Mathews-Tom/armory

What it solves

armory provides a curated collection of production-grade skills, agents, and workflows for AI coding agents, specifically targeting Claude Code and Claude.ai. It solves the problem of inconsistent or "magical" AI behavior by providing battle-tested, opinionated automation units that define exact inputs, outputs, and failure modes for complex development tasks.

How it works

The project organizes its capabilities into several categories:

• Agents: Orchestrators (like team-lead or project-architect) that manage multi-phase workflows and Analyzers (like code-reviewer or security-reviewer) that perform specific quality checks.
• Skills: Self-contained prompt or automation units for specific domains, such as GitHub operations, GPU optimization, systematic debugging, and architecture diagramming.
• Planning Lifecycle: A structured sequence of packages (from decision-map to stacked-prs) that guides a feature from an unresolved destination to a merged PR stack.
• Model Fit Matrix: A system to validate that the client and model (e.g., Claude Opus) are correctly configured for the required effort levels and telemetry.

Who it’s for

Developers who use AI coding agents as a serious, integrated part of their professional software development workflow and require repeatable, high-quality results.

Highlights

• Comprehensive Tooling: Includes everything from codebase auditing and security scanning to academic manuscript review and UX audits.
• Structured Planning: A defined lifecycle for moving from high-level decisions to implementation slices.
• Multi-Model Routing: Explicit routing for different Claude models (Opus, Sonnet, Haiku) based on task complexity.
• Broad Integration: Supports tools like the GitHub CLI, Tavily API, and Lightpanda for headless browser automation.