local-codingLocal coding assistant — run DeepSeek-Coder, Codestral, StarCoder, and Qwen-Coder across your device fleet. Code generation, review, refactoring, and debuggi...
Install via ClawdBot CLI:
clawdbot install twinsgeeks/local-codingGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/geeks-accelerator/ollama-herdAudited Apr 18, 2026 · audit v1.0
Generated May 6, 2026
Integrate the local coding assistant into CI/CD pipelines to automatically review pull requests for bugs, security issues, and style adherence. Code never leaves the corporate network, ensuring compliance with data sovereignty policies.
Use DeepSeek-Coder-V2 to refactor monolithic legacy codebases into modern, maintainable architectures. The fleet's routing selects the most powerful machine for large-scale refactoring tasks.
Developers working on classified or proprietary projects use Continue.dev or Aider pointed at the local fleet for real-time code generation and debugging without sending data to external APIs.
A global development team shares a fleet of machines across offices, each running herd-node. Requests are intelligently routed to the best available machine, enabling consistent code quality without cloud costs.
Data scientists and engineers compare outputs from Codestral, Qwen2.5-Coder, and StarCoder2 for specific coding tasks to select the best model for their use case, all within a local environment.
Offer a monthly subscription for enterprises to get pre-configured fleet management software, automatic updates, and priority support for deploying local coding assistants across their hardware.
Partner with hardware vendors to sell workstations and servers pre-loaded with the fleet software and optimized coding models, providing a turnkey solution for secure code development.
Provide consulting services to customize the fleet for specific industries, integrate with existing CI/CD and project management tools, and train teams on optimal model selection.
💬 Integration Tip
Start by running `herd` on one powerful machine and point your IDE tools (Aider, Continue.dev, Cline) to http://localhost:11435/v1. Then add herd-node on other machines to expand compute resources incrementally.
Scored May 6, 2026
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
This skill should be used ONLY when the user EXPLICITLY and UNAMBIGUOUSLY requests a Git repository commit-history analysis that produces aggregate collabora...
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent executi...
Best practices for Remotion - Video creation in React