Sandbox
@TechNomadCode/AI-Product-Development-Toolkit

Product prompts and Claude Code rules for AI planning

This toolkit gives you guided prompts and agent instructions for product work with AI. It covers the early steps from research and PRDs to MVP scope, UX flows, test plans, and session handoffs, using plain Markdown files you can copy into any chat.

959 stars163 forksUpdated 7d ago
Who it's for

Builders who want structured AI help for product definition, MVP planning, and keeping work consistent across sessions.

What it delivers

You can turn rough ideas into reviewable product specs and handoffs without re-explaining the project each time.

What it does

PRD generation

A guided prompt that turns rough notes, users, and constraints into a draft Product Requirements Document.

MVP concept and planning

Templates for choosing a first release, defining scope, and writing an MVP development plan or ultra-lean build spec.

UX and user flow prompts

Prompts for mapping user journeys and interface requirements before building.

Research and test planning

Templates for user research questionnaires and test plans with acceptance criteria.

Session continuation

A prompt for summarizing decisions, progress, and next tasks into a handoff for a fresh chat.

Claude Code instructions

Claude Code desktop rule files and guardrails for concise responses, task scope, and tool use.

README

AI Product Development Toolkit

Free prompts and agent rules for building software with AI: clarify what to build, keep the work focused, and carry project decisions into the next session.

Copy a prompt into your AI chat, answer its questions, and review the resulting specification or handoff. The templates are Markdown files; you can use them without cloning this repository or installing a package.

Start here

What you needOpen thisWhat to bringWhat you get
Turn an app idea into clear requirementsPRD prompt · GuideRough notes, intended users, and constraintsA draft Product Requirements Document built through questions and confirmation
Give your coding assistant clear working rulesClaude Opus 5 rules · Setup guideYour existing project instructions and the matching modelInstructions for concise responses, task scope, and tool use
Continue a project in a fresh AI chatSession-continuation prompt · GuideThe current conversation, while its history is still availableA reviewable handoff with decisions, progress, and remaining tasks

Try the PRD prompt

  1. Open the PRD prompt file and copy its contents.
  2. Replace the text between BRAINDUMP START and BRAINDUMP END with your idea; fill or remove the other bracketed placeholders.
  3. Paste the prompt into your AI chat, answer the questions, and confirm the decisions before asking for the final draft.

Already have a PRD and a concise MVP concept? Use the ultra-lean build prompt to define the first build's purpose, features, and technical approach.

Choose your next step

You can enter at the step you need; each folder explains its required inputs.

StepResourceOutput
Plan user researchResearch questionnaireQuestionnaire draft, then an evidence-linked PRD input from collected responses
Define the productPRD generationGoals, users, requirements, and constraints
Map the experienceUX and user flowUser journeys and interface requirements
Choose the first releaseMVP conceptCore problem, hypothesis, and limited feature scope
Plan the buildMVP development plan or ultra-lean build specificationDetailed development plan or a smaller build specification
Plan verificationTest planTest scope, cases, and acceptance criteria
Prepare a visual briefv0 design promptsA design prompt using your UX specification and MVP scope
Prepare the next sessionSession continuationCurrent state, corrections, and next tasks

For the full instructions, see the prompt template guide.

Configure your coding assistant

The agent configuration guide separates behavioral instructions from tool permissions:

The prompts use guided questions, confirmation points, and inputs from earlier steps to help you make explicit decisions. Outputs remain drafts: review requirements, code, and handoffs before relying on them, and remove private information you do not need to share with your AI tool.

Star this repository to save it for your next project. If you find an unclear step, open an issue with the template name and a small, non-sensitive example.

About and license

I develop these resources using official documentation, AI tools, and my own software development work. My separate Prompt Rulebook covers broader prompting techniques.

This toolkit is free to use, adapt, and share under the MIT license.

Files in the repo

Repository payload6 top-level entries
  • .github
  • agent-configs
  • prompt-templates
  • .gitignore
  • LICENSE
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More rules & prompts

All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

13k
wanshuiyin/
HERO-Anti-OverDefense

HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.

444
ilindaniel/
ponytail-lite

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

171
repowise-dev/
claude-code-prompts

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

1.2k