qwen-qwen3Qwen Qwen3 — run Qwen3.5, Qwen3, Qwen3-Coder, Qwen2.5-Coder, and Qwen3-ASR across your local fleet. LLM inference, code generation, and speech-to-text from A...
Install via ClawdBot CLI:
clawdbot install twinsgeeks/qwen-qwen3Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:11435/dashboard/api/settingsCalls external URL not in known-safe list
https://github.com/geeks-accelerator/ollama-herdAI Analysis
The skill orchestrates local model inference via Ollama Herd, and the flagged external calls are to the local router's dashboard API for configuration and the project's public GitHub repository for setup, which align with its stated purpose. No evidence of credential harvesting, data exfiltration to unauthorized servers, hidden instructions, or obfuscation was found.
Audited Apr 16, 2026 · audit v1.0
Generated May 6, 2026
Use Qwen3-Coder within a local fleet to generate, review, and refactor code without sending proprietary data to external APIs. Ideal for financial services or healthcare organizations with strict data residency requirements.
Deploy Qwen3-ASR across a fleet of Macs to transcribe meetings and conference calls locally in real time, enabling searchable archives and compliance monitoring without cloud dependency.
Run a Qwen3.5-based chatbot on local hardware for customer support in remote locations or air-gapped environments, providing contextual answers without internet access.
Utilize Qwen2.5's multilingual capabilities to moderate user-generated content across multiple languages locally, ensuring privacy and low-latency responses for social platforms.
A university fleet runs Qwen3.5 and Qwen3-Coder models on lab machines to provide students with free, unlimited access to AI-assisted learning and coding help, routing requests to the best available device.
Sell pre-configured Mac Mini or Mac Studio fleets with the Ollama Herd software, offering a subscription for model updates and priority support. Revenue comes from hardware markup and monthly subscription fees.
Provide a turnkey service where you deploy and manage the fleet for clients, handling updates, monitoring, and scaling. Clients pay a monthly fee based on number of devices and usage.
Offer a commercial API endpoint that routes to a locally hosted fleet, charging per token or per request while claiming zero data leakage. This targets businesses that want privacy but don't want to manage hardware.
💬 Integration Tip
Start by installing Ollama Herd on a single machine and test with a small Qwen model, then scale to multiple nodes for load distribution.
Scored May 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.