Managing multi-language translations across large projects is tedious and error-prone. This skill helps AI coding assistants write source strings correctly, follow project naming conventions, and integrate with Localhero.ai translation workflows.

Deep learning debugging often leads to speculative patches that break research reproducibility. This skill provides conservative diagnosis with explicit approval gates before any code modification, keeping debug fixes separate from research contributions.

Deep learning training runs often lack reproducible evidence and clear status reporting. This skill executes a selected training command conservatively and writes standardized training evidence to train_outputs/.

Manually scanning AI repositories for reproduction commands is time-consuming and error-prone. This skill automates README-first analysis to extract documented commands and generate minimal trustworthy reproduction plans.

When reproducing AI research, repository READMEs often leave critical gaps about dataset splits, evaluation protocols, or preprocessing details. This skill resolves those narrow reproduction questions from primary paper sources while preserving README-first guidance.

Running AI paper reproduction experiments requires consistent command execution and standardized reporting. This skill executes smoke tests, inference runs, or evaluation commands while automatically generating structured output bundles for audit trails.

Deep learning researchers need to run quick exploratory trials without overclaiming results. This skill generates budget-aware variant matrices with fair-comparison caveats, keeping exploratory evidence clearly separated from trusted baselines.

Deep learning researchers need to explore code modifications without breaking trusted baselines. This skill creates conservative, auditable change plans with explicit rollback paths for isolated worktrees.

Setting up AI research environments for paper reproduction is complex and error-prone. This skill automates conservative conda-first environment creation and asset path planning to reduce setup friction.

Understanding a new deep learning repository is time-consuming and error-prone. This skill provides read-only static analysis to map model structure, training entrypoints, and suspicious patterns without modifying code or running expensive training jobs.

Reproducing deep learning papers is slow and error-prone because commands, datasets, and assumptions are scattered across READMEs. This skill reads the repository first, selects the smallest documented target, and writes a standardized repro_outputs/ bundle with evidence, deviations, and human decision points.

Creating AI-generated images and videos typically requires navigating complex platforms and writing detailed prompts. This skill connects directly to liblib.tv's API, letting you generate and edit visual content through natural language commands.

Claude agents often produce generic, AI-looking interfaces. This skill enforces strict design standards to generate premium, anti-generic UI specifications that avoid common pitfalls like Inter font, neon glows, and centered hero sections.

AI-generated websites often share the same generic patterns, making them look indistinguishable. This skill audits your existing project and applies targeted design upgrades to create a polished, premium look without rewriting your codebase.

Most AI-generated interfaces look generic and derivative. This skill guides Claude to produce refined, editorial-style web designs with warm monochrome palettes, typographic hierarchy, and premium aesthetics.

Create bold, mechanical web interfaces with Swiss typography and military terminal aesthetics. Generate data-heavy dashboards and editorial sites with raw functionality and extreme typographic contrast.

Most AI web design tools produce generic, repetitive layouts that are hard to translate into real code. This skill generates premium design images first, analyzes them deeply, then produces frontend code that faithfully matches the visual reference.

Standard AI image generation defaults to repetitive, generic website layouts with purple gradients and left-text/right-image heroes. This skill breaks those patterns by enforcing art-directed, premium frontend design references that developers can actually build from.

Standard AI tools produce generic, cluttered mobile mockups with unreadable text and inconsistent design systems. This skill solves that by enforcing premium art direction, platform-native patterns, strict multi-screen consistency, and readable typography inside clean phone mockups.

Most AI tools produce generic, template-like UI designs that lack polish. This skill provides exact design rules for fonts, spacing, shadows, card structures, and animations to create interfaces that look like they came from a high-end design agency.