DC godot-city-game-3d
Build, run, debug and ship 3D city games in Godot 4 — procedurally generated cities (block grids, districts, weighted building typologies, MultiMesh batching, facade shaders, terrain, day/night, landmarks), first-person controllers, headless verification, Blender-generated .glb assets, rigged character and animation packs, real OpenStreetMap-derived cities, WebAssembly export, and cloud GPU streaming on GCP. Use this skill whenever the work involves Godot or a .gd/.tscn/.gdshader/project.godot file; whenever someone wants to start, set up, clone onto a new machine, or stand up a 3D game or city generator; whenever they mention procedural city, city generator, block grid, building typology, MultiMesh, facade shader, terrain heightmap, navmesh, Godot export templates, export presets, headless Godot, .glb pipeline, Blender asset generation, character rigs or borrowed animations; and whenever they want to deploy or share a game — web export, SharedArrayBuffer/COOP/COEP, Selkies, pixel streaming, GPU VM, or "let people play this without installing anything." Reach for it even on vague asks like "get this running", "why is my city slow", "my model faces backwards", "make it work on a cloud machine", or "set this up somewhere else too" when a Godot 3D project is in play.
Promises a full stack for 3D cities in Godot 4: procedural block generation, building typologies, MultiMesh batching, facade shaders, day-night cycles, animated characters, WebAssembly export, and GPU streaming. Contains 22 files with 14 GDScript files. Verification found dangerous commands (high severity) plus two medium-level issues. Code quality scored 68, process score 63. No model runs or sandbox tests completed. Description is truncated with lint errors. The skill may handle some tasks, but unsafe code and lack of working validation make it unreliable for production use.
Skip it until the author fixes critical issues and demonstrates working examples.
Build, run, debug and ship 3D city games in Godot 4 — procedurally generated cities (block grids, districts, weighted building typologies, MultiMesh batching…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
-
high Dangerous commands
cmd-disable-securityscripts/install_godot.sh:42Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy)xattr -dr com.apple.quarantine /Applications/Godot.app 2>/dev/null || true
Medium and low: 2
-
medium Dangerous commands
cmd-disable-securityreferences/troubleshooting.md:14Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (quoted — discussed, not commanded)Quarantine flag on a manually downloaded app. `xattr -dr com.apple.quarantine
quoted -
low Dangerous commands
cmd-background-processscripts/cloud/setup_host.sh:104Starts a background / autostarted processsystemctl enable godot-stream
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1284 chars, limit 1024
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3297 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1284: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 10 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.