MCP App StoreMCP App Store
from buildwithclaude3,150
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business,...
Convene a meeting of AI personas (3 to 10 participants) who debate a subject and reach a synthesis. Teams adapt to the theme (dev, design, product, business, life). The user can mix teams, add custom personas on the fly, and size the meeting up or down. Full debate written to a markdown file in the current directory, only the Boss's final synthesis is shown in the console.
Describe scenarios where this skill is useful.
A well-crafted prompt-only skill that orchestrates multi-agent debates on any topic. No bundled scripts — the skill works entirely through SKILL.md instructions for agent spawning, file writing, and console output management. The 8-step workflow (team selection, lineup customization, 3 debate rounds, Boss synthesis, pushback loop) is thorough and clearly documented. Shell commands use properly quoted heredocs to prevent interpolation. No security concerns detected.
Pure prompt skill with no scripts. Exceptionally detailed SKILL.md with clear step-by-step instructions, argument parsing, output discipline rules, and example invocations. The heredoc usage with quoted delimiters is a good security practice. Architecture could benefit from extracting persona definitions into a references/ directory for maintainability.
Content Research Writer
A writing partner skill that helps outline, research, draft, cite, and iteratively improve articles, tutorials, and technical content while preserving the autho
macOS Native App Design
Design and build native-feeling macOS application UIs: layouts, traffic-light chrome, light/dark themes, keyboard shortcuts, drag-and-drop, and micro-interactio
OPS — Next Action
Prioritises operational work across fires, unread comms, ready-to-merge PRs, sprint issues, and revenue-impact GSD tasks to recommend the next action.
OPS — Business Command Center
Route natural-language ops requests to specialized operational skills: briefing, inbox, incidents, projects, deploys, monitoring, and more.
Fix
Get fix intelligence for a vulnerability and propose concrete remediation for the current repository
SocialClaw Social Publishing
Omnichannel social media scheduling and publishing for AI agents across X, LinkedIn, Instagram, Facebook, TikTok, and more.
Vulnetix Exploit Search
Discover vulnerabilities with known exploits across VDB with advanced filtering by ecosystem, severity, and EPSS score.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Unitree Robot Controller
Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c