575 boosters for "all" — open source, verified from GitHub, ready to install
NexA4A is a meta-agent system prompt that creates specialized AI agents from natural language requirements, enabling product managers and developers to automate task creation and management across multiple coding platforms.
A mandatory human escalation agent that intercepts all errors and uncertainties across other agents to ensure human oversight. Useful for safety-critical workflows requiring explicit human approval before proceeding.
"description": "Cotask — task management with TASKS.md kanban dashboard", "homepage": "https://github.com/wbopan/cotask", "repository": "https://github.com/wbopan/cotask",
A system prompt that transforms Claude into 'Madsa', a data science assistant that converts natural language requests into concise, executable Python code for pandas DataFrame analysis. Ideal for data scientists and analysts using Claude-based IDEs who want rapid, code-first answers to data manipulation and exploration tasks.
Enables Claude to maintain long-term memory across sessions, automatically recalling user context, preferences, and prior work to provide continuous, personalized assistance. Essential for developers who need stateful AI interactions across multiple conversations.
You are the STUCK AGENT - the MANDATORY human escalation point for the entire system. You are the ONLY agent authorized to use AskUserQuestion. When ANY other agent encounters ANY problem, they MUST invoke you. You are invoked when:
Reference documentation for Prismatic platform operations and the standardized API access hierarchy. Prismatic API access follows a two-tier priority system for interactive agents (e.g., Orby). Builder agents (cni-builder, component-builder) use their own script-based pipelines and should not use MC
You are capturing this session's repeatable process as a reusable skill. You have the full conversation history available to you. Analyze it directly to understand what process was performed, what tools were used, and how the user steered you. If a description was provided: The user described this p
"name": "wordpress-expert", "description": "Expert WordPress diagnostics and site builder: structured investigations with intake questioning, site reconnaissance, parallel execution, findings verification, WordPress site generation as Local WP importable zips, and interactive modification sessions."
A Claude agent designed to help developers tackle coding challenges and agent-related tasks across Claude Code and Claude Desktop environments. Useful for developers building agents who need structured assistance with problem-solving.
A resource-allocator agent for optimizing task distribution and resource management across agent-based workflows in Claude environments. Benefits operations teams and developers building multi-agent systems.
Skill Issue audits installed agent skills to provide health reports including inventory, usage tracking, version checks, and actionable recommendations. Essential for agents managing multiple skills who need visibility into ecosystem health and dependency status.
Advanced security research skill for web servers, REST APIs, web applications, and network infrastructure. Designed for experienced users who want structured, tool-driven Claude's role is to interpret tool output, suggest next steps, and document findings.
A prompt-based ruleset for Cursor that applies negation and critical thinking techniques to enhance argumentation and collective decision-making. Useful for teams seeking to improve sense-making and governance processes through structured debate frameworks.
"name": "cc-godmode", "description": "Self-orchestrating multi-agent development system — 8 specialized AI agents, parallel quality gates, and automated workflows. You say WHAT, the AI decides HOW.", "name": "Dennis Westermann",
Teaches the functional options pattern for designing flexible Go APIs with optional configuration, helping developers build clean, extensible constructors that scale as requirements grow.
"name": "quantum-loop", "description": "Universal CLI orchestrator with multi-runner support. Autonomous spec-driven development with dependency DAG, parallel worktree execution, two-stage review gates, and modular merge hardening.", "name": "andyzengmath"
An adversarial validation agent that challenges expertise claims and mental models to prevent overconfident reasoning. Useful for researchers, engineers, and decision-makers who need rigorous validation of their assumptions.
Generate professional, high-converting email copy using proven copywriting frameworks. Produces subject line variants with scoring, responsive HTML templates with dark mode support, plain-text fallback, and preheader recommendations. This sub-skill is invoked by the main skill when the user needs t
Enables Claude to delegate code review, debugging, and alternative implementation exploration to Google Gemini CLI through a JSON bridge script. Useful for developers who want multi-model validation and second opinions on code without manual context switching.
"source": "./plugin", "description": "qrec session recall engine",
"description": "Recover conversation context when Claude loses track, with interactive browsing and observability logging",
ADHARA is an LLM system prompt that enables early detection of learning friction by analyzing behavioral metrics like mouse hesitation, attention, and task performance against age-appropriate baselines. It helps educators identify students who may need additional support before academic failure occurs.
"name": "claude-memory", "description": "Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.", "name": "Valentino Stoll",
