Is the Game Experience Analyzer skill free?

Yes. The skill itself is free from DY-2026/GameDesignOS. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Game Experience Analyzer SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Game Experience Analyzer?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Game Experience Analyzer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Game Experience Analyzer

Turns game screenshots and PVs into evidence-linked Chinese design diagnosis reports

by DY-2026 · DY-2026/GameDesignOS

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 6a863a8

Fetched SKILL.md + README; spot-checked 3 referenced files (references/sample-scope-gate.zh-CN.md, templates/experience-report.md, references/genre-strategy-router.yaml) — all HTTP 200; frontmatter parses with name+description and includes a Source Safety anti-injection clause, no curl|sh/base64/exfil smells. Ran the real task: downloaded two bundled example screenshots (survival33 welfare-popup + ui-density), viewed them, then produced a baseline analysis (no skill) and a skill-following analysis. Baseline was flat prose with zero evidence IDs and asserted unverifiable claims as fact; the skill version front-loaded a Sample Scope Gate marking operation-feel/pacing/loop/retention as unjudgeable from static images, built a 5-row evidence index tied to visible on-screen text, added visual-evidence-cards with confidence levels, and downgraded combat-feel to low and the monetization-interruption question to unsupported_by_sample.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Game Experience Analyzer does

Analyzes game screenshots, screen recordings, trailers/PVs, paid-ad creatives, store pages, and video links into evidence-first Chinese diagnosis reports, enforcing a sample-scope gate, an evidence index with per-claim IDs, mode routing, and genre-sensitive validation plans. Triggers on Chinese requests to analyze gameplay footage, early-game experience, mechanics, full teardowns, MDA, single-player pacing, or trailer virality potential. Outputs are constrained to what the sample can actually support, downgrading unverifiable claims to uncertain/unsupported.

How to install Game Experience Analyzer

git clone --depth 1 https://github.com/DY-2026/GameDesignOS.git /tmp/game-experience-analyzer-src
mkdir -p ~/.claude/skills
cp -R /tmp/game-experience-analyzer-src/game-experience-analyzer ~/.claude/skills/game-experience-analyzer
# SKILL.md lands at ~/.claude/skills/game-experience-analyzer/SKILL.md
# Pure methodology skill: no API keys required. Reports are written in Chinese.
# Optional for video-link/recording analysis: ffmpeg and yt-dlp (skill degrades gracefully and labels unknowns if absent).
# Bundles references/ (routers, lenses), templates/ (report + JSON schemas), examples/, evals/ — all included by the cp above.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Game Experience Analyzer

/game-experience-analyzer Turns game screenshots and PVs into evidence-linked Chinese design diagnosis reports

It also activates on plain-language prompts like these:

Analyze this gameplay recording for design flaws
Diagnose this store page's conversion issues
Review this trailer against genre expectations

Frequently asked questions

Is the Game Experience Analyzer skill free?: Yes. The skill itself is free from DY-2026/GameDesignOS. SkillProof publishes the install command and an independent test verdict at no cost.
Does Game Experience Analyzer work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md + README; spot-checked 3 referenced files (references/sample-scope-gate.zh-CN.md, templates/experience-report.md, references/genre-strategy-router.yaml) — all HTTP 200; frontmatter parses with name+description and includes a Source Safety anti-injection clause, no curl|sh/base64/exfil smells. Ran the real task: downloaded two bundled example screenshots (survival33 welfare-popup + ui-density), viewed them, then produced a baseline analysis (no skill) and a skill-following analysis. Baseline was flat prose with zero evidence IDs and asserted unverifiable claims as fact; the skill version front-loaded a Sample Scope Gate marking operation-feel/pacing/loop/retention as unjudgeable from static images, built a 5-row evidence index tied to visible on-screen text, added visual-evidence-cards with confidence levels, and downgraded combat-feel to low and the monetization-interruption question to unsupported_by_sample.
What is the Game Experience Analyzer SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Game Experience Analyzer?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Game Experience Analyzer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.