Search skill packs and skills together

Complex features often have several valid implementation paths. This skill runs independent agent implementations, reviews them, and helps select the strongest result.

Feature work can pass shallow tests while failing against real systems. This skill guides Claude, Codex, and Claude Code to prove behavior with scenario tests and documented real-dependency checks.

Complex software choices can be hard to judge from discussion alone. Test Kitchen guides parallel designs, implementations, reviews, and winner selection.

Teams often write copy without real customer language. This skill guides Claude, Codex, and Claude Code to collect exact quotes and organize them for messaging.

Security reviews can miss important controls across applications, infrastructure, and supply chains. This skill provides framework-based checklists and a consistent finding format for focused reviews.

Research tasks need current sources and clean page text. This skill routes Claude, Codex, and Claude Code requests through Tavily and Exa using the belt CLI.

Artist files can become inconsistent across context, songs, and releases. This skill organizes and updates one existing artist workspace using defined source-of-truth files.

Market sizing is hard to defend when assumptions, sources, and methods are scattered. This skill guides TAM, SAM, and SOM analysis with sourced calculations and validation.

Social research can be difficult when results lack context, source links, or clear evidence boundaries. Jev Social gathers browser-grounded records from supported platforms and returns a source-linked report.

Project teams may miss relevant AI development skills for their frameworks and workflows. This skill maps detected technologies to recommendations and optional project templates.

Unclear requirements cause scope creep and premature technology choices. This skill converts requirements and research into prioritized scope, effort estimates, and an approved technology stack.

Biosignal analysis requires careful preprocessing, validated metrics, and modality-specific methods. This skill guides NeuroKit2 workflows for ECG, EEG, EDA, RSP, PPG, EMG, EOG, HRV, events, and complexity.