DECRUX9812DECRUX9812/hermes-plugin-gameforge/skills/playtesting/SKILL.md

playtesting

Skill44 starsChanged 22 days agoMITView on GitHub

Playtest builds and turn reports into fixes.

2 other projects use a version of this.

Adopted by

Most recently taken up by

poorvith-mp/skills-gamedevtheir own version, first seen Aug 19, 2026
smileynet/game-spicetheir own version, first seen Feb 17, 2026

Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
poorvith-mp/skills-gamedev★ 4same name
smileynet/game-spice★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- 3d-asset-pipelineSkill
- blender-pipelineSkill
- game-audioSkill
- game-reverse-engineeringSkill
- game-studioSkill
- godot-devSkill
- pixel-art-pipelineSkill
- ship-itSkill
- unity-devSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
After any gameplay change, before any export, and whenever the user asks "is it fun / does it work".
line 22
Very specific:
Run, then read report.md with read_file and look at moments.jpg with vision_analyze.
line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Playtesting Skill

forge_playtest plays the build (headless Chrome for web builds, a bot for Godot) and reports where it breaks or gets boring. This skill covers choosing a policy, reading the report and fixing what it finds.

When to Use

After any gameplay change, before any export, and whenever the user asks "is it fun / does it work".

Prerequisites

Chrome, Chromium or Edge for web builds (auto-detected; set browser_path otherwise). Godot 4 for target=godot; screenshots=true there needs a display or xvfb-run.

How to Run

Smoke + design pass: forge_playtest target=web duration=90 (policy explorer).
Crash hunting: policy=monkey duration=120.
Human-like notes: policy=agent goal="find the chest" — your vision model plays and comments. Costs tokens.
Long-session balance: forge_playtest target=godot duration=600 (10 minutes of game time in ~15 s).
Any web game, not just GameForge's: pass a URL or a build directory as target.

Quick Reference — signals

Issue	Meaning	Usual fix
Runtime error (critical)	uncaught exception / console error	fix the line in the stack trace
Player got stuck (major)	position frozen while moving	collision gap, spawn inside a wall, map hole
Input had no visible effect	screen frozen under input (no telemetry games)	focus/start-screen bug, crash
Frame-rate drops / slow frames	p5 FPS < 30, Godot p95 > 16.7 ms	too many particles/props, per-frame allocations
Nothing happens	≥ 20 s without a game event	dead zone; add pickups/enemies/landmarks
Low-novelty stretch	the screen kept repeating	scenery variety, new areas, pacing
Too hard / too easy	deaths per minute / damage-free wins	tune `game.json`

Procedure

Run, then read report.md with read_file and look at moments.jpg with vision_analyze.
Fix criticals first, then majors; re-run with the same seed to confirm the fix.
Change one tuning value at a time for design issues and compare reports.
Telemetry makes reports richer: a custom game can publish window.__gameforge = {controls, state, events} (see the GameForge web template's game.js).

Pitfalls

One run is a sample. For balance decisions run 3 seeds and compare.
The explorer is not a good player; "too hard" from it means "hard for a newcomer", which is useful.

Verification

The re-run report no longer lists the issue, and the verdict improved or held.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free