Autopilot Predict

This is workflow automation that tries to guess what you should work on next based on patterns from your past sessions. It calls autopilot_predict, and if the confidence score is above 0.7 it just runs with that suggestion. Below that threshold it falls back to checking your task list and picking the highest priority item. The interesting bit is autopilot_learn, which updates the pattern database after you finish something, so theoretically it gets smarter over time. Designed to work inside loop mode where it can drive each iteration automatically. Honest take: the success of this depends entirely on whether the pattern matching is actually good, which you won't know until you've fed it enough data.

skills.sh installs: 744
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill autopilot-predict --agent claude-code

Installs into .claude/skills of the current project.

Files

Predict what to work on next using Ruflo autopilot intelligence:

Call mcp__plugin_ruflo-core_ruflo__autopilot_predict for the recommended next action
If confidence > 0.7, execute the prediction directly
If confidence < 0.7, check mcp__plugin_ruflo-core_ruflo__autopilot_progress for task breakdown
Pick the highest-priority incomplete task
After completing work, call mcp__plugin_ruflo-core_ruflo__autopilot_learn to update patterns

Learning Pipeline

mcp__plugin_ruflo-core_ruflo__autopilot_learn -- discover success patterns from completed tasks
mcp__plugin_ruflo-core_ruflo__autopilot_history({ query: "KEYWORD" }) -- search past completions
Patterns are stored in AgentDB for cross-session recall