ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
mhintz1980/ptl-lova
-
tool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
mhintz1980/ptl-lova
-
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
mhintz1980/ptl-lova
-
context-compression
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
mhintz1980/ptl-lova
-
context-fundamentals
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
mhintz1980/ptl-lova
-
context-degradation
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
mhintz1980/ptl-lova
-
context-optimization
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
mhintz1980/ptl-lova
-
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
mhintz1980/ptl-lova
-
evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
mhintz1980/ptl-lova
-
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
mhintz1980/ptl-lova
-
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
mhintz1980/ptl-lova
-
supabase-storage
Manage file storage operations in Supabase Storage. Use for uploading, downloading, listing, and deleting files in buckets.
mhintz1980/ptl-lova
-
supabase-realtime
Subscribe to realtime changes in Supabase using WebSocket connections. Use for listening to database changes, presence tracking, and broadcast messaging.
mhintz1980/ptl-lova
-
supabase-edge-functions
Deploy and manage Supabase Edge Functions. Use for invoking serverless functions, deploying new functions, and managing function deployments.
mhintz1980/ptl-lova
-
supabase-database
Perform database operations (CRUD) on Supabase tables using the REST API. Use for querying, inserting, updating, and deleting data in your Supabase database.
mhintz1980/ptl-lova
-
supabase-auth
Manage authentication and user operations in Supabase. Use for sign up, sign in, sign out, password resets, and user management.
mhintz1980/ptl-lova
-
search-and-fetch
通用网页搜索与内容提取技能。多源并行搜索（WebSearch、MCP 搜索工具、ctx7、agent-browser）、网页正文提取（crwl）与结构化文章分析。当用户需要搜索信息、研究主题、查找资料、获取网页内容、阅读文章、分析网页时使用。触发场景包括：搜索、研究、调研、fetch、查一下、帮我找、读这个链接、分析这篇文章。即使用户没有明确说"搜索"，只要涉及信息获取和网页内容处理都应触发此技能。
zhuxining/AgentOS
-
obsidian-knowledge
指导 Agent 助理如何在共享的 MyObsidian vault 中进行知识管理。当需要创建、整理、检索笔记，维护每日笔记，管理 _AgentSpace 知识库，或将已提取的网页内容保存到知识库时使用。触发关键词：记录、笔记、整理、归档、每日、任务、保存到知识库、知识、术语、记下来、记住、审计知识库。
zhuxining/AgentOS
-
news
新闻聚合与资讯获取技能。根据预配置的信息源，调用 search-and-fetch 抓取最新新闻并输出结构化摘要。当用户需要获取新闻简报、了解某个话题的最新动态、查看特定媒体的最新内容时触发。触发场景：今日新闻、新闻简报、资讯、briefing、最新动态、看看 X 今天有什么、帮我追踪、日报、早报、晚报。即使用户没说"新闻"，只要涉及获取最新信息、行业动态、热点追踪都应触发此技能。
zhuxining/AgentOS
-
memory
zhuxining/AgentOS
-
macos-screenshot
macOS 截屏技能。当需要截取屏幕截图时使用。触发词：截屏、截图、screenshot。
zhuxining/AgentOS
-
signalwire
Use when building telephony, messaging, or video applications; implementing voice AI agents; working with SWML call flows; debugging webhook callbacks or call state issues; setting up real-time WebSocket communication; encountering authentication 401/403 errors; or troubleshooting SWAIG function errors - provides REST API patterns, SDK examples, and production-tested workflows for modern SignalWire communication systems
signalwire/signalwire-claude 6
-
legacy-migration
This skill should be used when migrating features from src.legacy/ to the new kernel implementation or removing legacy code after reaching feature parity. Use for systematic legacy code removal, updating FEATURE_COMPARISON.md, verifying feature equivalence, and ensuring safe code retirement.
ryanbreen/breenix 7
-
kernel-debug-loop
This skill should be used when performing fast iterative kernel debugging, running time-bound kernel sessions to detect specific log signals or test kernel behavior. Use for rapid feedback cycles during kernel development, boot sequence analysis, or feature verification.
ryanbreen/breenix 7