Shallow modules spread complexity across callers and make tests depend on implementation details. This skill evaluates interfaces, seams, dependencies, and alternatives to improve module depth.

Engineering tasks often stall because the next process or skill is unclear. This skill maps each situation to a focused workflow and starting point.

Mastra APIs change quickly, so older examples can create broken agents and workflows. This skill guides Claude, Codex, and Claude Code to verify current docs before writing code.

Flutter motion can be hard to choose and implement correctly. This skill guides animation selection, code patterns, performance, and accessibility.

Internationalized projects need consistent source strings, keys, glossary terms, and translation updates. This skill applies project conventions and runs Localhero.ai workflows.

Deep learning failures can invite risky, premature changes. This skill classifies concrete errors and prepares conservative guidance before any code modification.

Deep learning experiments can blur candidate changes with trusted baseline work. This skill guides isolated adaptations and creates rollback-aware implementation records.

Research repositories can hide important model, configuration, and evaluation relationships. This skill maps those relationships and reports suspicious patterns without changing project code.

Local Apple builds require macOS and Xcode infrastructure. This skill sends projects to Limrun for remote builds, simulator installation, signing, previews, and App Store uploads.

iOS UI testing often requires macOS hardware and manual simulator access. This skill controls Limrun cloud simulators through the lim CLI from any supported environment.

Visual website builds often lose fidelity between reference images and frontend implementation. This skill guides Claude, Codex, and Claude Code through image-first analysis and faithful implementation.

Building reusable Lark automation requires consistent API research, permissions, and workflow documentation. This skill guides Claude and Codex through focused lark-cli skills for single APIs or multi-step workflows.

Frontend reviews often miss accessibility, data boundary, and component ownership issues. This skill gives Claude and Codex a focused checklist for Dify React and Next.js code reviews.

Large React components slow review, testing, and maintenance. This skill guides hook extraction, component splitting, and Dify-aligned verification.

Long-running workflows need a reliable way to stop without leaving stale state. This skill outlines a Redis-backed stop design, API flow, frontend option, and tests.

Interactive workflow nodes require coordinated backend, frontend, history, and localization changes. This skill gives Claude, Codex, and Claude Code a focused implementation guide for FastGPT interactive responses.

Coding-agent projects can drift when tasks, scope, and checks are vague. This skill gives PM templates and review rules that keep Claude, Codex, and Claude Code work bounded and verifiable.

Writing accurate conventional commits from complex staged changes takes time and can produce inconsistent results. This skill inspects staged Git changes and recommends a concise, scoped commit message.

Broad fixes can introduce unrelated regressions and overwrite existing work. This skill traces each bug to its responsible layer and verifies a focused correction.

Structural code changes can introduce subtle regressions and expand scope. This skill defines behavior boundaries and brackets focused refactors with verification.