Search Skills

Breaks down epics and features into actionable backlog tasks with dependency mapping for effective sprint planning and work organization.

Automates browser interactions including form filling, network debugging, responsive testing, and text-to-speech notifications.

Handles Git branch merging, conflict resolution, and worktree cleanup for efficient development workflows.

Enables structured ideation and workflow design for project planning before task creation, optimizing team alignment and execution.

Integrates web projects with TabzChrome terminals via HTML attributes, WebSocket, and JS API.

Automates creation and management of terminal tabs via REST API, enabling efficient setup of development environments for parallel work and worker spawning.

AI-powered tool for Agile backlog grooming: prioritizing tasks, managing dependencies, and setting quality gates in project workflows.

Automates Chrome browser tasks including screenshots, form filling, network debugging, and error checking.

Automates terminal spawning, worker management, and worktree setup for streamlined development environment workflows.

Automates browser interactions including screenshots, form filling, network debugging, responsive design testing, and text-to-speech notifications.

Automates creation and management of terminal tabs in browser using TabzChrome REST API for efficient developer workflows.

Verifies UI changes via screenshots, smoke tests, and console checks to ensure visual accuracy in extensions and backend.

Automates verification of user-facing change documentation, ensuring changelogs and lessons-learned are updated or explicitly bypassed.

Enables project integration with TabzChrome terminals using HTML attributes, WebSocket, JS API, or Spawn API.

Comprehensive framework for building terminal user interfaces (TUIs) with support for components, layout, keyboard handling, and testing.

Enforces rigorous validation steps including baseline comparisons, cross-validation, and leakage prevention in machine learning pipelines.

Provides standardized patterns for data loading, exploration, and statistical analysis to enhance data science workflows.

Enforces rigorous ML pipeline validation through baseline comparisons, cross-validation, model interpretation, and data leakage prevention.

Provides best practices for creating scientifically rigorous and reproducible experimental designs in data science and research contexts.

Provides standardized patterns for loading, exploring, and performing statistical analysis on datasets.

Provides best practices for designing reproducible experiments in data science and AI research contexts.

Adds pytest tests to validate reference implementations in flashinfer_trace against FlashInfer or SGLang ground truth, ensuring kernel and operation correctness.

Automates cloning of SGLang and FlashInfer repositories from GitHub to third_party for project initialization and kernel extraction.

Extracts and deduplicates kernel schemas from SGLang model implementations for AI model development and flashinfer_trace integration.