ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
analyzing-protocols
Analyzes network protocol implementations to identify parsing vulnerabilities, state machine issues, and protocol-level security problems. Use when analyzing network servers, protocol handlers, or investigating protocol implementation bugs.
majiayu000/claude-skill-registry 163
-
Ruby OOP Patterns
Comprehensive guide to Object-Oriented Programming in Ruby and Rails covering classes, modules, design patterns, SOLID principles, and modern Ruby 3.x features
majiayu000/claude-skill-registry 163
-
docs-components
Comprehensive MDX component patterns (Note, Pitfall, DeepDive, Recipes, etc.) for all documentation types. Authoritative source for component usage, examples, and heading conventions.
majiayu000/claude-skill-registry 163
-
cui-http
CUI HTTP client standards with HttpHandler, HttpResult pattern, and async-first adapters
majiayu000/claude-skill-registry 163
-
kotlin-patterns
Kotlin/Spring Boot patterns for Orca service - use when implementing backend features, writing services, repositories, or controllers
majiayu000/claude-skill-registry 163
-
validating-api-contracts
Validate API contracts using consumer-driven contract testing (Pact, Spring Cloud Contract).
Use when performing specialized testing.
Trigger with phrases like "validate API contract", "run contract tests", or "check consumer contracts".
majiayu000/claude-skill-registry 163
-
pr-review-loop
Manage the PR review feedback loop: monitor CI checks, fetch review comments, and iterate on fixes.
Use when: (1) pushing changes to a PR and waiting for CI/reviews, (2) user says "new reviews available",
(3) iterating on PR feedback from Gemini, Cursor, Claude, or other reviewers, (4) monitoring PR status.
Supports multiple review bots: Gemini Code Assist, Cursor Bugbot, and Claude agent fallback.
Automatically detects priority levels from different bot formats and handles rate limits.
RECOMMENDED: Spawn a Task agent (subagent_type: general-purpose) to execute the review loop autonomously.
See "Recommended Usage: Run as Task Agent" section for the prompt template.
CRITICAL: When using this skill, NEVER use raw git commit/push commands. ALWAYS use commit-and-push.sh script.
The user has NOT granted permission for raw git commands - only the script is allowed.
majiayu000/claude-skill-registry 163
-
managing-optimistic-ui
Implements "Fast Sync" using the useOptimistic hook. Use when you want to provide instant feedback for user actions like booking or liking while the backend processes.
majiayu000/claude-skill-registry 163
-
ansible-dev-setup
Generate and manage cross-platform Ansible playbooks for development environment setup across macOS, Linux, and Termux. Use when working with development environment automation, package installation configuration, or Ansible playbook generation.
majiayu000/claude-skill-registry 163
-
41-chatkit-server
Create your ChatKit Server skill in one prompt, then learn to improve it throughout the chapter
majiayu000/claude-skill-registry 163
-
hypothesis-driven
This skill should be used when refining hypotheses, checking testability, improving specificity, or designing verification strategies. Triggered by requests like "refine hypothesis", "validate hypothesis", "check if testable", or "improve this hypothesis". Used AFTER experiments to refine hypotheses based on results.
majiayu000/claude-skill-registry 163
-
langgraph-agents
Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI).
majiayu000/claude-skill-registry 163
-
unslopify
Tactical code cleanup focusing on type strictness, single responsibility, fail-fast patterns, and DRY. Detects sloppy code, workarounds, silent failures, god classes, and duplication. Use for quick code quality checks before committing or during code review.
majiayu000/claude-skill-registry 163
-
setperms
Set tool permissions for Claude Code. Configures allowed commands, rules, and preferences in .claude/ directory. Triggers on: setperms, init tools, configure permissions, setup project, set permissions, init claude.
majiayu000/claude-skill-registry 163
-
mcp-server-troubleshooting
Diagnoses and resolves common Model Context Protocol (MCP) server connection issues with OpenAI Agents SDK
majiayu000/claude-skill-registry 163
-
implement-feature
Implement an approved feature file using ATDD workflow with test-first development
majiayu000/claude-skill-registry 163
-
erpnext-impl-customapp
Implementation workflows for building Frappe/ERPNext custom apps. Covers app structure, module creation, doctype design, fixtures, patches, and deployment. V14/V15/V16 compatible. Triggers: create custom app, new frappe app, bench new-app, app structure, module creation, doctype creation, fixtures, patches.
majiayu000/claude-skill-registry 163
-
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
majiayu000/claude-skill-registry 163
-
openspec-change-implementation
Implements L0-1 changes from proposals.
majiayu000/claude-skill-registry 163
-
module-scaffolding
Module scaffolding using Yeoman generator including validation and sync-meta
majiayu000/claude-skill-registry 163
-
update-workspace-map
Validate workspace-map.md accuracy against actual 04-workspace/ structure (3 levels deep). Load when user says "validate workspace map", "update workspace map", "check workspace map", or from close-session. Ensures deep structure validation with comprehensive documentation.
majiayu000/claude-skill-registry 163
-
anthropic-office-pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
majiayu000/claude-skill-registry 163
-
ui-spec
majiayu000/claude-skill-registry 163
-
ragas-skill
RAGAS를 사용하여 LLM 애플리케이션을 체계적으로 평가하는 방법을 제공합니다.
majiayu000/claude-skill-registry 163