Browse Skills

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

Agent Architecture Audit diagnoses failures in agent and LLM applications by auditing the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Use it when an agent misbehaves and the failing layer is unknown, or before shipping an agent stack.

Agent Eval compares coding agents head-to-head on reproducible tasks, measuring pass rate, cost, time, and consistency. Use it to choose between agents or validate changes with data instead of impressions.

Agent Harness Construction designs and optimizes AI agent action spaces, tool definitions, and observation formatting to improve completion rates. Use it when defining or revising an agent's tool set, action space, or observation format.

Agent Introspection Debugging guides an AI agent through a structured four-phase loop to capture failures, diagnose root causes, apply contained recovery actions, and produce an introspection report. Use it when an agent run fails repeatedly, loops, or drifts and you need a reproducible diagnosis rather than a blind retry.

Agent Payment x402 adds x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Use it when an agent must pay for APIs or services, enforce spending limits, or manage its own wallet.

Agent Sort builds an evidence-backed ECC install plan for a specific repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use it when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Agentic Engineering guides agents through eval-first execution, task decomposition, and cost-aware model routing. Use it when planning or executing engineering work that agents will carry out end to end.

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Kanban Video Orchestrator plans and runs multi-agent video production pipelines by decomposing video requests into specialized agent roles and managing them via a Kanban board. Use it to orchestrate complex video projects that require multiple specialist agents rather than a single script.

AudioCraft Audio Generation provides guidance for using Meta's AudioCraft models (MusicGen, AudioGen, EnCodec) to generate music and sound effects from text descriptions. Use it when building applications that require text-to-music, melody-conditioned generation, or text-to-sound synthesis.