Autopilot Predict

by ruvnet60de638630abNo license74K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Use learned patterns and current state to predict the optimal next action

AI-generated overview

Predicts the next task to work on using Ruflo autopilot MCP tools and learned patterns.

What it does
This skill guides an agent through a prediction loop built on Ruflo autopilot MCP tools. It calls autopilot_predict for a recommended next action, executes it directly when confidence exceeds 0.7, and otherwise falls back to autopilot_progress for a task breakdown and picks the highest-priority incomplete task. After work is finished it calls autopilot_learn to update success patterns, which are stored in AgentDB for cross-session recall, and autopilot_history can search past completions by keyword.
When to use it
Use it when an agent needs to decide what to work on next from a task backlog or inside a repeated loop. It fits situations where prior completions should inform prioritization and where a confidence threshold can decide between acting immediately and consulting the task list.
Requirements
Requires the Ruflo autopilot MCP tools autopilot_predict, autopilot_progress, autopilot_learn and autopilot_history, plus the AgentDB pattern store they rely on. It ships no scripts and is instructions only.

Predict what to work on next using Ruflo autopilot intelligence:

  1. Call mcp__plugin_ruflo-core_ruflo__autopilot_predict for the recommended next action
  2. If confidence > 0.7, execute the prediction directly
  3. If confidence < 0.7, check mcp__plugin_ruflo-core_ruflo__autopilot_progress for task breakdown
  4. Pick the highest-priority incomplete task
  5. 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

Integration with /loop

When running inside a /loop, the predict skill guides each iteration:

  • High confidence prediction -> execute immediately
  • Low confidence -> fall back to task list priority order
  • No tasks remaining -> disable autopilot and exit loop

Source and attribution

Source:ruvnet/rufloinplugins/ruflo-autopilot/skills/autopilot-predictat commit60de638

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Autopilot Predict Agent Skill | SourceWeft