New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gum Codegen Test Rigor

by vchelaru in vchelaru/FlatRedBall

What actually proves a Gum-codegen fix works, vs. An agent skill from vchelaru/FlatRedBall.

MITAuto-check passedDevelopment

Install Gum Codegen Test Rigor

skills CLI
$ npx skills add vchelaru/FlatRedBall --skill gum-codegen-test-rigor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vchelaru/FlatRedBall gum-codegen-test-rigor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vchelaru/FlatRedBall.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gum-codegen-test-rigor .claude/skills/gum-codegen-test-rigor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gum-codegen-test-rigor
GitHub stars
578
Token cost
~952 tokens
SKILL.md length
476 words
Files
1
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

What actually proves a Gum-codegen fix works, vs. An agent skill from vchelaru/FlatRedBall.

  • Works in 4 steps: String-matching generated source… → Reflection-based member-contract checks… → Real compile against real assemblies… → …
  • Tasks that involve Project scaffolding
  • SKILL.md covers Verification strength ladder —…, The sharper landmine: matching…, Two separate axes — don't… and Related
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gum Codegen Test Rigor is an agent skill from vchelaru/FlatRedBall. What actually proves a Gum-codegen fix works, vs. what only looks like it does. Triggers: "tests pass but it's still broken", CS1061/CS0200/NRE surviving a green suite, verifying StandardsCodeGenerator/StateCodeGenerator/GueDerivingClassCodeGenerator changes.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Project scaffolding. The repository describes itself as: Cross-platform 2D game engine focused on ultimate productivity built in .NET. The licence is MIT.

When your agent uses it

  • Tasks that involve Project scaffolding

Example prompts

  • “tests pass but it”
  • “/gum-codegen-test-rigor”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. String-matching generated source (generatedSource.ShouldContain/ShouldNotContain(...)). Proves
  2. Reflection-based member-contract checks (GumRuntimeMemberContractTests). Proves a named member
  3. Real compile against real assemblies (BuildSmoke *CreationSmokeTests /
  4. Real instantiate-and-execute. Actually construct the generated runtime the way production code

What it can do on your machine

Read from SKILL.md and the folder at commit fa654ab. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gum Codegen Test Rigor loads about 952 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~952

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vchelaru/FlatRedBall at commit fa654ab, republished under its MIT licence (© vchelaru). 476 words, ~952 tokens.

Download SKILL.mdSave it as .claude/skills/gum-codegen-test-rigor/SKILL.md (or your agent's skills folder).
name
gum-codegen-test-rigor
description
What actually proves a Gum-codegen fix works, vs. what only looks like it does. Triggers: "tests pass but it's still broken", CS1061/CS0200/NRE surviving a green suite, verifying StandardsCodeGenerator/StateCodeGenerator/GueDerivingClassCodeGenerator changes.

Gum Codegen: What Actually Proves a Fix Works

Glue's Gum codegen (gum-codegen skill) emits C# source text with no compile-time link to the real runtime types it targets. That's why weak verification repeatedly looks green while real bugs ship — this skill is the record of that pattern recurring, so the next fix doesn't restart at the bottom of this list.

Verification strength ladder — each level misses a different bug class

From weakest to strongest, all four were tried in sequence on the same fix before it actually worked:

  1. String-matching generated source (generatedSource.ShouldContain/ShouldNotContain(...)). Proves text presence only. Misses everything about correctness.
  2. Reflection-based member-contract checks (GumRuntimeMemberContractTests). Proves a named member exists on the contained type, but only for patterns the check explicitly matches (e.g. a ContainedXxx.Member regex). Missed a base-class (GraphicalUiElement.RenderableComponent) assignment entirely — wrong access shape, so the pattern never matched it, so it never looked.
  3. Real compile against real assemblies (BuildSmoke *CreationSmokeTests / GumGeneratedCodeCompilesTests). Proves the generated code compiles. Says nothing about runtime behavior — code that compiles clean can still NRE the instant its constructor runs.
  4. Real instantiate-and-execute. Actually construct the generated runtime the way production code does, and run it. This is the only level that catches a construction-time NullReferenceException. Nothing weaker than this can.

If a fix "passed" at one level and still broke in the field, the next debugging step is always "move up this ladder," not "add another test at the same level."

Show full SKILL.md (237 more words)Show less

The sharper landmine: matching the real call path, not just reaching a level

Being at the top of the ladder isn't sufficient either — a test can compile-and-run and still miss the bug if it doesn't reproduce the exact parameters/state production code actually uses:

  • A BuildSmoke sweep silently defaulted GumProjectSave.Version, so it always exercised the v2 branch and never touched the v3 code path it was supposedly covering.
  • A fix worked when constructed with fullInstantiation: true, but every real screen/component instance is constructed with fullInstantiation: false (GumRuntime.ElementSaveExtensions.CreateGueForElement's default) — a test using the wrong flag stayed green while the real path NREs.

Before trusting any test at level 3 or 4, confirm it uses the same version flags, instantiation flags, and call path a real generated game project actually hits — not just some valid input. This is the single most expensive-to-rediscover fact in this list; everything else follows from it.

Two separate axes — don't conflate them when a run "looks stuck"

A test run that looks broken can be broken for two unrelated reasons: the test logic doesn't cover the real bug (this skill), or the environment is jammed (orphaned dotnet/testhost/MSBuild/ VBCSCompiler processes piling up across a long session — see glue-unit-test-bootstrap's standing cleanup rule). Diagnose which one you're looking at before changing test code.

  • [[gum-codegen]] — the two-pipeline skip-list mechanics this level of testing verifies.
  • [[glue-unit-test-bootstrap]] — process hygiene (bootstrap init, BuildSmoke filtering, orphaned-process cleanup) as opposed to test coverage.

© vchelaru, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gum-codegen-test-rigor of vchelaru/FlatRedBall.

Open the folder on GitHubat commit fa654ab

Compare with similar skills

Gum Codegen Test Rigor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gum Codegen Test Rigor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gum Codegen Test Rigor this skillvchelaru/FlatRedBall578—~952Automated safety check: PassMIT
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
PonytailDavidObando/gsharp5648 repos~1.7kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
Conductor Setupgemini-cli-extensions/conductor3.8k—~4.2kAutomated safety check: PassApache-2.0
Mirage VFS Adapter Authoringstrukto-ai/mirage3.7k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    564 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Run Nx Generator

    nrwl/nx

    Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes

  • Conductor Setup

    gemini-cli-extensions/conductor

    Scaffolds the project and sets up the Conductor environment.

    3.8k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Mirage VFS Adapter Authoring

    strukto-ai/mirage

    Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed

  • Siteboon Backend Module Standards

    siteboon/claudecodeui

    Enforces this repository's TypeScript backend module architecture under server/: feature folders, barrel exports, and where shared types and utilities belong.

    14k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from vchelaru/FlatRedBall

All 32 skills in this repo

  • Glue Live Game Testing

    vchelaru/FlatRedBall

    Testing GlueControl's embedded runtime (CommandReceiver, GlueControlManager) against a real running game process.

    578 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Glue Unit Test Bootstrap

    vchelaru/FlatRedBall

    Bootstrapping GlueUnitTests that touch GlueState.Self/GlueCommands.Self/ProjectManager.

    578 GitHub stars~4.3k tokensUpdated today
    Auto-check passed

  • Gluj Versions

    vchelaru/FlatRedBall

    A skill your agent uses when adding, modifying, or reasoning about Gluj/Glux file format versions, the GluxVersions enum, FileVersion checks, or anything that gates behavior on the version of a…

    578 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Gum Codegen

    vchelaru/FlatRedBall

    A skill your agent uses when working on Glue's Gum code generation — adding/removing/version-gating generated properties on Gum standard runtime types (NineSlice, Text, Container, Sprite, etc.), or…

    578 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Release

    vchelaru/FlatRedBall

    FRB1 (engine + Glue) release runbook — gh CLI sequence for Engine.yml/glue.yml, version scheme, release notes.

    578 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

  • Release Notes

    vchelaru/FlatRedBall

    Drafts FRB1 release notes from commits/PRs since the last release.

    578 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Gum Codegen Test Rigor

What does Gum Codegen Test Rigor do?

What actually proves a Gum-codegen fix works, vs. An agent skill from vchelaru/FlatRedBall. Gum Codegen Test Rigor is an agent skill from vchelaru/FlatRedBall. What actually proves a Gum-codegen fix works, vs.

When should I use Gum Codegen Test Rigor?

Gum Codegen Test Rigor fits situations like: tasks that involve Project scaffolding.

How do I install Gum Codegen Test Rigor in Claude Code?

Run `npx skills add vchelaru/FlatRedBall --skill gum-codegen-test-rigor -a claude-code`. Or copy the skill folder (.claude/skills/gum-codegen-test-rigor in vchelaru/FlatRedBall) into .claude/skills/gum-codegen-test-rigor in your project. Claude Code loads it when a task matches its description.

How do I install Gum Codegen Test Rigor in Codex?

Run `npx skills add vchelaru/FlatRedBall --skill gum-codegen-test-rigor -a codex`. Or copy the skill folder (.claude/skills/gum-codegen-test-rigor in vchelaru/FlatRedBall) into .agents/skills/gum-codegen-test-rigor in your project. Codex loads it when a task matches its description.

Can I use Gum Codegen Test Rigor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vchelaru/FlatRedBall --skill gum-codegen-test-rigor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gum-codegen-test-rigor, .gemini/skills/gum-codegen-test-rigor, .github/skills/gum-codegen-test-rigor and .opencode/skills/gum-codegen-test-rigor in your project.

What does Gum Codegen Test Rigor need to run?

SKILL.md names no scripts, command-line tools or credentials: Gum Codegen Test Rigor is instructions for the agent only.

Does Gum Codegen Test Rigor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gum Codegen Test Rigor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gum Codegen Test Rigor use?

Gum Codegen Test Rigor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gum Codegen Test Rigor use?

About 952 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gum Codegen Test Rigor?

Skills that share tags, products or a category with Gum Codegen Test Rigor: Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 564 stars), Run Nx Generator (nrwl/nx, 29k stars) and Conductor Setup (gemini-cli-extensions/conductor, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gum Codegen Test Rigor?

vchelaru (a GitHub user) maintains it in vchelaru/FlatRedBall, which has 578 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 8, 2026.

Source: vchelaru/FlatRedBall on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.