alirezarezvani/claude-skills
Claude Skills
This project is a framework for integrating modular instruction packages and domain-specific tools into large language model agents. It provides a system for managing agent context and extending coding assistants through a modular prompt library of persona-based instruction sets and skill trees.
The framework distinguishes itself through a persistent memory layer that tracks architectural decisions and infrastructure patterns to prevent regressions during autonomous code modifications. It includes an orchestrator for managing multi-agent swarms and autonomous coding loops that cycle through generation, validation, and refinement.
The system further covers automated software engineering capabilities, including the generation of technical scaffolds and the synchronization of skill directories via filesystem symlinks. It provides utilities for prompt migration across model versions, skill security auditing to prevent command injection, and project metric analysis for scoring technical debt.
Features
- AI Agent Orchestrators - Provides a central orchestrator to manage groups of AI agents collaborating on complex multi-step workflows.
- Agent Context Management - Implements a persistent memory layer to track architectural decisions and infrastructure patterns to prevent regressions.
- Automated Software Engineering Agents - Uses AI agents to generate technical scaffolds and execute iterative coding loops for software projects.
- Agentic Workflow Orchestration - Coordinates multi-agent systems and swarms to execute complex engineering tasks without creating technical debt.
- Multi-Agent Coordination Systems - Provides a coordinator for managing parallel AI agent swarms to perform collaborative tasks.
- Agent Skill Frameworks - Provides a framework for integrating modular instruction packages and domain-specific tools into LLM agents.
- Agentic Context Management - Implements a persistent memory layer for tracking architectural decisions and infrastructure patterns.
- Agent Capability Extensions - Provides a framework for extending agent capabilities through modular instruction packages and domain-specific plugins.
- Agent Persona Definitions - Allows the configuration of specialized professional roles using specific system prompts and behavioral constraints.
- Domain Expertise Packages - Enables the installation of modular instruction packages tailored for roles like engineering, product management, and finance.
- Persistence Layers - Maintains a persistence layer to track architectural decisions and patterns across autonomous coding sessions.
- Agentic Workflow Construction - Implements a system for constructing automated multi-step sequences to execute complex engineering tasks.
- AI Agent Integrations - Integrates modular instruction packages and tools into AI agents across multiple platforms.
- AI Knowledge Management - Maintains persistent architectural memory and syncs skill directories to prevent regressions in autonomous updates.
- Instruction Set Packaging - Organizes domain expertise into portable file sets that can be dynamically loaded into agent system prompts.
- Validation Cycles - Implements a cycle of code generation, test execution, and iterative fixing until technical criteria are met.
- Multi-Agent Systems - Coordinates groups of specialized AI agents to complete complex software engineering tasks.
- Persona Instruction Sets - Offers a library of persona-based instruction sets and skill trees to direct model reasoning.
- Instruction Packages - Creates and distributes reusable instruction packages to provide agents with professional personas and domain expertise.
- Agentic Workflow Automations - Manages interactions between multiple AI agents to prevent message loops and resource exhaustion.
- Autonomous Coding Agents - Orchestrates an iterative loop of writing, testing, and committing code until a feature is complete.
- Skill Synchronizers - Automates the installation and synchronization of skill directories and symlinks into local configurations.
- Reasoning Effort Budgets - Directs the depth of model thinking and effort levels via prompts to optimize performance for complex tasks.
- Agentic Workflow Automation - Sequences complex engineering tasks through a dedicated extension bridging the agent and the local environment.
- Technical Research Agents - Analyzes search results to draft and verify technical articles using source-linked claims.
- AI Coding Assistants - Extends coding assistants by automating execution-validation loops and generating technical scaffolds.
- Automated Codebase Maintenance - Enables automated modification of shared code through an autonomous layer that bypasses traditional manual workflows.
- Agent Security Auditing - Scans instruction packages for command injection and data exfiltration risks before installation.
- Scaffolding Generators - Automatically generates technical codebase artifacts including pipelines, servers, and migrations.
- Agent and Skill Libraries - Broad collection of skills spanning multiple development domains.
