ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
review:pre-merge
Pre-merge review focusing on correctness, testing, security, refactor safety, and maintainability. Spawns the senior-review-specialist agent for thorough pre-merge analysis.
majiayu000/claude-skill-registry 163
-
validating-cors-policies
Validate CORS policies for security issues and misconfigurations. Use when reviewing cross-origin resource sharing. Trigger with 'validate CORS', 'check CORS policy', or 'review cross-origin'.
majiayu000/claude-skill-registry 163
-
ln-622-build-auditor
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
majiayu000/claude-skill-registry 163
-
rust-lifetime-complex
高级生命周期专家。处理 HRTB, GAT, 'static 约束, dyn trait object, 泛型边界冲突等问题。触发词：lifetime, HRTB, GAT, 'static, dyn, trait object, one type is more general, 生命周期, 类型约束
majiayu000/claude-skill-registry 163
-
artificial-analysis-compare
Compare LLM models using the Artificial Analysis API. This skill should be used when the user asks to compare AI models, benchmark LLMs, evaluate model performance, compare pricing between models, or find the best model for a specific use case (coding, math, speed, cost). Triggers on requests like "compare GPT-5 and Claude", "which model is fastest", "cheapest model for coding", "benchmark comparison", "model performance analysis", or "artificial analysis". (user)
majiayu000/claude-skill-registry 163
-
lang-clojure-dev
Foundational Clojure patterns covering functional programming, REPL-driven development, immutable data structures, and idiomatic code. Use when writing Clojure code, working with sequences and lazy evaluation, understanding macros, or needing guidance on functional programming patterns. This is the entry point for Clojure development.
majiayu000/claude-skill-registry 163
-
component-analysis
Cross-component consistency analysis for the 12 component groups (Brand, Typography, Button, Form, Selector, Table, Chart, Display, Overlay, Navigation, Feedback, Fallback). Evaluates uniformity and identifies pattern deviations. Combinable with other review skills.
majiayu000/claude-skill-registry 163
-
quality-validator
majiayu000/claude-skill-registry 163
-
test-sdk-task-tools
Test if forked skill called from SDK has TaskCreate/List/Get/Update tools
majiayu000/claude-skill-registry 163
-
scaffold-analysis
识别项目技术栈、测试框架和环境依赖，为 Compile ExecSpec 提供基础上下文。当需要编译 ExecSpec 前，识别项目类型（Node/Python/Go）、测试框架（Jest/Pytest/RSpec）、环境变量依赖（dotenv/os.getenv）时使用。
majiayu000/claude-skill-registry 163
-
AI Cross Validator
Dual-AI code validation using both Claude and Google Gemini to catch 20% more issues. Validates React Native screens for security vulnerabilities, performance anti-patterns, accessibility gaps, and best practices. Use when user says "validate with Gemini", "cross-validate", "AI review", or before deploying code to production.
majiayu000/claude-skill-registry 163
-
gh-creating-project-drafts
Creates a draft issue item in a GitHub Project. Use for items that don't yet have a corresponding repository issue.
majiayu000/claude-skill-registry 163
-
tome-guide
How to use tome - the AI agent skill manager
majiayu000/claude-skill-registry 163
-
bench
Generate mitata benchmark files following project conventions
majiayu000/claude-skill-registry 163
-
Gardening Skills Wiki
Maintain skills wiki health - check links, naming, cross-references, and coverage
majiayu000/claude-skill-registry 163
-
javascript-pro
Master modern JavaScript with ES6+, async patterns, and Node.js APIs. Handles promises, event loops, and browser/Node compatibility. Use PROACTIVELY for JavaScript optimization, async debugging, or complex JS patterns.
majiayu000/claude-skill-registry 163
-
frontend-ui
UI/UX guidelines for app development in this Turborepo (apps/web and future apps). Use when designing or implementing app pages, layouts, navigation, or interactions with Tailwind and @repo/ui components.
majiayu000/claude-skill-registry 163
-
sop-rfc2119
Use when writing SOPs that require precise requirement levels using RFC 2119 constraint keywords (MUST, SHOULD, MAY). Covers proper usage of requirement keywords for deterministic agent behavior.
majiayu000/claude-skill-registry 163
-
coolify-deployment
Deploy Coolify self-hosted PaaS for application hosting. Covers VM provisioning, installation, GitHub integration, and application deployment with auto-SSL.
majiayu000/claude-skill-registry 163
-
names-check
Analyze examples and mock data for name diversity, understanding the context and purpose before suggesting changes. Use when reviewing test data, documentation, or seed data.
majiayu000/claude-skill-registry 163
-
kubernetes-essentials
Quick reference for Kubernetes core concepts and kubectl commands. This skill should be used as a refresher for basic K8s operations including pods, deployments, services, configmaps, secrets, and namespaces. Use this skill when working with Kubernetes clusters for Phase IV+ deployments.
majiayu000/claude-skill-registry 163
-
backlog-refinement-guide
Эксперт backlog refinement. Используй для grooming sessions, story estimation и prioritization.
majiayu000/claude-skill-registry 163
-
risk-sizing-not-blocking
Risk managers should SIZE trades, not BLOCK them. Trigger when: (1) capital manager blocks trades, (2) risk manager rejects orders, (3) trades fail due to 'exceeds limit', (4) components don't work in harmony.
majiayu000/claude-skill-registry 163
-
code-review-trigger
Natural language wrapper for code review - automatically triggers /code-review when users express intent to review code, check for bugs, or validate code quality
majiayu000/claude-skill-registry 163