streaming-progress
The streaming-progress skill formats and emits real-time progress events during AI agent execution, providing both human-readable summaries and machine-readable metrics for UI consumption. Use this when tracking multi-stage workflows that require live progress updates, calculating completion percentages, and displaying dynamic feedback to users monitoring project execution across different processing phases.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/streaming-progress && cp -r /tmp/streaming-progress/library/methodologies/automaker/skills/streaming-progress ~/.claude/skills/streaming-progressSKILL.md
# Streaming Progress Emit real-time progress events for streaming UI consumption. ## Agent Progress Streamer - `automaker-progress-streamer` ## Workflow 1. Receive progress event from execution stage 2. Format event with timestamp and stage information 3. Calculate completion percentage 4. Generate human-readable summary 5. Include machine-readable data for UI rendering 6. Emit formatted event ## Inputs - `projectName` - Project name - `featureId` - Feature being tracked - `event` - Progress event with stage, message, data ## Outputs - Formatted streaming event with progress metrics ## Process Files - `automaker-orchestrator.js` - Phase 3 (batch progress) - `automaker-agent-execution.js` - All stages
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement