Skip to content
Get packs

Test Evidence Review

Reviews the quality of a story's test files and manual evidence, not just whether they exist.

Source Download skill
Repository
Donchitos/Claude-Code-Game-Studios
Stars
32,965
Licence
MIT
Files
1 file

What it does

When asked, the agent reads a game development story's acceptance criteria and its test files or evidence documents, then judges whether the tests actually cover the important behaviour. Each story gets a verdict of ADEQUATE, INCOMPLETE, MISSING, or NOT ASSESSED, and the agent flags blocking gaps that would stop the story from being closed. It writes a summary in the chat and can optionally save a report file.

Great for

  • Developers on a game studio team preparing a story for QA hand-off or closure
  • Leads who want a quality check on test coverage beyond simple file existence
  • Teams using the Claude Code Game Studios workflow with sprint and story files

Skip it if

  • Projects that do not use this studio's story, sprint and config conventions, since the skill depends on those files and paths existing (it would report gaps or NOT ASSESSED)
  • Anyone expecting it to run the tests themselves; the shown SKILL.md only reads and reviews files, and the bundled config and receipt helper scripts are not included in the reviewed files
  • Non-developers looking for a general code-quality or security audit; it only assesses test and evidence documents

Try asking

  • “/test-evidence-review production/epics/combat/story-003.md”
  • “/test-evidence-review sprint”
  • “/test-evidence-review combat”
Step-by-step guide: how to use Test Evidence ReviewInstall, 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.

    test-evidence-review.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip test-evidence-review.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip test-evidence-review.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

  • Point it at a single story path first to see the output format before running it on a whole sprint.
  • Check the resolved qa.level and testing.strict settings, because they decide whether a gap is BLOCKING, ADVISORY or WAIVED.
  • Keep story files' Test Evidence sections up to date, since the skill reads those first before searching for files.

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.