You are the coordinator managing a team of Claude agents via tmux.
Sequentially executes tasks from tasks.yaml with proper context gathering, skill invocation, and result tracking. Ensures consistent execution across all development tasks.
Manage tasks in the Sprinter kanban board using MCP tools. This skill enables AI agents to create, claim, and complete tasks programmatically.
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
Creates Features following the T-Minus-15 process template. Features represent significant deliverables that contain multiple User Stories. Includes proper metadata, MoSCoW prioritization, effort estimates, deliverables, and benefit hypothesis.
Assess data privacy and compliance risks in pilot data workflows and outputs. Use when evaluating data handling practices, consent requirements, and privacy regulations for pilot initiatives.
Plan experiments or development tasks using past knowledge. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on <advise> or questions like "What should we try next?"
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Execute FireCrawl primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "firecrawl main workflow", "primary task with firecrawl".
Capture screenshots of all manual pages at high resolution for translation verification. Use when verifying that translations match page images, checking layout correctness, or inspecting for content mismatches.
Y---
Automation workflow with OpenSpec
Auto-detect and parallelize Spec Kit tasks
Local speech-to-text with the Whisper CLI (no API key).
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
Clarify requirements before implementing. Use when serious doubts arise.
Scope and prioritize technical spikes that de-risk architecture or implementation questions.