Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
majiayu000/claude-skill-registry 163
-
gtars
High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.
majiayu000/claude-skill-registry 163
-
md-tables
majiayu000/claude-skill-registry 163
-
design-system-creator
Builds comprehensive design systems and design bibles with production-ready CSS. Expert in design tokens, component libraries, CSS architecture. Use for design system creation, token architecture, component documentation, style guide generation. Activate on "design system", "design tokens", "CSS architecture", "component library", "style guide", "design bible". NOT for typography deep-dives (use typography-expert), color theory mathematics (use color-theory-palette-harmony-expert), brand identity strategy (use web-design-expert), or actual UI implementation (use web-design-expert or native-app-designer).
majiayu000/claude-skill-registry 163
-
code-gen-agent
Fast code generation agent optimized for speed and iteration
majiayu000/claude-skill-registry 163
-
research-add-fields
Add field definitions to existing research outline.
majiayu000/claude-skill-registry 163
-
qrcode-generator
从文本、URL或数据生成二维码,支持自定义颜色、Logo和多种输出格式。
majiayu000/claude-skill-registry 163
-
kit-builder
Build ClaudeKit Marketing components - skills, agents, commands, workflows. Use when creating new automation, extending marketing capabilities, or understanding kit structure. Includes templates, examples, and init scripts.
majiayu000/claude-skill-registry 163
-
claude-code-plugin-development
This skill should be used when the user asks to "create a plugin", "build a plugin", "write a plugin", or wants to bundle agents, hooks, commands, skills, or MCP servers into a distributable Claude Code plugin.
majiayu000/claude-skill-registry 163
-
context-management
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration.
Use when approaching token limits or needing to preserve essential context.
Complements /transcripts and PreCompact hook with proactive optimization.
majiayu000/claude-skill-registry 163
-
consulting-wealth-managers
Use this skill when working with wealth managers, financial advisors, RIAs, or financial planners. Covers AI enablement for advisory workflows, portfolio management tools, client reporting automation, CRM integration, and wealth management industry knowledge. Invoke for any wealth management consulting, tool recommendations, or workflow automation for financial advisors.
majiayu000/claude-skill-registry 163
-
add-doc
Add new documentation sources to .claude/doc-sources.toml for Context7 access
majiayu000/claude-skill-registry 163
-
bio-experimental-design-power-analysis
Calculates statistical power and minimum sample sizes for RNA-seq, ATAC-seq, and other sequencing experiments. Use when planning experiments, determining how many replicates are needed, or assessing whether a study is adequately powered to detect expected effect sizes.
majiayu000/claude-skill-registry 163
-
cloudflare-kv
Store key-value data globally with Cloudflare KV's edge network. Use when: caching API responses, storing configuration, managing user preferences, handling TTL expiration, or troubleshooting KV_ERROR, 429 rate limits, eventual consistency, cacheTtl errors, wrangler types issues, or remote binding configuration.
majiayu000/claude-skill-registry 163
-
context7-docs
Fetches up-to-date documentation for technologies used in the Personal AI Employee project via Context7 MCP server. Use when you need current API documentation, library references, code examples, or implementation guidance for any technology in the stack.
majiayu000/claude-skill-registry 163
-
llm_evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
majiayu000/claude-skill-registry 163
-
commissioning-reports
Building commissioning workflows including MBCx procedures, testing protocols, report generation, and energy conservation measure verification following ASHRAE Guideline 0 and NEBB standards
majiayu000/claude-skill-registry 163
-
peak-end-rule
Las experiencias se juzgan por su punto más intenso y su final. Use cuando diseñe user journeys, onboarding, checkout, o cualquier experiencia extendida.
majiayu000/claude-skill-registry 163
-
nitro-testing
Test Nuxt 3 / Nitro API handlers with real PostgreSQL, transaction rollback isolation, and typed factories. No mocks, real SQL.
majiayu000/claude-skill-registry 163
-
suggest-tests
Recommend unit tests to add based on git diff changes. Analyzes modified code and prioritizes by risk level.
majiayu000/claude-skill-registry 163
-
nielsen-help-documentation
Proporciona documentación accesible y orientada a tareas. Use cuando diseñe sistemas de ayuda, onboarding, tooltips, o documentación de usuario.
majiayu000/claude-skill-registry 163
-
tailwindcss-backgrounds
Background utilities Tailwind CSS v4.1. Colors (bg-{color}, palette OKLCH P3), Gradients (bg-linear-*, bg-radial-*, bg-conic-* NEW), Images (bg-cover, bg-contain, bg-repeat), Blend modes.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-keyvalue-get
Get a value from the keyvalue storage. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
pytorch-geometric
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
majiayu000/claude-skill-registry 163