Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
save-session
Save session state to Pieces LTM. Use when context is running low, before /compact, when ending a session, or handing off to a fresh Claude instance.
majiayu000/claude-skill-registry 163
-
when-automating-workflows-use-hooks-automation
majiayu000/claude-skill-registry 163
-
staged-hydration-systems
Develop staged hydration systems for prioritizing critical UI regions and progressive interactivity.
majiayu000/claude-skill-registry 163
-
nextjs-opentelemetry-instrumentation
OpenTelemetry distributed tracing for Next.js 14+
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
-
gpt-researcher
Use this skill for comprehensive research tasks requiring deep investigation, multiple source validation, and citation-backed reports. Triggers on keywords like "research", "investigate", "deep dive", "comprehensive analysis", "literature review", or when needing validated, sourced information.
majiayu000/claude-skill-registry 163
-
bio-read-qc-fastp-workflow
All-in-one read preprocessing with fastp including adapter trimming, quality filtering, deduplication, base correction, and HTML report generation. Use when preprocessing Illumina data and wanting a single fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps.
majiayu000/claude-skill-registry 163
-
architecture-paradigm-microservices-athola-claude-night-market
majiayu000/claude-skill-registry 163
-
when-using-advanced-swarm-use-swarm-advanced-dnyoussef-context-cascade
majiayu000/claude-skill-registry 163
-
ln-721-frontend-restructure
Restructures React frontend from monolith to component-based architecture
majiayu000/claude-skill-registry 163
-
build-design-system
Build a design system from scratch using the Design Graph methodology. Use when starting a component library, creating design tokens, establishing typography scales, or structuring a theme. Based on Brent Jackson's (jxnblk) constraint-based systems.
majiayu000/claude-skill-registry 163
-
stakeholder-summary
majiayu000/claude-skill-registry 163
-
dokploy-management
Use when deploying, managing, or troubleshooting Dokploy instances via the CLI (https://github.com/Dokploy/cli).
Triggers: "dokploy deploy", "manage dokploy", "dokploy app", "dokploy database", "push to dokploy",
"dokploy CI/CD", "dokploy authentication", "zero-downtime deployment", "dokploy docker-compose",
"dokploy environment variables", "dokploy health checks".
Provides comprehensive workflows for authentication, project/app/database management, environment variable
sync, and production-ready CI/CD patterns with GitHub Actions.
majiayu000/claude-skill-registry 163
-
ln-710-dependency-upgrader
Coordinates dependency upgrades across all detected package managers
majiayu000/claude-skill-registry 163
-
prompt-improvement
Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example identification, initial draft, chain of thought refinement, example enhancement), keyword registries for documentation lookup, and decision trees for improvement strategies. Use when improving prompts, optimizing for accuracy, adding chain of thought reasoning, structuring with XML tags, enhancing examples, or iterating on prompt quality. Delegates to docs-management skill for official prompt engineering documentation.
majiayu000/claude-skill-registry 163
-
codebase-locator
Find and document file locations in the codebase. Use this when you need to locate implementation files, tests, configurations, or any code artifacts by feature or topic. Works with Grep, Glob, and LS tools.
majiayu000/claude-skill-registry 163
-
mcp-deepwiki
This skill provides guidance for using DeepWiki MCP to explore GitHub repository documentation. Use when researching repository structure, understanding library APIs, asking questions about open-source projects, or exploring documentation for any GitHub repository.
majiayu000/claude-skill-registry 163
-
genomic-feature-annotation
This skill is used to perform genomic feature annotation and visualization for any file containing genomic region information using Homer (Hypergeometric Optimization of Motif EnRichment). It annotates regions such as promoters, exons, introns, intergenic regions, and TSS proximity, and generates visual summaries of feature distributions.
majiayu000/claude-skill-registry 163
-
multi-model-orchestrator
多模型协作 — 调用 gemini-agent 和 codex-agent 辅助分析
**触发场景**（主动使用）：
- 深度代码分析：算法理解、性能瓶颈、架构梳理
- 大范围探索：5+ 文件、模块依赖、调用链追踪
- 复杂推理：方案评估、逻辑验证、并发安全分析
- 多视角决策：需要不同角度分析再综合判断
**不触发**：
- 简单修改（1-2 文件的明确改动）
- 文件查找（用 Explore 或 Glob/Grep）
- 已知路径的读写操作
**核心原则**：你是决策者和执行者，外部模型是顾问。
majiayu000/claude-skill-registry 163
-
reframe
This skill should be used when the user is stuck, obvious solutions aren't working, constraints feel impossible, or they keep circling back to bad options. Use when designs keep getting rejected or the user is solving symptoms instead of root causes.
majiayu000/claude-skill-registry 163
-
manage-version
Terraform/Terragrunt のバージョンを管理する。「terraform バージョン」「tfenv」「tgswitch」「tf バージョン切り替え」「terraform インストール」「バージョン確認」「tf version」「terraform 1.5 にして」「tg バージョン」などで起動。
majiayu000/claude-skill-registry 163
-
video-production-taiyousan15-taisun-agent
majiayu000/claude-skill-registry 163
-
sharing-skills
Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository
majiayu000/claude-skill-registry 163
-
jotai-reactive-atoms
Implement reactive state management with Jotai atoms in Electron renderer. Use when creating atoms, implementing real-time updates via IPC, or setting up hybrid stream + HTTP fallback patterns. Covers event subscription optimization, debouncing, and Suspense integration.
majiayu000/claude-skill-registry 163