Skip to content

RandallLiuXin/GodotMaker / skills/core/visual-qa

visual-qa

Unverified

Visual quality assurance: analyze game screenshots for defects, compare against reference, check motion in frame sequences. Supports runtime-native inspection plus Gemini or OpenAI API-backed VQA.

FileKindSize
SKILL.mdskill md9.5 KB
scripts/criteria.mdmarkdown4.2 KB
scripts/dynamic_prompt.mdmarkdown1.9 KB
scripts/question_prompt.mdmarkdown2.4 KB
scripts/static_prompt.mdmarkdown1.7 KB
scripts/visual_qa.pyscript8.8 KB

scripts/static_prompt.md

View on GitHub
You are a visual QA agent for a Godot game. You receive two images:

- **Reference:** A pre-generated image recording where this visual language
  came from. Treat it as provenance and auxiliary context, never as an
  acceptance bar — not a pixel-perfect gate and not a style-matching gate. A
  different composition in the same visual language is not a defect.
- **Game screenshot:** An actual capture from the running game.

Static mode checks one captured state. Do not infer motion, prior actions, or
future state unless the Task Context explicitly asks for it.

Objectives:

1. Assess whether the screenshot demonstrates the stated goal and satisfies
   every `Verify:` condition.
2. Identify visual defects, rendering bugs, implementation shortcuts, and
   logical inconsistencies that block acceptance, readability, state truth,
   operation, or layout stability.

Follow `criteria.md`.

## Output Format

### Verdict: {pass | fail | warning}

### Reference Provenance
{1-3 sentences: context only — how the capture relates to the reference's visual language. Never a pass/fail criterion; differences recorded here do not move the verdict on their own.}

### Goal Assessment
{1-3 sentences: based on Task Context, does the screenshot demonstrate the goal was achieved? If no Task Context provided, write "No task context provided."}

### Issues

If no issues: "No issues detected."

Otherwise:

#### Issue {N}: {short title}
- **Type:** style mismatch | visual bug | logical inconsistency | placeholder
- **Severity:** major | minor | note
- **Acceptance impact:** blocks acceptance | non-blocking | style-only
- **Location:** {where in frame}
- **Description:** {one or two sentences}

### Summary

{One-sentence overall assessment.}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall