Agents

Prompt Skills

by marioluciofjr

Repositório com minhas skills para Claude, Antigravity, Agno, ADK e demais sistemas agênticos

tdd-workflow

by dgalarza

Use this skill whenever you are implementing a feature using TDD.

aisa-twitter-api

by AIsa-team

'Twitter/X research, monitoring, watchlists, and OAuth-approved posting through AIsa. Use when: the user needs one flagship Twitter skill for trend tracking, competitor monitoring, timeline analysis, or approved posting without sharing passwords. Supports search, watchlists, relay-based reads, and OAuth-gated text or media posting.'

aisa-youtube-search

by AIsa-team

Search YouTube videos, channels, and playlists through the AIsa YouTube relay with one API key. Use when the user asks for YouTube discovery, query expansion, or pagination without managing Google credentials.

web-search

by AIsa-team

'Search the web using AIsa Scholar Web endpoint. Returns structured web results with titles, URLs, and snippets. Use when: the user needs web search, research, source discovery, or content extraction.'

agents-md-pro

by alexander-danilenko

Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) optimize/condense existing AGENTS.md to reduce token count, (3) update/refresh AGENTS.md to sync with codebase changes, (4) validate AGENTS.md quality and completeness, or (5) improve AGENTS.md files to be more effective for AI agents. Always generates token-efficient, condensed output focused on actionable commands and patterns while maintaining model-agnostic language.

agent-browser

by pacphi

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

ralph

by kv0906

Set up and run Ralph Wiggum loop - autonomous AI coding with clean slate iterations, PRD-driven features, and CI quality gates. Use for long-running autonomous coding tasks.

root-cause-analysis

by kopai-app

Analyze telemetry data for root cause analysis using Kopai CLI. Use when debugging errors, investigating latency issues, tracing request flows across services, or correlating logs with traces.

multi-lang-readme-cn

by YangsonHung

创建多语言 README。用于用户要求“中英 README”“多语言 README”“把 README 翻译成某语言”等场景。支持英文、德语、日语、韩语、中文，并保持 Markdown 结构与链接一致。

novel-writer-cn

by YangsonHung

小说创作助手，支持从零开始创作小说、续写章节、角色设计、世界观构建等。适用于各种类型（科幻、奇幻、悬疑、言情、武侠等）。触发场景：(1) 用户请求写小说，如"帮我写一部科幻小说"、"创作一个推理故事"； (2) 续写或修改现有内容，如"给这个故事续写一章"、"修改这个角色"； (3) 角色相关任务，如"帮我设计一个反派角色"、"给主角设计一个恋爱对象"； (4) 世界观构建，如"帮我设计一个魔法体系"、"构建一个赛博朋克世界"。

building-ai-agent-on-cloudflare

by hainamchung

Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling".

azure-ai-agents-python

by hainamchung

Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP), managing threads and messages, implementing streaming responses, or working with vector stores. This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead.

Agent Framework Azure Hosted Agents

by hainamchung

autonomous-agents

by hainamchung

"Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b"

geo-infer-sim

by ActiveInferenceInstitute

Agent-based simulation for geospatial environments. Use when building spatial simulations, modeling agent interactions in geographic space, running Monte Carlo spatial experiments, or comparing spatial planning scenarios.

geo-infer-log

by ActiveInferenceInstitute

Logistics optimization including route planning, fleet management, delivery scheduling, and supply chain modeling. Use when optimizing delivery routes, managing fleets, analyzing supply chain resilience, or computing emissions from transportation.

business-logic

by florianbuetow

This skill should be used when the user asks to "check business logic security", "find logic flaws", "audit workflow security", "check for coupon abuse", "detect negative amount exploits", "analyze state machine security", or mentions "business logic", "workflow bypass", "negative amount", "coupon abuse", "self-referral", "state manipulation", or "time-based exploit" in a security context.

geo-infer-econ

by ActiveInferenceInstitute

Geospatial economics and bioregional market modeling. Use when analyzing spatial economic patterns, bioregional markets, location-based pricing, call auctions, or supply-demand modeling with geographic context.

geo-infer-agent

by ActiveInferenceInstitute

Multi-agent geospatial systems with Active Inference. Use when building spatial agents, implementing perception-action loops, managing agent telemetry, or coordinating multi-agent spatial exploration.

burner-phone

by SouthpawIN

Control Android devices via ADB with vision feedback. Use this to see the screen, take screenshots, analyze UI elements, and automate phone tasks.

claudish-usage

by MadAppGang

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

agent-browser

by itechmeat

"Headless browser automation CLI for AI agents. Covers commands, refs, sessions, snapshots, cloud providers, profiles. Keywords: agent-browser, browser automation, refs, snapshot."

pydantic-ai

by itechmeat

"Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Keywords: pydantic-ai, agents, evals, MCP, Logfire."