MVP Follow-Up
SkillAI & modelsThis skill guides your AI to answer 'what should we do next?' with the smallest steps that actually finish and ship an MVP. After a feature pass, it looks for unfinished work and steers the plan away from adding new features that only add bloat.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then ask your AI what to do next after a round of feature work. It will respond with the smallest steps needed to finish and ship.
Then ask your AI: use the MVP Follow-Up skill
What your AI can do with it
- Suggest the smallest next steps to finish and ship an MVP
- Check for unfinished MVP work after a feature pass
- Steer next-step planning away from new features that add bloat
- Keep planning focused on shipping instead of expanding scope
What this skill tells your AI
The instructions your AI receives, as published by builderio/agent-native in .agents/skills/mvp-followup/SKILL.md and read by ahel’s review.
Rule
Recommend or execute only closeout work that makes the current MVP more real, verified, documented, or shippable. Do not propose new product scope unless there is a clear blocker to the MVP working for real users.
Workflow
- Identify the current feature or thread outcome.
- Check for unfinished work in this order:
- failing or skipped verification
- unreviewed real-data pilot results
- pending review/proposals/approval queues
- docs that no longer match behavior
- unrelated dirty files that block full prep/ship hygiene
- Recommend the smallest next batch that closes those gaps.
- Explicitly skip tempting bloat: new integrations, dashboards, settings, abstractions, or extra UI unless they directly unblock real use.
- If the user says "do it", run the closeout work in parallel where safe and keep edits minimal.
Output Shape
Lead with the concrete next step. Keep the list short. Separate:
- Do now: validation, real pilot, docs, or bug fixes.
- Defer: useful ideas that should wait for real user feedback.
- Blocker: any specific user/manual action needed.
Verification Bias
Prefer non-mutating checks when the worktree has unrelated dirty files. Use full
pnpm prep only when it will not rewrite someone else's concurrent work.
Related Skills
qashipadding-a-featurecapture-learnings
Signals
- GitHub stars
- 5k
- Forks
- 440
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
mvp-followup- Source
- github.com/builderio/agent-native