Game Dev Skill
2D Animation Pipeline
Unity 6 Animator + AnimationClip pipeline for 2D sprite projects convert Aseprite tags to…
$15
Game QA
Game QA physics, FPS and playtest
A game QA agent that validates maps and assets against a physics checklist, measures FPS, frame budget and thermals, runs touch-control playtests, and stress-tests edge cases. It produces nothing and accepts nothing on trust: maps, sprites and builds either clear the 12-item physics checklist and the FPS-and-thermal gate on baseline devices, or they go back with the failing items named.
$79 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Agent
- Category Game Dev
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
This agent builds nothing and approves or rejects everything. Maps face a 12-item physics checklist, builds face real devices and a 55 FPS floor, and the verdict comes back as one word with the proof attached.
- Invokes its five QA skills (asset physics rules, Y-sort, isometric constants, e2e testing patterns, accessibility) and frames the job as a gate: it produces nothing, it approves or rejects.
- Runs the 12-item asset-physics checklist as a script against the delivered scene: ground contact, leaning angles between 55 and 75 degrees, collider overlaps, shadow direction consistency, pivot (0.5, 0), Y-sort axis, center of mass, spill direction, density gradients, palette and light coherence. Anything under 12 of 12 goes back to the level designer with the failing items named.
- Profiles performance on real baseline devices, iPhone 13 and Galaxy A54: average FPS at or above 55, a 16.6ms frame budget, under 100 draw calls, then a 10-minute sustained playtest watching thermal state and battery drain. FPS below 55 or thermal serious means the build is rejected.
- Attacks the build adversarially: mutates the save file expecting the signature check to fail, spam-clicks every button hunting race conditions, drops the network mid-sync and validates every touch target sits inside the safe area at minimum size.
- Analyzes playtest funnels with cold players who have never seen the game: first 30 seconds hook, tutorial completion rate, drop-off peaks; numeric benchmarks quoted in reports are verified against official sources first, unverified ones are labeled as such.
- Returns a one-word verdict, APPROVE or REJECT, with test output as proof and every bug filed with repro steps, device, OS and build version, routed to whichever agent owns the fix.
One power source. 5 lines out.
game-qa · core
core active · 5 lines
- ✓ validating a new map's p…
Validating a new map's physics and render order before deploy
- ✓ measuring fps, frame bud…
Measuring FPS, frame budget and thermals on baseline devices
- ✓ playtesting touch controls
Playtesting touch controls and accessibility
- ✓ checking sprite animation
Checking sprite animation consistency
- ✓ stress-testing edge cases
Stress-testing edge cases before a build ships
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Catch physics and render bugs before players do
license: perpetual -
Builds that hold 60 FPS and stay cool on real phones
license: perpetual -
Accessible, playable controls verified by playtest
license: perpetual -
A clear approve/reject gate before any build ships
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Twelve-item asset-physics checklist run on every map hand-off
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Mobile game teams that need a hard quality gate before each build.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
We are a two-person studio without a QA department, does this agent replace that role for builds?
It covers the gating part of the role: every map hand-off runs the 12-item asset-physics checklist, builds get FPS, frame-budget and thermal telemetry on baseline devices, and touch controls go through thumb-zone playtests. What you still provide is the device access and the willingness to act on a REJECT verdict.
-
How does it judge a build, gut feel or measurable thresholds?
Measured gates only. A map either clears all 12 physics-checklist items or comes back with the failing items named; a build either holds the FPS and thermal targets on baseline devices or gets rejected. It accepts nothing on trust, including work from the other game agents.
-
Will it fix the bugs it finds or produce the corrected sprites and maps?
No, by design it produces nothing. It is a pure validation gate: PASS or FAIL with named failures. Fixes go back to whoever made the asset: the level designer for maps, the art pipeline for sprites, engineering for code, which keeps the gate honest.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.