AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Gsp Ux Flow Audit

skill-mike007jd-game-superpowers-gsp-ux-flow-audit · by mike007jd

Use when auditing first-minute onboarding, menus, fail/retry flow, or player comprehension in a game.

↗ Repository
— No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-mike007jd-game-superpowers-gsp-ux-flow-audit

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Gsp Ux Flow Audit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Game UX Flow Audit

Goal

Audit the player journey and moment-to-moment experience flow, especially the first 30 seconds.

Outputs

Follow the gsp-orchestrator output strategy:

  • inline (default): present findings in conversation.
  • minimal or full: write to docs/game-studio/audit/ux-findings.md, docs/game-studio/audit/audit-summary.md, docs/game-studio/audit/scorecard.json.

Use:

  • ./shared/checklists/ux-flow-audit-checklist.md
  • ./shared/reference/first-30-seconds.md
  • ./shared/reference/audit-confidence-and-evidence.md

Evaluate

  • first actionable screen clarity
  • onboarding length and interruption cost
  • main verb discoverability
  • fail / retry / pause / resume flow
  • menu-to-play transitions
  • whether the UI or setup blocks the core loop

Evidence discipline

Tag each important finding with:

  • confidence: high, medium, or low
  • evidence: code, config, asset, screenshot, or inferred

Output style

Write findings in game-language, such as:

  • what the player understands too late
  • what the player is asked to do too early
  • where friction kills momentum

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills