Skill UI

Workflow automation ensures AI agents and business processes remain reliable despite failures. This skill covers durable execution patterns and platforms like n8n, Temporal, and Inngest. It transforms brittle scripts into production-grade systems handling sequential, parallel, and orchestrator-worker patterns for payment flows, document analysis, and background jobs.

This skill optimizes LLM context usage through prompt caching, log pruning, and AST-based file inspection. It enforces ultra-dense output, minimizes filler text, and manages token budgets efficiently. Ideal for technical tasks requiring precise code edits, structured data handling, and reduced context window consumption during long sessions.

Automates Zoom meeting scheduling, webinar handling, cloud recording retrieval, and participant tracking through the Rube MCP toolkit, ensuring you first fetch current schemas and maintain an active OAuth connection for paid accounts.

Build a human-reviewed conduct register after context-first intake. Use when an SME needs policy acknowledgements, complaint handling, and breach follow-up.

Skill for setting up a minimal sales accounting system, handling invoices, receivables, VAT, TDS, and credit terms. Generates recommendations and optional artifacts like CSV, SQL DDL, JSON Schema, and Notion mappings.

Security hardening guidance for AI agent frameworks processing untrusted content, invoking tools, writing files, managing identifiers, or handling credentials. Use when building or reviewing agent runtimes, autonomous workers, tool gateways, memory services, or multi-tenant deployments.

Best practices for processing, storing, and displaying Bengali (Bangla) text in software applications and AI systems, including Unicode normalization, script detection, tokenization, conjunct handling, and Bangla-specific NLP techniques.

Safely rebase the checked-out feature branch onto the latest upstream default branch, detecting main or master and handling conflicts without discarding work.

Design and build all UI states agents forget: first use, empty, loading, error, offline, no results, long content, permission denied, and success. Use when making screens production-ready and handling edge cases.