Sentry01

Builds accessible, production-ready frontend components. Use when building UI components, forms, modals, or any React/Vue/Svelte frontend work — before writing component code.

Use when a task needs multi-model perspectives, brainstorming, or stress-testing. Supports two modes: collaborative (default — agents build on each other's ideas) and adversarial (agents debate to find the strongest answer). Triggers: council, siege, swarm, multi-agent, debate, brainstorm.

Read, edit, analyze, and create Microsoft Excel files (.xlsx, .xls, .xlsm, .csv, .tsv). Use when a user asks to: (1) Open/read/inspect an Excel file, (2) Edit or modify spreadsheet data, formulas, or formatting, (3) Analyze spreadsheet data and provide insights, statistics, or trends, (4) Create new Excel files with data, formulas, charts, or formatting, (5) Convert between CSV/TSV and Excel formats, (6) Build financial models or dashboards in Excel.

Build, edit, analyze, and improve PowerPoint presentations (.pptx). Use when a user asks to: (1) Create a new presentation from scratch, (2) Edit or modify slides, text, images, or layouts, (3) Analyze a presentation for quality, consistency, or content, (4) Improve an existing presentation's design, structure, or readability, (5) Extract text or speaker notes, (6) Add charts, tables, or media to slides, (7) Review or critique a presentation.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when a task needs multi-model perspectives, brainstorming, or stress-testing. Supports two modes: collaborative (default — agents build on each other's ideas) and adversarial (agents debate to find the strongest answer). Triggers: council, siege, swarm, multi-agent, debate, brainstorm.