Skip to content

QA Test Plan Builder

Builds a sprint, feature or story QA plan classifying tests by Logic, Integration, Visual and UI.

Stars
32,965
Licence
MIT
Files
1 file

What it does

When invoked, the agent reads the story files for a sprint, feature or single story, along with the design documents they reference, and classifies each story by test type (Logic, Integration, Visual/Feel, UI). It then writes a markdown QA plan saying what should be automated, what needs manual checking, the smoke-test scope, and when to involve a playtester. It is meant to run before a sprint starts so testing work is known upfront.

Great for

  • Teams using the Claude Code Game Studios structure who plan sprints and stories in production/ folders
  • Game developers who want a structured test plan derived from acceptance criteria before implementation begins
  • QA leads who need a consistent plan format across stories

Skip it if

  • Projects without the expected production/sprints and production/epics story structure, since the skill cannot find stories and will stop with NOT ASSESSED (no stories in scope)
  • Non-game software where the Visual/Feel and playtester categories do not apply and the output may be poorly matched to the need
  • Replacing actual test execution: it plans tests and writes a document but does not run a test suite

Try asking

  • “/qa-plan sprint”
  • “/qa-plan feature: combat”
  • “/qa-plan story: production/epics/combat/story-003.md”
Step-by-step guide: how to use QA Test Plan BuilderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    qa-plan.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip qa-plan.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip qa-plan.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run it before the sprint starts, as the skill itself recommends, so the plan informs implementation rather than documenting it afterwards
  • Use the feature: or story: argument to limit scope and keep the plan small
  • Check the MISSING and no-Edge-Cases notes in the output, since those flag gaps in the source stories or GDDs

What's inside

  • SKILL.md

Redistributed unmodified from Donchitos/Claude-Code-Game-Studios under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.