Generate comprehensive GitHub ecosystem configuration including CI/CD workflows, issue templates, PR templates, CODEOWNERS, dependabot, and Copilot instructions. Language-agnostic with Python, Go,...
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user...
Setup instructions and required secrets
# Liberty House Club **A Parallel Binance Chain to Enable Smart Contracts** _NOTE: This document is under development. Please check regularly for updates!_ ## Table of Contents -...
Exports project instructions and knowledge files from the current Claude project. Use when users want to clone, copy, backup, or export a project's configuration and files.
Synthesize structured directives and command specifications. Creates executable instruction sets with proper syntax and parameter definitions.
Create AGENTS.md files for project-specific inline rules. Use when adding small, project-specific instructions that should be committed in repos.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Search recipes by ingredients, cuisine, or dietary needs. Get nutrition info, meal plans, and cooking instructions. Use when user asks about cooking, recipes, meals, or food.
Implement the complete spec-driven development workflow from instructions through requirements, design, and implementation planning. Use this skill when starting new features or major refactorings...
Migrate existing repositories with provider-specific files (.claude, .cursor, etc.) to OmniDev's unified approach. Consolidates instructions, converts skills/commands to capabilities, and...
Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up...
Creates and reviews CLAUDE.md configuration files for Claude Code. Applies HumanLayer guidelines including instruction budgets (~50 user-level, ~100 project-level), WHAT/WHY/HOW framework, and...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
Validates output-style persona definitions, behavior specifications, and keep-coding-instructions decisions. Use when auditing, reviewing, or improving output-styles, checking persona clarity,...
Set up a complete book writing workspace with AI agents, instructions, prompts, and scripts. Use when users want to create a new book/technical writing project with Markdown + Re:VIEW + PDF output...