Agent skills for Devin Desktop

Create or update Claude skills. Use for new skills, skill references, skill scripts, optimizing existing skills, extending Claude's…

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy.

Interactively create a new Grok skill (SKILL.md + optional scripts/references).

Generate MSIX packaging configuration with manifest, assets, and signing for Windows applications

SQL Server database development specialist.

REQUIRED and PRIMARY testing approach for packages/playground and packages/playground-ui.

Improve an existing 60-card Standard deck for MTG Arena (MTGA) that the user pastes in.

Build synergy-dense, format-legal, budget-compliant 100-card Commander decks via a multi-agent pipeline.

Deploys and configures Microsoft Defender for Cloud as a CNAPP for

Board of experts — consults multiple ecosystem agents in parallel for multi-perspective analysis of any topic.

Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration.

Enforces strict handoff and shared state protocols for multi-agent workflows across DeepSeek, Claude, and Codex.

Run a gated multi-agent coding workflow for development requests.

Orchestrates multi-agent collaboration within Claude Code using a structured 'Company Model' for parallel development and task management.

Conducts comprehensive, parallel code reviews using Codex, Gemini, and Claude to generate a unified analysis report.

Protect production environment files while allowing safe access to dev and QA configurations.

Generates structured business reports, presentations, spreadsheets, and documents across formats including Word, PDF, Excel, PowerPoint…

Lifecycle management for rigs where several views/engines share several instruments — single-connection ownership with a central hub…

When the user manages SEO across multiple business locations (10-500+).

Decide and execute safe routing of complex tasks across currently available Codex agents.