Agent Architecture Audit
affaan-m/eccEvery AI agent has a hidden stack of layers. Problems like wrapper regression and memory pollution can quietly break your application. This agent architecture audit checks all 12 layers and produces severity-ranked fixes.
You get clear results when the model works in a playground but fails inside your code. The audit finds tool discipline failures, hidden repair loops, and rendering corruption. If your agent seems to get worse over time, this diagnostic reveals the root cause.
Developers building agent applications, autonomous loops, or LLM-powered features will benefit. The skill uses code-first fixes that are easy to apply. No more guessing where the problem lives.
Add Agent Architecture Audit skill to your workflow
Global
mkdir -p ~/.claude/skills/agent-architecture-auditProject
mkdir -p .claude/skills/agent-architecture-auditSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly