mirror of https://github.com/TechNomadCode/AI-Product-Development-Toolkit.git synced 2026-10-20 08:39:44 +02:00

Files

T

TechNomadCodeandClaude Opus 5.5 30b9b8cf55 Give each planning step one name and make the guides easier to follow

- Rename prompt-templates/ to planning-prompts/ with numbered step
  folders, so GitHub lists them in workflow order. Folder, prompt file
  and skill now share one name per step (2-prd/prd.md is /prd).
- Merge the full and ultra-lean MVP plan prompts into 5-mvp-plan/, as
  the /mvp-plan skill already did.
- Rename the /mvp skill to /mvp-scope; the installer removes an earlier
  mvp install and tells the owner about the new name.
- Rename agent-configs/claude-code-desktop/ to agent-configs/claude-code/,
  since the rules apply to the terminal too.
- Rewrite each prompt guide in one short layout with previous and next
  links, drop outdated model and temperature advice, and fix the copied
  "final PRD draft" lines and the claimed v0.dev section.
- Point to GitHub's Copy raw content button for copying a prompt.
- Move the AI App Starter details from the root README into the starter
  guide, add the skills to the top table, and align the test plan
  wording with what the prompt produces.
- Add issue forms, a Discussions link and a short contributing guide.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-12 14:57:27 +02:00

README.md

Give each planning step one name and make the guides easier to follow

2026-10-12 14:57:27 +02:00

test-plan.md

Give each planning step one name and make the guides easier to follow

2026-10-12 14:57:27 +02:00

README.md

Test plan prompt

Step 6 of the planning prompts. The AI helps you plan how to test a feature, a release or your MVP.

Prompt: test-plan.md

What you get

A test plan outline:

The objective, and what's in and out of scope
The features to test
The kinds of testing and the approach, such as functional, usability, performance or security, manual or automated
Test environments and test data
Who runs the tests, and how bugs are reported
What the testing produces, such as test cases and reports
Entry and exit criteria: when testing can start, and when it's done
Risks to the testing and how to handle them
Optionally, tools and a schedule

It's an outline, not a list of test cases. Write those from it afterwards, or ask the AI to in the same chat.

What to bring

What to test (required): the features, requirements, user stories or MVP spec for this round of testing. Add context from your PRD if it helps.
Constraints (optional): fill in the bracketed line under TONE & CONSTRAINTS, such as limited time, no dedicated testers or a required bug tracker, or delete it.

How to use it

Open test-plan.md and copy it with the copy button at the top right of the file (Copy raw content).
In a text editor, replace the example between --- SCOPE START --- and --- SCOPE END --- with what you want to test.
Paste it into a new AI chat and answer its questions. It starts with the objective and scope, then moves through the rest of the plan.
When it offers to write the outline, say yes. Review it and save it as a Markdown file.

In Claude Code or Codex? The /test-plan skill runs this same prompt and fills it in from your files.

Good to know

Be specific about scope. The clearer the list of what's in, the more useful the plan.
Update the plan as requirements change or bugs turn up.

Next step

This is the last planning step. Ready to build? The AI App Starter builds a web app with you, step by step, using the documents you made.

← Previous: MVP build plan · All planning prompts