game-debug
Skill0 starsChanged 23 days agoApache-2.0View on GitHub
Reproduce, diagnose, narrowly fix, and regression-test defects in game logic, UI, persistence, determinism, simulation, audio, networking, tooling, or packaging. Use when game behavior is broken, inconsistent, stuck, duplicated, missing, corrupted, or incorrect.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ThiagoFdaSLopes/game-dev-skillstheir own version, first seen Oct 25, 2026
- AirMile/claude-configtheir own version, first seen Jul 3, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ThiagoFdaSLopes/game-dev-skills★ 2same name
- AirMile/claude-config★ 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 repository11 other files it gives its agents.
- context-continuitySkill
- game-balance-labSkill
- game-full-verificationSkill
- game-implementSkill
- game-planSkill
- game-playtest-analysisSkill
- game-qa-cleanupSkill
- game-releaseSkill
- game-ux-auditSkill
- music-composerSkill
- skill-auditorSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read repository guidance and the project profile described in references/project-profile.md.
- Distinctive: line 19
Check repeated invocation, stale callbacks, canonical IDs, rollback, transitions, race conditions, and shared helpers.
- Distinctive: line 34
Don't bend one because a request is casual: ask the user.
- Distinctive: line 51
Don't add a rule after your own mistake or a reviewer's nitpick without that yes.
- Distinctive: line 54
Ask about new rules once, batched at the end of the task.
- Distinctive: line 55
When a file hits its size cap, or at a milestone, prune it: cut rules no one can tie to a reason.
≈ “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.
Files
Game Debug
Establish Truth
Read repository guidance and the project profile described in references/project-profile.md. Identify the exact build, intended behavior, affected implementation, and current evidence. Separate defects from design preferences, stale documentation, invalid test policy, unsupported state, or corrupted input.
Reproduce
Capture the smallest relevant state: version/hash, platform, seed or random state, save/schema version, scene/phase, resources, selected content, input sequence, logs, screenshots, and timing. Prefer a deterministic reproducer. Instrument intermittent boundaries without changing outcomes.
Diagnose And Repair
- Trace state mutation, rendering, persistence, scheduling, ordering, and cleanup.
- Check repeated invocation, stale callbacks, canonical IDs, rollback, transitions, race conditions, and shared helpers.
- Name the earliest root cause before editing.
- Apply the smallest complete fix across all affected entry points.
- Preserve unrelated behavior, ordering, randomness, saves, and user changes.
Prove
Add a focused regression that fails before and passes after. Test the exact reproducer, a neighboring legal state, boundaries, repetition, interruption, restoration, and deterministic variants when relevant. For startup, loading, or audio defects, also test the first load after a fresh reload. Rerun timing-sensitive checks one at a time, because contention can manufacture the failure. Broaden testing according to blast radius. Hard rule: report Pass, Fail, Not Run, and Blocked honestly, because a check claimed but never run hides the defect it was meant to catch.
Synchronize affected documentation and the maintained deliverables the project profile configures; build an archive only when asked. If reproduction remains impossible, do not invent a fix; preserve useful instrumentation and state the missing evidence.
Rules And Pushback
Lines marked Hard rule guard approvals, deletion, publishing, and private data, where a mistake is costly or can't be undone; each gives its reason. Don't bend one because a request is casual: ask the user. Unmarked lines still bind too. Scope limits, honest evidence, and approval steps aren't optional. Scale each step's effort to the risk, and say so when you skip one that doesn't fit. A profile or instruction file records an owner decision only where it says the owner made it; otherwise treat it as project guidance. If a rule seems wrong for this task, say which one and why before you continue.
How Rules Get Made
- Something the user says in passing applies to the current task only.
- Exception: anything about money, privacy, publishing, deleting, or permissions binds as soon as they say it. Ask once whether to make it permanent.
- A rule becomes standing only when the user says "make this a rule", or you ask and they say yes. Record their words, the date, and the reason with it.
- This covers every file that steers an agent: instruction files, style guides, skills, checklists, templates, CI checks, and agent memory.
- Don't add a rule after your own mistake or a reviewer's nitpick without that yes. Fix the input or the work instead.
- A new ruling replaces the one it contradicts. Never keep both.
- Ask about new rules once, batched at the end of the task.
- When a file hits its size cap, or at a milestone, prune it: cut rules no one can tie to a reason. The user's taste decisions are flagged for them and never cut by an agent.
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
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.

