Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
client-discovery-interview
Conducts structured discovery interviews for consultants, agencies, and service providers. Guides conversation through problem identification, stakeholder mapping, success criteria definition, budget/timeline scoping, and produces a formatted discovery brief with next steps.
majiayu000/claude-skill-registry 163
-
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
majiayu000/claude-skill-registry 163
-
claude-code-self-generation-over-api
Use when Claude Code needs to generate or transform text data in bulk. Try self-generation before API calls on Max plan.
majiayu000/claude-skill-registry 163
-
equipment-telematics
Integrate and analyze telematics data from heavy construction equipment. Track location, utilization, fuel consumption, maintenance needs, and operator behavior.
majiayu000/claude-skill-registry 163
-
linkedin-campaign-development
This skill should be used when the user asks to "create a LinkedIn campaign", "develop personalized outreach", "write LinkedIn messages", "research leads for a campaign", "create Sales Navigator outreach", "build B2B outreach", "personalize messages for leads", or mentions LinkedIn campaign development, lead personalization, identity-first messaging, or Sales Navigator campaigns.
majiayu000/claude-skill-registry 163
-
verify-class-tabs
수업 그룹(시간표/출석부/출결관리/수업관리/강의실/강의실배정/숙제관리/시험관리/교재관리) 탭의 핵심 기능을 검증합니다. 수업 관련 컴포넌트 수정 후 사용.
majiayu000/claude-skill-registry 163
-
pydantic-evals
Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4) Compare model performance across experiments, (5) Integrate evaluations with Pydantic AI agents, (6) Set up observability with Logfire, (7) Generate test datasets using LLMs, (8) Implement regression testing for AI systems.
majiayu000/claude-skill-registry 163
-
marketing-ideas
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category.
majiayu000/claude-skill-registry 163
-
release
Release workflow — version bump, changelog generation, git tag, release notes. Use when preparing a new version for deployment.
majiayu000/claude-skill-registry 163
-
jinling
Jinling (JILN) connector MPN encoding, position-based part numbering for pin headers, female headers, and IDC connectors.
majiayu000/claude-skill-registry 163
-
go-testing-code-review
Reviews Go test code for proper table-driven tests, assertions, and coverage patterns. Use when reviewing *_test.go files.
majiayu000/claude-skill-registry 163
-
deploying-kafka-k8s
Deploys Apache Kafka on Kubernetes using the Strimzi operator with KRaft mode.
Use when setting up Kafka for event-driven microservices, message queuing, or pub/sub patterns.
Covers operator installation, cluster creation, topic management, and producer/consumer testing.
NOT when using managed Kafka (Confluent Cloud, MSK) or local development without K8s.
majiayu000/claude-skill-registry 163
-
skill-vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
majiayu000/claude-skill-registry 163
-
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
majiayu000/claude-skill-registry 163
-
pyinstaller-config
Configure PyInstaller for Python binary builds with spec files and bundling options.
majiayu000/claude-skill-registry 163
-
team-builder
Designs high-performing team structures using organizational psychology AND creates new skills on-the-fly when team needs unmet expertise. Expert in team composition, personality balancing, collaboration ritual design, and skill creation for missing capabilities. Use for team design, role definition, skill gap identification. Activates on 'team building', 'team composition', 'skills needed', 'what skills'. NOT for general project management or solo work planning.
majiayu000/claude-skill-registry 163
-
agent-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
majiayu000/claude-skill-registry 163
-
frontend-design
创建具有高设计质量的独特生产级前端接口。当用户要求构建Web组件、页面、工件、海报或应用程序时（例如，包括网站、登录页面、仪表板、React组件、HTML/CSS布局，或在样式化/美化任何Web UI时） ，请使用此技能。生成创意、精美的代码和UI设计，避免通用的AI美学。
majiayu000/claude-skill-registry 163
-
dont-be-greedy
When a user uploads or references a data file (CSV, JSON, XLSX, TXT, LOG) or any
file larger than 100KB, immediately estimate token cost using scripts/estimate_size.py.
If >30k tokens, chunk the file and summarize each chunk. If smaller, run quick inspection.
Return a safe preview and summary without asking the user what to do.
majiayu000/claude-skill-registry 163
-
build-and-run-tassadar2499-novatune
Build, run, and test the NovaTune .NET Aspire application
majiayu000/claude-skill-registry 163
-
Bun Docker
Use for Docker with Bun, Dockerfiles, oven/bun image, containerization, and deployments.
majiayu000/claude-skill-registry 163
-
bmad-wds-view-components
Preview selected design system components rendered in localhost
majiayu000/claude-skill-registry 163
-
scan-scss-styling
[Documentation] Scan project and populate/sync docs/project-reference/scss-styling-guide.md with BEM methodology, SCSS architecture, mixins, variables, theming, and responsive patterns.
majiayu000/claude-skill-registry 163
-
claude-gladiator
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
majiayu000/claude-skill-registry 163