This is Amazon's Working Backwards methodology implemented as a coaching gauntlet. You walk in with a product idea, get pushed through writing the press release before you build anything, then answer the hardest customer and internal questions until the concept either holds up or breaks. The coaching is deliberately tough: vague thinking gets challenged, technology-first pitches get redirected to customer problems, and you don't move forward until you can articulate who this is for and why they care. It includes headless mode for autonomous first-draft generation and automatically researches competitive context to ground your claims in reality. Good for forcing clarity before you waste resources building the wrong thing.

skills.sh installs
14K
GitHub stars
55.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add bmad-code-org/bmad-method --skill bmad-prfaq --agent claude-code

Installs into .claude/skills of the current project.

Files

This is Amazon's Working Backwards methodology implemented as a coaching gauntlet. You walk in with a product idea, get pushed through writing the press release before you build anything, then answer the hardest customer and internal questions until the concept either holds up or breaks. The coaching is deliberately tough: vague thinking gets challenged, technology-first pitches get redirected to customer problems, and you don't move forward until you can articulate who this is for and why they care. It includes headless mode for autonomous first-draft generation and automatically researches competitive context to ground your claims in reality. Good for forcing clarity before you waste resources building the wrong thing.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/bmad-code-org/bmad-method
First seen
Jun 3, 2026

More from bmad-code-org/bmad-method

All 41

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs