Next Action Suggester
Topics
| Topic | Description | Guide |
|---|
| stall-detect | Detect stalled follow-up steps and invoke /fix | stall-detect.md |
After task completion, use AskUserQuestion to suggest next steps and get user selection.
When to use
Automatically use after any task completion:
- Code writing/modification complete
- Configuration changes complete
- File creation complete
- Commit/push complete
- Skill/agent creation complete
- Bug fix complete
Instructions
Step 0: Stall Detection (mandatory)
Before suggesting next actions, run the stall-detect topic.
If stall detected → topic invokes /fix. If no stall → proceed to Step 1.
Step 1: Identify completed task type
Identify the type of task just completed.
Step 2: Use AskUserQuestion tool
Present next step options via AskUserQuestion:
AskUserQuestion({
questions: [{
question: "What would you like to do next?",
header: "Next Action",
multiSelect: true
options: [
{ label: "Option 1", description: "Description" },
{ label: "Option 2", description: "Description" }
]
}]
})
Step 3: Execute selected action
Immediately perform the action(s) user selected.
Suggestion Patterns
After code writing/modification
options: [
{ label: "Run tests", description: "Verify changes with test suite" },
{ label: "Commit", description: "Git commit the changes" }
]
After feature implementation
multiSelect: true,
options: [
{ label: "Write tests", description: "Add tests for new feature" },
{ label: "Document", description: "Update README or JSDoc" },
{ label: "Commit", description: "Git commit the changes" }
]
After bug fix
multiSelect: true,
options: [
{ label: "Add regression test", description: "Prevent bug recurrence" },
{ label: "Commit", description: "Git commit the fix" },
{ label: "Close issue", description: "Close related issue" }
]
After configuration change
options: [
{ label: "Verify", description: "Source or restart to apply settings" },
{ label: "Backup", description: "Backup config file" }
]
After commit
options: [
{ label: "Push", description: "Git push to remote" },
{ label: "Create PR", description: "Create Pull Request" }
]
After push
options: [
{ label: "Create PR", description: "Create Pull Request" },
{ label: "Check CI", description: "Verify pipeline status" }
]
After skill/agent creation
options: [
{ label: "Test", description: "Verify activation with trigger keywords" },
{ label: "Review integration", description: "Check for duplicates" }
]
After file creation
options: [
{ label: "Review content", description: "Verify created file" },
{ label: "Git add", description: "Stage with git add" }
]
After refactoring
multiSelect: true,
options: [
{ label: "Run tests", description: "Verify existing tests pass" },
{ label: "Check performance", description: "Run benchmarks (if applicable)" },
{ label: "Commit", description: "Commit refactoring" }
]
After complex workflow completion
multiSelect: true,
options: [
{ label: "Agentify", description: "Convert this workflow to an agent/skill" },
{ label: "Serena memory", description: "Save key learnings to Serena memory" }
]
After project exploration/research
multiSelect: true,
options: [
{ label: "Serena memory", description: "Store findings in project memory" },
{ label: "Document", description: "Update project documentation" }
]
Rules
- Always 2-4 options - AskUserQuestion limitation
- Be specific - "Run npm test" instead of just "Test"
- Context-based - Adjust based on project/situation
- Use multiSelect - When multiple actions can be done together
- Execute immediately - Perform action(s) right after user selection
