Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
loading-states
Design effective loading states, skeleton screens, and empty states that maintain user confidence. Use when content takes time to load, when showing progress, or handling empty data scenarios. Triggers on "loading state", "skeleton screen", "empty state", "spinner", "progress bar", "loading animation", "zero state".
majiayu000/claude-skill-registry 163
-
payment-tracking-rule
majiayu000/claude-skill-registry 163
-
android-e2e-testing-setup
Setup UI Automator 2.4 smoke test for validating app launches (works with debug and release builds)
majiayu000/claude-skill-registry 163
-
ios-game-testing
Test the Nathaniel iOS game in simulator. Use when asked to test the game, verify changes work, run sanity tests, check if a feature works, or when the user says "test this", "run the game", "verify it works", "check in simulator".
majiayu000/claude-skill-registry 163
-
ai-model-nodejs
Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation (generateText), streaming (streamText), AND image generation (generateImage) via @cloudbase/node-sdk ≥3.16.0. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended), DeepSeek (deepseek-v3.2 recommended), and hunyuan-image for images. This is the ONLY SDK that supports image generation. NOT for browser/Web apps (use ai-model-web) or WeChat Mini Program (use ai-model-wechat).
majiayu000/claude-skill-registry 163
-
meta-convert-dev
Create language conversion skills for translating code from language A to language B. Use when building 'convert-X-Y' skills, designing type mappings between languages, establishing idiom translation patterns, or defining conversion methodologies. Provides foundational patterns that specific conversion skills extend.
majiayu000/claude-skill-registry 163
-
checkpoint-resume
Exactly-once processing semantics with distributed coordination for file-based data pipelines. Atomic file claiming, status tracking, and automatic retry with in-memory fallback.
majiayu000/claude-skill-registry 163
-
cloud-backup
云备份方案
majiayu000/claude-skill-registry 163
-
go-cli
CLI application patterns and best practices
majiayu000/claude-skill-registry 163
-
rag-implementation
Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.
majiayu000/claude-skill-registry 163
-
document-feature-whatifwedigdeeper-application-tracker
Generate technical and user documentation for a feature
majiayu000/claude-skill-registry 163
-
datadog-cli
Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.
majiayu000/claude-skill-registry 163
-
golang-pro
Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. Expert in the latest Go ecosystem including generics, workspaces, and cutting-edge frameworks. Use PROACTIVELY for Go development, architecture design, or performance optimization.
majiayu000/claude-skill-registry 163
-
experimental-research-metacognition
Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling. Use when behavior is uncertain, contested, or performance-sensitive.
majiayu000/claude-skill-registry 163
-
vulnerability-scanning
Automated vulnerability detection using OWASP tools, CVE databases, and security scanners. Use when performing security audits, compliance checks, or continuous security monitoring.
majiayu000/claude-skill-registry 163
-
deepwork_rules.define
Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands.
majiayu000/claude-skill-registry 163
-
dokploy-security-hardening
Security best practices for Dokploy templates: secrets management, network isolation, least privilege, image security, and hardening recommendations.
majiayu000/claude-skill-registry 163
-
account-health-framework
Use to score accounts, flag risks, and standardize remediation triggers.
majiayu000/claude-skill-registry 163
-
01-meta-chain-of-skills-150
[01] META. Сканирует доступные skills, создает план выполнения и идет шаг за шагом с подтверждением каждого этапа. Triggers on complex tasks, multi-step work, or when structured execution is needed.
majiayu000/claude-skill-registry 163
-
critical-business-brief
Create critical business briefs through challenging dialogue that validates ideas and stress-tests assumptions. Use when user presents business ideas, wants to explore concepts, mentions starting a business, or needs business validation. Conducts realistic, skeptical conversations to expose weaknesses and creates structured business briefs in .ideas/ folder. Triggers include "I have a business idea", "business opportunity", "startup idea", or "validate this concept".
majiayu000/claude-skill-registry 163
-
ta-vfx-particles
GPU particle systems for high-performance visual effects. Use when creating particle effects, instanced rendering, GPU-accelerated VFX.
majiayu000/claude-skill-registry 163
-
new-skill
Creates a new Claude Code Skill following best practices. Use when the user wants to create a new skill, add a skill, or asks about writing skills for Claude Code. Fetches latest documentation before generating skill content. New skill. Create a skill.
majiayu000/claude-skill-registry 163
-
pragmatic-writing
This skill should be used when writing technical content in the style of Hunt/Thomas (The Pragmatic Programmer) and Joel Spolsky (Joel on Software). It applies when creating technical essays, documentation, tutorials, or explanatory content that needs to be clear, engaging, and actionable.
majiayu000/claude-skill-registry 163
-
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
majiayu000/claude-skill-registry 163