Poorly defined tools cause invalid calls, silent failures, and wasted tokens. This skill guides schema design, validation, error handling, MCP integration, and parallel execution.

Multi-agent workflows often waste time, tokens, and compute through poor coordination. This skill guides profiling, workload distribution, cost controls, and measured optimization.

Deploying custom agent containers in Azure AI Foundry requires precise SDK, identity, registry, and protocol configuration. This skill provides focused Python patterns for creating and managing hosted agents.

Agent changes often lack reliable evidence, testing, and rollout controls. This skill provides a measured workflow for analysis, prompt refinement, evaluation, deployment, and monitoring.

Agents lose useful context across interactions and may retrieve stale or irrelevant memories. This skill provides architectures, storage patterns, retrieval controls, decay methods, and evaluation guidance.

Persistent Azure AI agents require careful setup across authentication, tools, threads, and response handling. This skill provides focused Python patterns for each workflow.

Single-run checks hide stochastic failures and production regressions. This skill designs repeatable evaluations with behavioral, adversarial, statistical, and leakage tests.

Pull request feedback can become difficult to track. This skill organizes comments, plans fixes, applies approved changes, and reports completion.

Interactive 3D websites often suffer from poor performance, inaccessible controls, and fragile asset pipelines. This skill guides stack selection, scene integration, optimization, loading states, and WebGL fallbacks.

Python projects often need stronger correctness, types, and style. This skill guides implementation and review using practical Python best practices.

Teams lose time when frontend, API, database, and deployment choices are handled separately. This skill guides Claude, Codex, and Claude Code through full-stack application planning and implementation.

Bugs waste engineering time when symptoms hide the real cause. This skill guides Claude, Codex, and Claude Code through structured investigation, hypothesis testing, fixes, and prevention.

Building consistent shadcn interfaces requires current project context and correct component APIs. This skill guides discovery, installation, updates, styling, composition, and registry workflows.

Teams often know a repository needs improvement but lack a clear, verified execution plan. This skill surveys the codebase, prioritizes evidence-backed findings, and writes plans that another agent can execute safely.

Email implementation often spans templates, content, tests, and rollout approvals. This skill helps AI agents make scoped repository changes with QA checks and approval boundaries.

Manual browser inspection makes reliable automation scripts difficult to author. This skill uses Playwright CLI to navigate pages, capture snapshots, and verify selectors.

Go error paths often lose context, duplicate logs, or expose internals. This skill gives Claude, Codex, and Claude Code concrete rules for safer Go errors.

Go code can pass formatting checks while still being hard to read. This skill guides Claude, Codex, and Claude Code toward clearer style choices.

Complex projects need coordinated agents, dependencies, memory, and recovery. This skill provides reusable Claude Flow patterns for research, development, testing, analysis, and monitoring.

Complex software work often lacks a consistent path from requirements to completion. This skill applies SPARC phases, specialized modes, and coordinated development workflows.