Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
feedback-indicators
Use when confirming user actions - success checkmarks, error alerts, form validation, save confirmations, or any animation acknowledging what the user did.
majiayu000/claude-skill-registry 163
-
creating-kubernetes-deployments
This skill enables Claude to generate Kubernetes deployment manifests, services, and related configurations following best practices. It should be used when the user asks to create a new Kubernetes deployment, service, ingress, or other related resources. Claude will generate YAML files for Deployments, Services, ConfigMaps, Secrets, Ingress, and Horizontal Pod Autoscalers. Use this skill when the user mentions "Kubernetes deployment", "K8s deployment", "create service", "define ingress", or asks for a manifest for any K8s resource.
majiayu000/claude-skill-registry 163
-
fiftyone-dataset-inference
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
majiayu000/claude-skill-registry 163
-
prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
majiayu000/claude-skill-registry 163
-
excel-pivot-wizard
Generate pivot tables and charts from raw data using natural language - analyze sales by region, summarize data by category, and create visualizations effortlessly
majiayu000/claude-skill-registry 163
-
Query Axiom Logs
Query logs from Axiom for debugging (read-only, no ingestion allowed)
majiayu000/claude-skill-registry 163
-
java-test-engineer
This skill should be used when the user asks to 'write unit tests', 'add integration tests', 'create property-based tests', 'fix failing test', 'improve test coverage', 'reduce mocking', 'test this class', 'add jqwik tests', or needs guidance on JUnit 5, Mockito, Spring Boot Test, property testing with jqwik, test patterns, mocking strategies, or test anti-patterns. Covers Java/Spring Boot testing best practices.
majiayu000/claude-skill-registry 163
-
windows-git-bash-paths
Windows and Git Bash path handling for SSDT, SqlPackage, and DACPAC files with shell detection
majiayu000/claude-skill-registry 163
-
plan-week
Create a focused weekly plan based on tasks, priorities, and your work patterns. Use when the user types /plan_week, after a weekly review, at the start of a new week, or when feeling overwhelmed by options.
majiayu000/claude-skill-registry 163
-
rust-development-vuralserhat86-antigravity-agentic
majiayu000/claude-skill-registry 163
-
refactor-agent
Refactors code with loop behavior for iterative improvement
majiayu000/claude-skill-registry 163
-
nextjs-opentelemetry-instrumentation
OpenTelemetry distributed tracing for Next.js 14+
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
-
precommit
Running precommit checks and build validation. ALWAYS use after ANY code changes.
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
-
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
-
redis-state-management
Comprehensive guide for Redis state management including caching strategies, session management, pub/sub patterns, distributed locks, and data structures
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. ChIPseeker mode is also supported according to requirements.
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
-
codex-plugin-dev-validate
Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), check description quality for discovery, or needs a plugin-dev-like validation step for skill packaging.
majiayu000/claude-skill-registry 163
-
claude-mem
Persistent memory compression system for Claude Code enabling context preservation across sessions with automatic observations, semantic search, and privacy controls
majiayu000/claude-skill-registry 163
-
second-opinion
Cross-validate code, architecture or design decisions using a second model. Use for critical decisions, complex refactoring, security reviews.
majiayu000/claude-skill-registry 163