MCP App StoreMCP App StoreLynkr is a universal LLM proxy that analyzes incoming coding requests, scores their complexity, and routes them to the most appropriate provider and model. It includes token-optimization techniques (Distill compression, history compression) and routing telemetry to reduce costs and improve response quality for developer-facing coding tools.
Use Lynkr when you want to centralize multi-provider model routing for code-assistant workflows (e.g., Claude Code, Cursor, Codex) to lower costs, enforce routing policies, or gain telemetry on model choices and latencies. Ideal for teams running hybrid/local/cloud models.
lynkr-setup, and environment variables to map tiers to providers. The skill documents provider compatibility and telemetry endpoints.Suitable for agents and systems that can configure HTTP proxies and environment variables, and for tooling that integrates with Claude/Codex/Cursor developer flows. Compatible with Copilot/Codex-style automation and platform-level routing setups.
Lynkr is an LLM routing proxy that directs coding requests to optimal providers based on complexity scoring. SKILL.md is thorough with clear configuration examples and feature documentation. No bundled scripts were present for runtime testing. Telemetry and admin endpoints are exposed but documented; no malicious patterns detected.
No scripts bundled with this skill, so scoring is based purely on static analysis of SKILL.md. The skill describes a legitimate LLM proxy product. Telemetry endpoints are for local monitoring, not external phone-home. No curl|bash patterns, no hardcoded credentials, no destructive commands.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Monad Development
Practical developer skill for deploying and verifying smart contracts, configuring Foundry projects, and integrating frontends (viem/wagmi) on the Monad blockch
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Uloop: Execute Dynamic Code
Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat