About autopilot-predict
autopilot-predict is a skill that uses Ruflo autopilot intelligence to recommend the next task and guide its execution. It draws on learned completion patterns and past-task history stored in AgentDB.
Key features
- 01Recommend a next action
- 02Use confidence to guide execution
- 03Break down tasks when confidence is low
- 04Learn patterns from completed tasks
- 05Search completion history
Use cases
- 01Choose a next task based on a prediction
- 02Fall back to task priorities when confidence is low
- 03Guide iterations inside a /loop
MCP support
Uses Ruflo MCP tools to predict actions, inspect task progress, learn from completed work, and search history.
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/autopilot-predictin Claude Code to confirm it loaded.
Details
From the project READMEPredict what to work on next using Ruflo autopilot intelligence:
- Call
mcp__plugin_ruflo-core_ruflo__autopilot_predictfor the recommended next action - If confidence > 0.7, execute the prediction directly
- If confidence < 0.7, check
mcp__plugin_ruflo-core_ruflo__autopilot_progressfor task breakdown - Pick the highest-priority incomplete task
- After completing work, call
mcp__plugin_ruflo-core_ruflo__autopilot_learnto update patterns
Learning Pipeline
mcp__plugin_ruflo-core_ruflo__autopilot_learn-- discover success patterns from completed tasksmcp__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
Comments
Markdown supported