Installs into .claude/skills of the current project.
Are you the author of Predict Next Action?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/next-ai-labs-inc-predict-next-action)
---
name: predict-next-action
description: Predict the next highest-leverage task based on the session, evaluate risk, and frame the UX possibility being moved toward.
triggers:
- "what's next"
- "predict next"
- "next action"
---
# Predict next actionable task
## 1. UX possibility (one sentence)
State the full scope of what you've been working on, framed as the UX possibility you're moving us toward. Not what you did — where it's going.
## 2. Prediction (one sentence)
Predict your next actionable task based on the session. All signal, no noise, in language the user will immediately understand — mirror how they talk.
## 3. Risk reflection
> Any risk:
> {your human-level reasoning about what could go wrong, create problems, or introduce downside risk}
Then reflect on the risk. If needed, reshape your prediction to avoid it.
## 4. Final framed action (one sentence)
One nuanced sentence that captures the UX intent, the actionable work, AND constraints to avoid risk — all together.
## 5. Incomplete items (one sentence)
Anything left unfinished from the current session. Skip if nothing.