Manual checks slow reviews and let inconsistent releases reach production. This skill creates GitHub Actions workflows with required quality gates and deployment patterns.

API teams lose time when contracts are unclear or written after implementation. This skill guides OpenAPI-first design, TypeScript generation, validation, documentation, and mock workflows.

Teams forget why major technical choices were made. This skill helps draft, review, and organize ADRs with clear context, alternatives, and consequences.

Accessibility defects make products difficult to use and increase compliance risk. This skill guides Claude, Codex, and Claude Code through WCAG 2.2 checks for UI work.

Agent frameworks often hide how tools are registered, validated, and retried. This skill guides a structured review of tool abstractions, schemas, built-in tools, and error feedback.

Agent frameworks often hide failure paths, weak isolation, and incomplete recovery behavior. This skill guides structured reviews of propagation, sandboxing, retries, fallbacks, and production readiness.

Multi-agent systems can hide brittle handoffs, shared-state coupling, and unclear communication paths. This skill guides Claude, Codex, or Claude Code to map coordination models and produce a structured review.

Agent frameworks often hide how context, memory, and token budgets interact. This skill gives Claude, Codex, and Claude Code a structured way to inspect memory flow and compare design choices.

Agent framework audits often miss the translation layer between internal state and provider APIs. This skill guides Claude, Codex, and Claude Code through message formats, tool calls, streaming events, and provider abstractions.

Agent frameworks hide concurrency, topology, events, and hooks across many files. This skill guides Claude, Codex, or Claude Code through a structured execution-engine review.

Data models and state updates can drift without clear review. This skill guides analysis of typing, mutation, and serialization choices.

Agent frameworks hide reasoning loops across scattered files. This skill guides Claude, Codex, and Claude Code to find loops, step functions, and termination conditions.

Framework extension points can be hard to compare across codebases. This skill guides Claude, Codex, and Claude Code through abstraction, dependency injection, and configuration analysis.

Technical teams often need to compare frameworks with clear criteria and evidence. This skill turns analysis notes into structured matrices, trade-off summaries, and recommendations.

Large repositories are hard to understand quickly. This skill maps structure, imports, entry points, and module boundaries for focused analysis.

Designing an agent framework requires clear primitives, interfaces, and execution rules. This skill turns prior analysis into a reference architecture and implementation roadmap.

Agent framework design is hard to compare because behavior spans code structure and reasoning patterns. This skill guides Claude, Codex, and Claude Code through a staged architecture forensics workflow.

Framework analyses often produce scattered code smell notes. This skill turns observations into a structured catalog with severity, impact, and remediation guidance.

Pydantic AI projects need clear patterns for agents, tools, dependencies, and structured outputs. This skill provides concise guidance and examples for building type-safe Python agent applications.

Researchers need fast access to preprints that may not appear in journal indexes yet. This skill searches arXiv and returns concise paper titles, summaries, and links.