mverab/slashstack-skills / skills/next
next
VerifiedUse when the user is unsure what to ask next and needs safe prompt options.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
SKILL.md
View on GitHub---
name: next
description: Use when the user is unsure what to ask next and needs safe prompt options.
---
# Next
## Purpose
Suggest safe next prompts when the user does not know what to ask next.
## When to Use
Use after preflight, explain, audit, ship, a failed test, an unclear error, or
any moment where the user needs direction before continuing.
## Workflow
1. Read current context: summarize the user's goal, current repo state, and any
recent tool output.
2. Identify risk: note whether the next action could edit files, change config,
deploy, delete data, or expose secrets.
3. Offer 2-3 safe next prompts: make each prompt specific, scoped, and suitable
for pasting into the agent.
4. Label each option: use Beginner, Safer, or Faster so the user understands the
tradeoff.
5. Modo Aprendiz: for EACH recommended prompt, explain WHY with three
sub-fields in beginner-friendly Spanish:
- Qué significa: what the recommendation means in plain language.
- Por qué importa: why it matters for the project.
- Qué hacer ahora: one concrete action to take now.
6. Do not edit files, run risky commands, deploy, or change configuration until
the user chooses an option.
## Output
A next-step menu containing:
- Current state: one-sentence summary
- Options: 2-3 safe next prompts with labels
- Modo Aprendiz: each option includes Qué significa, Por qué importa, and Qué hacer ahora
- Recommendation: the best default option and why
- Caution: any action the user should avoid for now
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |