Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
puppeteer
使用Puppeteer（Google）进行浏览器自动化和PDF生成。支持无头Chrome控制，用于网页爬虫、截图、PDF生成和自动化测试。
majiayu000/claude-skill-registry 163
-
css-generation-lobbi-docs-claude
Generate CSS, Tailwind, and styled-components code from design style selections
majiayu000/claude-skill-registry 163
-
axiom-ios-vision
Use when implementing ANY computer vision feature - image analysis, object detection, pose detection, person segmentation, subject lifting, hand/body pose tracking.
majiayu000/claude-skill-registry 163
-
clean-ddd-hexagonal
Apply Clean Architecture + DDD + Hexagonal patterns to backend services. Use when designing APIs, microservices, domain models, aggregates, repositories, bounded contexts, or scalable backend structure. Triggers on DDD, Clean Architecture, Hexagonal, ports and adapters, entities, value objects, domain events, CQRS, event sourcing, repository pattern, use cases, onion architecture, outbox pattern, aggregate root, anti-corruption layer. Language-agnostic (Go, Rust, Python, TypeScript, Java, C#).
majiayu000/claude-skill-registry 163
-
learning-objectives
Generate measurable learning outcomes aligned with Bloom's taxonomy and CEFR proficiency levels for educational content. Use when educators need to define what students will achieve, create learning objectives for curriculum planning, or ensure objectives are specific and testable rather than vague.
majiayu000/claude-skill-registry 163
-
user-experience
Consistent user communication patterns for confidence, clarity, and engagement. Reference for all command output.
majiayu000/claude-skill-registry 163
-
standards-us-state-mapper
Map curriculum to any US state standards framework, support all 50 states' unique standards, crosswalk between state standards, and generate state-specific alignment reports. Use when aligning to state education standards. Activates on "state standards", "TEKS", "state curriculum", or "standards alignment".
majiayu000/claude-skill-registry 163
-
scope-discipline
Use when implementing features, editing source code, or responding to task handoffs. Enforces doing exactly what was requested - no scope creep, no "while I'm here" additions.
majiayu000/claude-skill-registry 163
-
fluff-detector
Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.
majiayu000/claude-skill-registry 163
-
critical-code-reviewer
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
majiayu000/claude-skill-registry 163
-
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
majiayu000/claude-skill-registry 163
-
Benchmark Manager
Create and manage AILANG eval benchmarks. Use when user asks to create benchmarks, fix benchmark issues, debug failing benchmarks, or analyze benchmark results.
majiayu000/claude-skill-registry 163
-
Bun Next.js
This skill should be used when the user asks about "Next.js with Bun", "Bun and Next", "running Next.js on Bun", "Next.js development with Bun", "create-next-app with Bun", or building Next.js applications using Bun as the runtime.
majiayu000/claude-skill-registry 163
-
value-objects
majiayu000/claude-skill-registry 163
-
frontend-design-system
フロントエンドUIデザインを洗練された独自性のあるスタイルで生成します。ランディングページ、ダッシュボード、Webアプリケーションのデザイン、UIコンポーネント作成時に使用してください。「AIっぽい」汎用デザインを避け、プロフェッショナルで記憶に残るUIを実現します。
majiayu000/claude-skill-registry 163
-
dependency-audit
Audit npm dependencies for security vulnerabilities, outdated packages, and license compliance.
majiayu000/claude-skill-registry 163
-
gcp-storage
GCP Cloud Storage 버킷 관리
majiayu000/claude-skill-registry 163
-
jupyter-notebook
Use when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; classifies intent as experiment or tutorial, scaffolds from bundled templates via new_notebook.py, fills cells with small runnable steps, and validates the result against a quality checklist.
majiayu000/claude-skill-registry 163
-
prometheus
Prometheus monitoring and alerting for cloud-native observability.
USE WHEN: Writing PromQL queries, configuring Prometheus scrape targets, creating alerting rules, setting up recording rules, instrumenting applications with Prometheus metrics, configuring service discovery.
DO NOT USE: For building dashboards (use /grafana), for log analysis (use /logging-observability), for general observability architecture (use senior-infrastructure-engineer).
TRIGGERS: metrics, prometheus, promql, counter, gauge, histogram, summary, alert, alertmanager, alerting rule, recording rule, scrape, target, label, service discovery, relabeling, exporter, instrumentation, slo, error budget.
majiayu000/claude-skill-registry 163
-
optimizing-wpf-memory
Covers WPF memory optimization including Freezable patterns, common memory leak causes, and diagnostic techniques. Use when experiencing memory growth, implementing resource caching, or debugging memory issues.
majiayu000/claude-skill-registry 163
-
load-skill
Load, activate, and optionally install an AI skill from a .skill file. Use this skill when the user wants to load, activate, or use a skill file. The user can invoke this skill with slash command `/load-skill [ --install | -i ] SKILLFILE`, where SKILLFILE is the path to a .skill file.
majiayu000/claude-skill-registry 163
-
repository-class-conventions
Governs the structure and functionality of repository classes, emphasizing the use of JpaRepository, JPQL queries, and EntityGraphs to prevent N+1 problems.
majiayu000/claude-skill-registry 163
-
ci-test-claude-skill
CI Test Claude Skill
majiayu000/claude-skill-registry 163
-
cross-skill-references-test
Test skill with cross-skill reference notation
majiayu000/claude-skill-registry 163