This is the execution engine for BuilderOS projects. Once you've run the Product Planner and have your PRD and roadmap docs ready, this skill grinds through every task in order: implement, test, verify, check the box, move on. It won't skip ahead or improvise. It reads only what each task's Notes section points to, respects your stack choices from the PRD, and pulls design tokens from your design doc. The loop runs until every phase is done and your magic moment works end to end, then it initializes git and offers to wire up a remote. It's methodical to the point of being stubborn, which is exactly what you want when turning a 40 task roadmap into a working MVP without cutting corners.

skills.sh installs
1.7K
GitHub stars
233
last updated
Aug 21, 2026

Install

$ npx -y skills add buildgreatproducts/builder-os --skill build-mvp --agent claude-code

Installs into .claude/skills of the current project.

Files

Build MVP

Build the complete app by executing every task in docs/product-roadmap.md, in order, until all tasks are checked off.

Setup

Read docs/product-roadmap.md first — it is the source of truth for what to build and in what order. docs/prd.md is the technical spec behind it; docs/design.md holds the visual design tokens; docs/product-vision.md holds the product strategy. Do not load these documents wholesale — each phase lists the specific Reference sections to read, plus whatever a task's Notes line points to. If docs/product-roadmap.md or docs/prd.md is missing, stop and tell the user to run the Product Planner skill first (part of BuilderOS: https://github.com/BuildGreatProducts/builder-os).

Work loop

Repeat until every task in the roadmap is complete:

Sponsors

Details

Repository
github.com/buildgreatproducts/builder-os
Categories
Testing & QA, DevOps & CI/CD, Git & Pull Requests, Documentation, Productivity & Planning, Design & UI/UX
First seen
Jul 14, 2026

More from buildgreatproducts/builder-os

All 9
1alirezarezvani avatarreportalirezarezvani/claude-skillsGenerate test report. Use when user says "test report", "results summary", "test status", "show results", "test dashboard", or "how did tests go".1.6Kskills.sh installs
2daymade avatarpromptfoo-evaluationdaymade/claude-code-skillsConfigures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Py1.6Kskills.sh installs
3alirezarezvani avatartestrailalirezarezvani/claude-skillsSync tests with TestRail. Use when user mentions "testrail", "test management", "test cases", "test run", "sync test cases", "push results to testrail", or "imp1.6Kskills.sh installs
4kostja94 avatarconversion-optimizationkostja94/marketing-skillsWhen the user wants to improve conversion rates, run A/B tests, optimize funnels, or reduce friction. Also use when the user mentions "CRO," "conversion rate op1.4Kskills.sh installs
5forztf avataropenspec-implementationforztf/open-skilled-sddImplements approved specification proposals by working through tasks sequentially with testing and validation. Use when implementing changes, applying proposals1.4Kskills.sh installs
6neolabhq avataragent-evaluationneolabhq/context-engineering-kitEvaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring impro1.3Kskills.sh installs