ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
creating-skills
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples
majiayu000/claude-skill-registry 163
-
pr-context-retriever
Specialized GitHub PR intelligence agent for automatically gathering comprehensive context from Pull Requests. Activate when users need CI failure analysis, review comment investigation, or PR status assessment. Triggers on requests like "CI 실패 원인 찾아줘", "gather review comments", "check PR status", "analyze PR".
majiayu000/claude-skill-registry 163
-
docker
Guide for using Docker - a containerization platform for building, running, and deploying applications in isolated containers. Use when containerizing applications, creating Dockerfiles, working with Docker Compose, managing images/containers, configuring networking and storage, optimizing builds, deploying to production, or implementing CI/CD pipelines with Docker.
majiayu000/claude-skill-registry 163
-
fzf
Command-line fuzzy finder for interactive filtering of any list. Use when interactively selecting files, searching command history (CTRL-R), creating selection interfaces in scripts, building interactive menus, or integrating fuzzy search with tools like ripgrep, fd, and git. Triggers on mentions of fzf, fuzzy finder, ** completion, interactive filtering, or shell keybindings CTRL-T/CTRL-R/ALT-C.
majiayu000/claude-skill-registry 163
-
code-review
Review source code and create a report in Japanese
majiayu000/claude-skill-registry 163
-
github-kernel
foundational definitions for GitHub skills, safety rules, tool escalation, and security boundaries
majiayu000/claude-skill-registry 163
-
dev-swarm-create-update-agent-skill
Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or update an existing skill.
majiayu000/claude-skill-registry 163
-
queue-observability
Monitor message queues, job processing, and detect backpressure
majiayu000/claude-skill-registry 163
-
council-router
Route code reviews to appropriate council members. Use when reviewing PRs, architecture decisions, or significant code changes that need expert perspective.
majiayu000/claude-skill-registry 163
-
claude-agent-validation
Validates and reviews Claude Code agents against best practices. Checks YAML syntax, naming conventions, description quality, system prompt effectiveness, and tool configuration. Provides improvement suggestions and optionally applies fixes. Use when validating agents, reviewing agent quality, checking agents before commit, or when `--validate-agent` is mentioned.
majiayu000/claude-skill-registry 163
-
td-outlier-detection
Outlier detection and handling using TD_OutlierFit
majiayu000/claude-skill-registry 163
-
connection-management
Redis connection pooling, client configuration, and reconnection strategies. Use when setting up Redis clients, managing connection pools, handling reconnection logic, or configuring sentinel/cluster modes.
majiayu000/claude-skill-registry 163
-
Hono API 编写助手
Hono API 编写助手，基于用户需求创建新的 API，或修改现有 API。
majiayu000/claude-skill-registry 163
-
godot-coding-standards
Godot 4.x GDScript 编码规范。当编写、审查、修改 Godot 代码时使用。适用于：GDScript 脚本、场景创建、组件设计、Resource 类、信号连接、节点组织、类型注解、命名规范、性能优化。触发词：godot, gdscript, 组件, 信号, export, 场景。
majiayu000/claude-skill-registry 163
-
screenshot-feature-extractor
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.
majiayu000/claude-skill-registry 163
-
validate_translation
Validate that a translation is acceptable by checking placeholder preservation, length, encoding, and common errors. Use when reviewing translations or validating i18n file updates.
majiayu000/claude-skill-registry 163
-
cache-guard
Monitor Laravel configuration file changes and automatically manage caches. Use immediately after .env modifications, config file edits, or when user reports "settings not reflecting" or "changes not applied". Prevents stale configuration issues.
majiayu000/claude-skill-registry 163
-
communication-guidelines
Use when starting work - guidelines for asking questions and commit policies
majiayu000/claude-skill-registry 163
-
linear-algebra-expert
Expert in vector spaces, matrices, linear transformations, eigenvalues, and applications to data science and machine learning
majiayu000/claude-skill-registry 163
-
ispc-lit-tests
Best practices for creating ISPC lit tests. Use when writing regression tests, verifying code generation, or checking compiler diagnostics.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
usage-rules-elixir
Elixir Core Usage Rules
majiayu000/claude-skill-registry 163
-
transcript-condenser
Condenses Claude Code session transcripts into readable summaries by filtering metadata, system notifications, and command artifacts. Use when the user wants to review, analyze, or understand what happened in a Claude Code session, view tool usage patterns, or export session data. Triggers when user mentions "analyze session", "review transcript", "condense logs", "what tools did I use", or similar workflow analysis requests.
majiayu000/claude-skill-registry 163
-
flaky-test-prevention
フレーキー（不安定）なテストを検出・修正するスキル。非決定性の排除、リトライロジック、テスト安定性向上パターンを提供。並列実行時の問題解決やタイミング依存の除去を支援。
Anchors:
• Test-Driven Development（Kent Beck） / 適用: Red-Green-Refactor / 目的: 安定したテスト設計
• xUnit Test Patterns（Gerard Meszaros） / 適用: テストダブル / 目的: 非決定性の隔離
• Continuous Delivery（Jez Humble） / 適用: パイプライン信頼性 / 目的: CI/CDの安定化
Trigger:
Use when tests fail intermittently, detecting flaky tests, eliminating non-determinism in tests, fixing timing-dependent failures, or stabilizing CI/CD pipelines.
majiayu000/claude-skill-registry 163