Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ai-context-kit
SkillsAI Context Kit provides a structured, instruction-based framework for context-aware AI collaboration across LLM providers. It includes authoritative specs, canonical templates, and skills workflows for creating and validating user context and project AGENTS.md files.
git clone https://github.com/MSiccDev/ai-context-kit.git -
agents-inc
SkillsAn agent composition framework that builds stacks and compiles specialized subagents for Claude Code
git clone https://github.com/agents-inc/agents-inc.git -
Backend Architect
Prompts--- name: backend-architect description: "Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems. This agent specializes in creating robust…
-
DevOps Automator
Prompts--- name: devops-automator description: "Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating deployment processes. This agent specializes in…
-
Frontend Developer Agent Role
Prompts# Frontend Developer You are a senior frontend expert and specialist in modern JavaScript frameworks, responsive design, state management, performance optimization, and accessible user interface implementation. ##…
-
code-review
SkillsReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
-
Subscriptions
Public APIsSubscriptions allow contacts to control what forms of communications they receive. Contacts can decide whether they want to receive communication pertaining to a specific topic, brand, or an entire HubSpot account.
-
Lifestyle Product Images
PromptsUsing the uploaded product image of ${Product Name:MacBook Pro}, create an engaging lifestyle scene showing realistic usage in ${Lifestyle Scenario:Office}. Target visuals specifically for ${Audience…
-
Sprint Prioritizer
Prompts--- name: sprint-prioritizer description: "Use this agent when planning 6-day development cycles, prioritizing features, managing product roadmaps, or making trade-off decisions. This agent specializes in maximizing…
-
Update Agent Permissions
Prompts# Task: Update Agent Permissions Please analyse our entire conversation and identify all specific commands used. Update permissions for both Claude Code and Gemini CLI. ## Reference Files - Claude…
-
System Architect Agent Role
Prompts# System Architect You are a senior software architecture expert and specialist in system design, architectural patterns, microservices decomposition, domain-driven design, distributed systems resilience, and…
-
Backend Architect Agent Role
Prompts# Backend Architect You are a senior backend engineering expert and specialist in designing scalable, secure, and maintainable server-side systems spanning microservices, monoliths, serverless architectures, API…
-
# Agent Profile: Packer Automation & Imaging Expert This document defines the persona, scope, and technical standards for an agent specializing in **HashiCorp Packer**, **Unattended OS Installations**, and…
-
A site's electricity, gas, solar or EV charging, specified the way suppliers and installers price.
-
Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.
git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite.git -
agentchef
SkillsAn unofficial, cross-platform setup kit for OpenAI Codex CLI and Anthropic Claude Code: specialist agents, curated skills, safe MCP defaults, preview-first installation, and clear verification.
git clone https://github.com/ucsahinn/agentchef.git -
agents-context-router
Skills🧭 Keep AGENTS.md lean. Route coding agents to task-specific docs with byte budgets and integrity checks.
git clone https://github.com/runkids/agents-context-router.git -
agentic-robotics
MCP serversThe goal of this project is to create a modular Agentic Python framework for robotics that can be used to develop specific robotic applications for various types of robots, IoT, and physical devices. The initial focus will be on the hospitality sector, with a longer-term focus on transitioning to consumer usage such as household tasks.
git clone https://github.com/ruvnet/agentic-robotics.git -
SlashForge
SkillsWorkflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.
git clone https://github.com/rajdeepratan/SlashForge.git -
openapi
SkillsPachca API platform: MCP server and plugin for AI agents (Claude Code, Codex, VS Code, Cursor) with skills and commands, OpenAPI spec, CLI, SDKs (TypeScript, Python, Go, Kotlin, Swift, C#) and n8n node
git clone https://github.com/pachca/openapi.git -
Cloud Deployment Manager V2 API
Public APIsThe Google Cloud Deployment Manager v2 API provides services for configuring, deploying, and viewing Google Cloud services and APIs via templates which specify deployments of Cloud resources.
-
Cloud Video Intelligence API
Public APIsDetects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.
-
Interzoid Global Page Load Performance API
Public APIsThis API provides a timed, browser-simulated page load function (or a measured API call) from the specified geography using a server from that geography.
-
UK Parliament Search Service
Public APIsPerforms search on parliament.uk domain. Implements OpenSearch specification (https://github.com/dewitt/opensearch). Throttled at 10 requests per second per IP address.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.