262 boosters for "ai-agents" — open source, verified from GitHub, ready to install
Implement UVM-based hardware verification testbenches — stimulus generation, scoreboarding, coverage-driven verification, and assertion-based testing.
The Crisis Management Platform skill provides crisis response platform integration and real-time monitoring capabilities. This skill enables rapid crisis detection, coordinated response, and comprehensive documentation throughout crisis situations. This skill integrates with the following PR process
AgentDock Cursor Rules is a framework guide that establishes architectural principles and coding conventions for building AI agents using TypeScript in Cursor. It benefits developers creating complex, configurable AI-powered applications who need clear structure and best practices.
"name": "actionbook", "description": "Actionbook MCP server for up-to-date browser automation. Get verified CSS/XPath selectors for any website directly into your agent context.", "name": "Actionbook"
Heuristic scoring (no AI key configured).
A skill that automates backlog grooming operations for enterprise workflows, helping development teams organize and prioritize work items efficiently.
Automates Vercel SDK upgrades with breaking change detection and migration planning, helping developers safely update their dependencies and identify deprecations.
"description": "Cloud-backed persistent memory powered by Deeplake — read, write, and share memory across Claude Code sessions and agents", "version": "0.7.104", "name": "Activeloop",
"name": "memsearch-plugins", "email": "support@zilliz.com" "description": "Semantic memory search plugin for Claude Code — markdown-first, backed by Milvus",
A system prompt that enables AI agents to automate browser tasks by navigating websites, extracting data, and performing interactive actions across multiple AI platforms (Claude, ChatGPT, Cursor, Windsurf). Ideal for developers and AI engineers building autonomous web automation workflows.
template: scoreinteractivesystem_prompt role: system prompt for interactive planning mode vars: hasWorkflowPreview, workflowStructure, stepDetails, hasRunSession, runTask, runWorkflow, runStatus, runStepLogs, runReports
Use this before submission when the empirical story is not yet locked. FSE reviewers are SE empiricists; the evaluation is where a good idea is won or lost. The organizing principle is on subjects and baselines a skeptic would accept.
"name": "home-assistant-manager", "description": "Expert-level Home Assistant configuration management: deploy workflows, SSH/hass-cli access, automation verification, and Lovelace dashboard development", "name": "komal-SkyNET"
TAKT is a system prompt for coordinating multi-agent AI workflows with human intervention checkpoints, enabling developers to define agent orchestration topologies and retry logic in YAML. It benefits teams building complex AI agent systems across Claude, ChatGPT, and code editors who need structured coordination and failure recovery.
A multi-agent framework that dynamically spawns specialized agents (frontend, backend, DevOps, etc.) to autonomously handle software development tasks across platforms like Claude and OpenAI. Developers building complex applications benefit from delegating work to a coordinated swarm of AI agents that each handle domain-specific responsibilities.
"description": "Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved c
"description": "Agent orchestration harness for Claude Code — campaign persistence, fleet coordination, intent routing", "name": "SethGammon" "homepage": "https://github.com/SethGammon/Citadel",
"name": "antigravity-skills", "description": "Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.", "email": "guanyangsunlight@gmail.com",
Generate getopts-based argument parsing for shell scripts. Invoke this skill when you need to:
Query affiliate program data from openaffiliate.dev in real-time. Persistent daemon with in-memory cache — first call auto-starts the server, every subsequent call is instant. Before using any command, find the skill and check if the binary exists:
The Portfolio Optimization skill applies mathematical optimization techniques to project portfolio selection and balancing. It maximizes portfolio value while respecting budget, resource, and strategic constraints, enabling data-driven investment decisions. 1. Annual Planning: Optimize project selec
Integrate with Open Science Framework (OSF) for project management, preregistration, and open science workflows. 2. Create/select project 4. Set up integrations
This skill provides production-ready operational patterns for designing, building, evaluating, and deploying AI agents. It centralizes procedures, checklists, decision rules, and templates used across RAG agents, tool-using agents, OS agents, and multi-agent systems. No theory. No narrative. Only wh
"description": "AI-native job queue for Bun — skills, MCP server (73 tools), custom agent, SQLite persistence, cron, priorities, retries, DLQ, webhooks", "name": "egeominotti" "homepage": "https://github.com/egeominotti/bunqueue",
