from skillshub29
Run parallel queries across multiple LLMs with a live dashboard to compare outputs, synthesize consensus, and perform anonymous model voting.
LLM Council launches a lightweight web dashboard and API that queries multiple AI models in parallel, streams their responses, and provides synthesis and anonymous voting to surface consensus across models. It includes a small Python server, AI Gateway client code for parallel streaming, and a browser UI for side-by-side comparison and voting.
Use this skill when you need to compare answers from multiple LLM providers, validate model robustness, run ensemble-style synthesis, or perform blind voting between model outputs. It's useful for model evaluation, prompt tuning, and situations where a quick human-orchestrated consensus is needed.
scripts/server.py, scripts/ai_gateway.py, scripts/static/app.js (has dashboard + SSE streaming)Compatible with agents that can run local Python services and open browser ports (Claude/Copilot-style agent runtimes and local CLI agent runners).
This skill has not been reviewed by our automated audit pipeline yet.
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.
Anthropic Security Basics
Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.
Colorize — Strategic UI Color Introduction
Introduce purposeful color to monochromatic interfaces to improve hierarchy, meaning, and visual engagement while preserving accessibility.
Input Validation Checker
Automated guidance and code patterns for implementing robust input validation and secure-coding practices (OWASP-aligned).
Plotly Chart Generator
Generates Plotly charts and production-ready code for visualizations; validates outputs and follows best practices for charts and presentations.
Security Headers Generator
Auto-activating skill that generates and validates security HTTP headers and provides guidance for implementing secure header configurations.
Turborepo Guidance
Practical Turborepo guidance for JavaScript/TypeScript monorepos: task configuration, caching, filtering, and CI best-practices.
Exa Webhooks & Events
Patterns and example code for building webhook-style monitors and alerts around Exa neural search (scheduled monitors, similarity alerts, digests).
Test Orchestrator Skill
QA orchestration skill: defines test strategy, assigns unit/integration/E2E suites, enforces coverage thresholds, and coordinates CI test execution.
Splitwise Automation (Composio/Rube MCP)
Automation patterns for Splitwise via Composio's Splitwise toolkit over Rube MCP; includes discovery, connection checks, and safe execution patterns.
