Agents
AI agents and automation
create-publish-skill
by ffhope
Guides users through creating and publishing agent skills to GitHub. Use when users want to create new skills, publish skills, understand skill structure, set up skill repositories, or ask about skill development workflow. Provides step-by-step instructions for creating SKILL.md files, setting up GitHub repositories, and making skills installable via npx skills add.
langchain-agents
by cuba6112
Building LLM agents with LangChain and LangGraph, covering tool-calling model initialization, state management, and observability with LangSmith. Triggers: langchain, langgraph, langsmith, agent-executor, chat-model-tools.
AI Engineer Agent
by gajakannan
Opinionated AI‑agent development framework with a reference Insurance CRM implementation.
ralpher
by tomrford
Generate Ralph loop scaffolding for autonomous codex workflows. Use when user asks to set up a ralph loop, scaffold ralph, or configure autonomous development.
jujutsu-colocated
by khoaHyh
Safe, practical workflows for using Jujutsu (jj) in colocated repositories (.git + .jj) and parallel-agent environments. Use when planning, editing, splitting, recovering, coordinating, isolating parallel agents with workspaces, or publishing changes with jj, especially when avoiding destructive history/state operations.
ad-launch-package
by tonyflo79
Platform-compliant packaging and delivery preparation for ad campaign launch. Use after pre-launch scoring (A10) is complete and you need to package everything for the media buyer to go live. Launch-ready means COMPLETE — the media buyer can launch without asking a single question. Includes correct platform specs, file naming conventions, folder structure, campaign structure recommendations, and budget allocation suggestions. Trigger when users mention launch package, ad delivery, campaign packaging, preparing ads for launch, media buyer handoff, or getting ads ready to go live. Requires A10 scoring report and all upstream production assets.
SKILL.md
by dance10
escalation_needed: true false
Team Lead
by coco-de
Agent Teams orchestrator for parallel Phase 4 workflows
Ralph (Autonomous Loop)
by anorbert-cmyk
An autonomous agent loop that iteratively plans, executes, and verifies tasks from a PRD or Task list until completion, mimicking the behavior of the Ralph CLI tool.
agent-cost-optimization
by arielperez82
Framework for analyzing agent telemetry data to optimize cost, token usage, and model tier selection. Use when tuning agent configurations, reviewing agent costs, selecting model tiers, or interpreting optimization_insights/cost_by_model/agent_usage_summary pipe outputs.
azure-ai-agent-deploy
by johnmaeda
Deploy prompt-based Azure AI agents from YAML definitions to Azure AI Foundry projects. Use when users want to (1) create and deploy Azure AI agents, (2) set up Azure AI infrastructure, (3) deploy AI models to Azure, or (4) test deployed agents interactively. Handles authentication, RBAC, quotas, and deployment complexities automatically.
reembolsajus-2
by yumiacontato-lab
A brief description of what this skill does
wrap
by keenranger
Pre-commit session analysis for docs and permissions. Use when user is finishing work, about to commit, has completed a significant task, or says /wrap.
compose-ui-control
by forketyfork
Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.
erc8004-avalanche
by Colombia-Blockchain
Register and manage AI agent identities on any EVM chain using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries. Currently deployed on Avalanche (mainnet and Fuji testnet).
verification-before-completion
by Jackiexiao
（中文）Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Routing
by LauraFlorentin
A control flow pattern where a central component classifies an input request and directs it to the most appropriate specialized agent or tool.
letterly-automation
by psycho-baller
Comprehensive automation for Letterly transcriptions. This skill exports the latest CSV from Letterly, processes "magic" notes into Obsidian markdown with custom metadata, semantically links them using a vector database, and moves them to the final Transcriptions directory. Use when the user asks to "process new letterly transcriptions", "sync letterly", or "import magic notes from letterly".
mentor-workflow
by nicolas-codemate
Coaching workflow orchestrator. Guides the developer through implementation without writing code.
agent-browser
by kunhai-88
"浏览器自动化工具，用于网页导航、交互、截图、录制等。当需要自动化浏览器操作、测试网页、抓取网页内容、填写表单、截图、录制视频，或提到「浏览器自动化」「网页测试」「agent-browser」「浏览器操作」时使用。"
preventing-agent-overreach
by chrbailey
Scope guard that prevents AI agents from exceeding task boundaries. Enforces the principle of minimal action -- do exactly what was asked, nothing more. Use when delegating tasks to AI agents, when an agent starts modifying files beyond the original request, or when generated code includes unnecessary abstractions, features, or refactoring.
eve-agent-memory
by Incept5
Choose and combine Eve storage primitives to give agents persistent memory — short-term workspace, medium-term attachments and threads, long-term org docs and filesystem. Use when designing how agents remember, retrieve, and share knowledge.
chain-of-responsibility-go
by progmichaelkibenko
Implements the Chain of Responsibility pattern in Go. Use when the user mentions chain of responsibility, CoR, or when you need to chain handlers that each process and pass to the next—validation pipelines, processing steps, transformation chains, or any sequential pipeline.
agent-social
by teamily-ai
Smart AI agent social matching. Analyze your profile, register to NextMarket platform, and find matched agents based on skills, interests, and goals.