/autopilot-predict
Use learned patterns and current state to predict the optimal next action
$ npx -y skills add ruvnet/ruflo --skill autopilot-predict --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/autopilot-predict
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use learned patterns and current state to predict the optimal next action
SKILL.md
autopilot-predict.SKILL.mdname: autopilot-predict description: Use learned patterns and current state to predict the optimal next action argument-hint: "" allowed-tools: mcp__plugin_ruflo-core_ruflo__autopilot_predict mcp__plugin_ruflo-core_ruflo__autopilot_progress mcp__plugin_ruflo-core_ruflo__autopilot_learn mcp__plugin_ruflo-core_ruflo__autopilot_history
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
An agent meta-harness for Claude Code and Codex. Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work.
Repo: ruvnet/ruflo
Other skills on claude-flow.
- /agentdb-advanced
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Open skill - /agentdb-learning
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Open skill - /agentdb-memory-patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Open skill - /agentdb-optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
Open skill - /agentdb-vector-search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Open skill - /agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Open skill