Manual checks miss project-specific TypeScript and architecture violations. This skill runs focused scripts and explains fixes using DevPrep AI standards.

Unclear requirements and repeated failed attempts can waste time and create unreliable work. This skill provides repeatable checks for complexity, dependencies, evidence, and escalation before work continues.

Prototype markup often lacks reusable structure, types, and accessibility. This skill analyzes the design and produces components suited to the target frontend stack.

Slow applications lose users and make incidents harder to diagnose. This skill gives Claude, Codex, and Claude Code practical patterns for faster systems.

Production systems need logs, metrics, traces, alerts, and health checks that work together. This skill gives Claude, Codex, and Claude Code practical templates for service observability.

Creating consistent feature modules by hand is slow and error-prone. This skill generates DevPrep AI module structure, starter TypeScript files, components, and quality checks.

Many teams mark AI-generated work complete without proof. This skill guides agents to collect test, build, lint, and deployment evidence before closure.

Edge platforms differ in runtime limits, storage, and deployment behavior. This skill provides practical patterns for routing, authentication, caching, streaming, and rate limiting.

Deployment teams need consistent patterns for CI/CD, containers, Kubernetes, and cloud infrastructure. This skill provides templates and review guidance for planning these workflows safely.

Hand-converting prototypes creates repetitive mapping and setup work. This skill analyzes HTML, guides component choices, scaffolds React files, and checks local conventions.

Inconsistent interface decisions slow teams and weaken accessibility. This skill provides token structures, React patterns, templates, and checklists for a scalable design system.

Inconsistent reviews miss defects and create unclear feedback. This playbook provides structured checklists, conventional comments, templates, and review workflows for reliable decisions.

Complex technical explanations can be difficult to scan in plain prose. This skill converts them into compact ASCII diagrams with consistent visual structure.

Developers can lose time deciding where code belongs in DevPrep AI. This skill maps the structure and applies documented placement rules.

Important architecture choices often lose their rationale over time. This skill provides structured ADR templates, examples, and review guidance for preserving decisions and trade-offs.

Inconsistent API contracts create integration errors and expensive migrations. This skill applies reusable REST, GraphQL, gRPC, OpenAPI, and AsyncAPI patterns to create clear contracts.

Teams need reliable patterns for adding LLMs, retrieval, tools, and agents to production software. This skill provides practical templates and references for RAG, vector search, function calling, observability, and cost control.

Genomics dataset investigation often requires multiple accession, metadata, and literature searches. SRAgent coordinates SRA and GEO queries, technology identification, and publication retrieval.

Blocklet releases require version, changelog, build, metadata, and bundle checks. This skill guides Claude, Codex, or Claude Code through that release workflow.

Preparing a web project for ArcBlock deployment requires correct metadata, assets, and bundle settings. This skill guides Claude, Codex, or Claude Code through conversion and validation steps.