ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
agent-deployment-pipeline
Implement CI/CD pipelines for AI agent deployment with evaluation gates. Use for GitHub Actions workflows, GitOps with ArgoCD, container image building, and automated testing. Triggers on "CI/CD", "pipeline", "GitHub Actions", "GitOps", "ArgoCD", "deployment automation", "continuous deployment", or when implementing safe agent release workflows.
majiayu000/claude-skill-registry 163
-
spaced-repetition
This document describes the translation-based spaced repetition system, its data model, and study flow.
majiayu000/claude-skill-registry 163
-
data-privacy-guardian
Detect PII, mask data, and manage consent and encryption.
majiayu000/claude-skill-registry 163
-
uloop-unity-search
Search Unity project for assets. Use when: finding scenes, prefabs, scripts, materials, or other assets by name/type, or when user asks to search project files. Returns asset paths and metadata.
majiayu000/claude-skill-registry 163
-
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
majiayu000/claude-skill-registry 163
-
ai-ad-spec-governor
majiayu000/claude-skill-registry 163
-
media-reviewer
Deep content analysis for structure, themes, narrative flow,
key moments, and important quotes. Use before content-documenter.
majiayu000/claude-skill-registry 163
-
0200
majiayu000/claude-skill-registry 163
-
Chatbot Implementation
Details of the RAG Chatbot, including UI and backend logic.
majiayu000/claude-skill-registry 163
-
linting-workflow
Generic linting workflow for multiple languages with auto-fix and error resolution guidance
majiayu000/claude-skill-registry 163
-
prompting-pattern-library
Comprehensive library of proven prompting patterns, frameworks, and examples for different use cases. This skill should be used when creating prompting guides, analyzing prompt effectiveness, teaching prompting techniques, or troubleshooting prompting issues. Use when writing about prompting, explaining prompting concepts to others, or improving existing prompts.
majiayu000/claude-skill-registry 163
-
rag-quality
RAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다.
majiayu000/claude-skill-registry 163
-
geniml
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
majiayu000/claude-skill-registry 163
-
firecrawl-common-errors
Diagnose and fix FireCrawl common errors and exceptions.
Use when encountering FireCrawl errors, debugging failed requests,
or troubleshooting integration issues.
Trigger with phrases like "firecrawl error", "fix firecrawl",
"firecrawl not working", "debug firecrawl".
majiayu000/claude-skill-registry 163
-
udemy-crawler
Extract Udemy course content to markdown. Use when user asks to scrape/crawl Udemy course pages.
majiayu000/claude-skill-registry 163
-
optimization.quality_report
Compile a recurring quality report that synthesizes defect trends, automation health, and recommendations.
majiayu000/claude-skill-registry 163
-
privacy-patterns
Implement privacy-preserving patterns using zero-knowledge proofs on Midnight Network. Use when designing private data handling, commitment schemes, nullifiers, or selective disclosure. Triggers on privacy, ZK proof, commitment, nullifier, or confidential computing questions.
majiayu000/claude-skill-registry 163
-
write-integrated
JD 기반 통합 지원서 HTML 작성이 필요할 때
majiayu000/claude-skill-registry 163
-
django-model
Creating Django models following Counterpart's patterns. Use when building new models, working with audit fields, implementing relationships, or using PydanticJSONEncoder. Triggers: 'create model', 'new database table', 'audit fields', 'BaseModel inheritance', 'add foreign key', 'JSON field validation'
majiayu000/claude-skill-registry 163
-
user-journey-mapping
Create comprehensive user journey maps that identify pain points, opportunities, and emotional states across touchpoints. Use when mapping user experiences or analyzing conversion flows.
majiayu000/claude-skill-registry 163
-
pydicom
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
majiayu000/claude-skill-registry 163
-
seo-fundamentals
TRIGGERS: "SEO check", "will this rank?", "meta tags", "search optimization", "Google",
"adding meta", "page title", "search ranking", "Next.js page", "building page",
"head section", "og:image", "social sharing", "sitemap", "robots.txt",
SEO, meta description, title tags, Open Graph, semantic HTML, sitemap, structured data.
USE WHEN: Junior is BUILDING pages, adding meta tags, or working on public-facing content.
PROVIDES: Meta tag standards, semantic HTML patterns, Open Graph setup, SEO best practices.
PROACTIVE: Triggers when junior mentions building pages or public-facing features.
majiayu000/claude-skill-registry 163
-
validating-ai-ethics-and-fairness
Validate AI/ML models and datasets for bias, fairness, and ethical concerns.
Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection.
Trigger with phrases like "evaluate model fairness", "check for bias", or "validate AI ethics".
majiayu000/claude-skill-registry 163
-
session-state-manager
Persistently stores conversation state, decisions, and progress to allow seamless resume across sessions.
majiayu000/claude-skill-registry 163