ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
converting-bicep-to-avm
Converts raw Bicep resource definitions to Azure Verified Modules (AVM). Use when user asks to convert to AVM, replace resources with modules, use verified modules, or modernize bicep templates.
majiayu000/claude-skill-registry 163
-
td-convolution
Convolution operations for signal processing and filtering
majiayu000/claude-skill-registry 163
-
composable-svelte-core
Core architecture patterns for Composable Svelte. Use when creating stores, writing reducers, working with effects, composing reducers, or implementing business logic. Covers the Store-Reducer-Effect trinity, all 12 effect types, composition strategies (scope, combineReducers, forEach), and immutable state updates.
majiayu000/claude-skill-registry 163
-
using-git-worktree
Create isolated git worktrees at bare repo root level
majiayu000/claude-skill-registry 163
-
codex-cli-subagent
Helps you to run a subagent using codex exec
majiayu000/claude-skill-registry 163
-
handler-work-tracker-jira
[DEPRECATED] Jira Cloud handler - Use Fractary CLI instead
majiayu000/claude-skill-registry 163
-
codearchitect
Analyzes a codebase to generate comprehensive architectural documentation including technologies used, data flows, functional components, APIs, external dependencies, commit history analysis, and complexity hotspots.
majiayu000/claude-skill-registry 163
-
backend-test-writer
Use when generating tests for backend code (Express routes, MongoDB models, Node services) - analyzes file type, detects test framework from package.json, generates comprehensive tests with setup/teardown and edge case coverage
majiayu000/claude-skill-registry 163
-
monty-code-review
Hyper-pedantic code review skill that emulates Monty's Django4Lyfe backend engineering philosophy and review style. Use this when reviewing or refactoring Python/Django code in this backend repo and you want a strict, correctness-first, multi-tenant-safe, deeply nitpicky review.
majiayu000/claude-skill-registry 163
-
agentdb-learning
Learning loops on top of AgentDB for reinforcement, curriculum, and replay buffers.
majiayu000/claude-skill-registry 163
-
commit-messager
Write clear and concise commit messages that accurately describe the changes made in the codebase
majiayu000/claude-skill-registry 163
-
tsh-i18n
Internationalization for TSH Clients Console (English/Arabic with RTL). Use when:
(1) Adding new text strings that need translation
(2) Creating components with user-facing text
(3) Working with RTL layout for Arabic
(4) Setting up new pages with proper i18n
(5) Debugging translation issues
(6) Adding metadata translations for SEO
majiayu000/claude-skill-registry 163
-
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
majiayu000/claude-skill-registry 163
-
github-issue-helper
GitHub 이슈 작성 도우미. 사용자가 이슈 초안이나 아이디어를 제시하면 고품질 GitHub 이슈로 개선. Use when user asks to (1) write/create/draft a GitHub issue, (2) improve/refine an issue draft, (3) convert an idea into a proper issue format, (4) review issue quality. Supports bug reports, feature requests, and improvement proposals. Communicates in Korean but produces final issues in English.
majiayu000/claude-skill-registry 163
-
agent-builder
Design and build AI agents for any domain. Use when users:
(1) ask to "create an agent", "build an assistant", or "design an AI system"
(2) want to understand agent architecture, agentic patterns, or autonomous AI
(3) need help with capabilities, subagents, planning, or skill mechanisms
(4) ask about Claude Code, Cursor, or similar agent internals
(5) want to build agents for business, research, creative, or operational tasks
Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
majiayu000/claude-skill-registry 163
-
decay-upkeep
Building decay and upkeep systems for survival games. Use when implementing timer-based decay, Tool Cupboard patterns (Rust-style protection radius), resource upkeep costs, or server performance management through automatic cleanup. Balances gameplay and server health.
majiayu000/claude-skill-registry 163
-
jpa-entity-creator
Creates JPA entities following best practices.
majiayu000/claude-skill-registry 163
-
api-cache-invalidation
Automatic cache invalidation system với Laravel Observers và Next.js On-Demand Revalidation. Tự động sync data real-time giữa backend và frontend khi admin update. USE WHEN cần setup cache management, sync frontend-backend, API cache strategy, hoặc user phàn nàn "phải Ctrl+F5 mới thấy data mới".
majiayu000/claude-skill-registry 163
-
code-review-practices
Provides practical guidance for conducting thorough code reviews that identify issues early, promote knowledge sharing, and deliver constructive feedback. This skill should be used when reviewing pull requests, establishing team review standards, or mentoring developers on effective review practices.
majiayu000/claude-skill-registry 163
-
hexo-butterfly
Hexo Butterfly 主题配置与使用指南，包括主题安装、页面配置、主题配置、标签外挂、FAQ、进阶教程
majiayu000/claude-skill-registry 163
-
body-tracking
Person detection, tracking, and Re-ID. Use when faces aren't visible but cast should still be tracked, or when debugging face-body association.
majiayu000/claude-skill-registry 163
-
voice-update
This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.
majiayu000/claude-skill-registry 163
-
gemini-megacontext
Gemini mega-context patterns for very large prompts and retrieval planning.
majiayu000/claude-skill-registry 163
-
Modify Generated Code
Workflow for modifying generated code in Baseplate, including template extraction, generator updates, and project synchronization.
majiayu000/claude-skill-registry 163