Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.

Help users write syntactically and semantically correct primary constructors in Dart, and migrate/use the new constructor syntax, empty-body semicolon syntax, in-body initializer list syntax, and abbreviated concise constructor syntax.

Guides agents in compiling and packaging C/C++ source code into dynamic or static libraries (Code Assets) using Dart's Native Assets hook system (via hook/build.dart and hook/link.dart utilizing package:hooks and package:native_toolchain_c). Use when a user asks to: 'setup native assets', 'compile C/C++ source code', 'bundle dynamic libraries', 'build native C code', 'link native assets', 'implement build.dart or link.dart hooks', or 'integrate C/C++ interop in Dart/Flutter'. Helps agents avoid manual toolchain orchestration and configures secure hash-validated binary downloads or advanced linker tree-shaking with package:record_use mapping.

Workflow for fixing package version conflicts. Use this when `pub get` fails due to incompatible package versions.

Uses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.

Collect coverage using the coverage packge and create an LCOV report

Write and organize unit tests for functions, methods, and classes using `package:test`. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.

Safe, portable, and efficient command-line patterns for macOS/BSD Unix tools (grep, find, sed, awk, xargs, mdfind, pbcopy, open) and modern alternatives (ripgrep, fd). Covers common shell scripting and one-liner use cases including fast searching, text processing, codebase navigation, and parallel execution.

This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.

Minimal SPARV workflow (Specify→Plan→Act→Review→Vault) with 10-point spec gate, unified journal, 2-action saves, 3-failure protocol, and EHRB risk detection.

给剪好的口播做字幕：直接用已有的逐词稿加账本算出剪后时间（不必导出、不必重新转录）、用词典和作者文稿改写听错的专名、按句子分屏、在 Studio 里逐屏复核。用户说做字幕、加字幕、改字幕、重新分屏、字幕不对时使用。不要用于删词剪辑、物理剪切、分镜动画或成片渲染。

把已审核的口播删词账本落成剪后视频：展示确认卡、执行物理剪切、验收剪后媒体。只在删词已经人工复核之后使用。用户说导出口播、执行剪切、把剪好的视频导出来、继续导出，或确认卡回传 action=continue_cut 时使用。不要用于生成删词候选、字幕、分镜动画或成片渲染。

Set an explicit objective, success criteria, and stopping conditions for the current OpenScience session.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.