1 prevention, and Spring Boot 4 specifics (JSpecify null-safety, AOT repositories). For DDD concepts and design decisions, see the domain-driven-design skill.
majiayu000/claude-skill-registry 163
-
create-plan
Create comprehensive implementation plan in .plans directory based on analysis or report. Use when user asks to create a plan, plan implementation, design a solution, or structure work for a feature/refactor/fix.
majiayu000/claude-skill-registry 163
-
wms-testing-patterns
Warehouse Management System testing patterns for inventory operations, pick/pack/ship workflows, wave management, EDI X12/EDIFACT compliance, RF/barcode scanning, and WMS-ERP integration. Use when testing WMS platforms (Blue Yonder, Manhattan, SAP EWM).
majiayu000/claude-skill-registry 163
-
flutter-testing
Comprehensive Flutter testing guidance covering unit tests, widget tests, and integration tests. Use when working with Flutter applications to write unit tests for functions/methods/classes, create widget tests to verify UI components, develop integration tests for end-to-end testing, mock dependencies and plugin interactions, debug common testing errors, test Flutter plugins with native code, and run tests in different build modes (debug, profile, release)
majiayu000/claude-skill-registry 163
-
writing
This skill should be used when the user asks to 'write a paper', 'start a writing project', 'draft an article', 'write about', 'brainstorm writing topics', 'gather sources for a paper', 'what should I write about', or needs the writing workflow entry point for any writing task.
majiayu000/claude-skill-registry 163
-
project-management
Manage projects and tasks across domains. USE WHEN create project OR new project OR pull tasks OR sync tasks OR update plan OR project status OR list projects OR task dashboard OR archive project OR project management OR track tasks.
majiayu000/claude-skill-registry 163
-
national-expungement-expert
Criminal record expungement laws across all 50 US states and DC — eligibility rules, waiting periods, filing processes, fees, Clean Slate laws, automatic expungement provisions. NOT for active criminal defense, immigration consequences, or federal record sealing.
majiayu000/claude-skill-registry 163
-
resolve-findings
Choose an implementation path (trivial or standard) for evaluated findings and dispatch it. Trivial path applies fixes directly; standard path runs /turboplan. Use after /evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "apply evaluated findings", or "dispatch findings to implementation".
majiayu000/claude-skill-registry 163
-
specsafe-done
Complete and archive spec
majiayu000/claude-skill-registry 163
-
ln-741-linter-configurator
Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers. Use when setting up linting and formatting for a project.
majiayu000/claude-skill-registry 163
-
terraform-engineer
Use when implementing infrastructure as code with Terraform across AWS, Azure, or GCP. Invoke for module development, state management, provider configuration, multi-environment workflows, infrastructure testing.
majiayu000/claude-skill-registry 163
-
translational-gap-analyzer
Assess translational gaps between preclinical models and human diseases to predict clinical failure risks
majiayu000/claude-skill-registry 163