check
Skill2 starsChanged 13 days agoMITView on GitHub
Verify a Godot game yourself before reporting: script errors, screenshots you actually look at, real input replayed into the running game (touch, mouse, keys), other aspect ratios, and video recording. Use after changing code, scenes or UI in a Godot project, and for "check it", "take a screenshot", "does it still work", "record a demo", "does it break on a tall phone". For "would a new player understand this" use the playtest skill. 「確認して」「スクショ撮って」「動くか見て」「録画して」などで使う。
- Reads credentials
87 other projects use a version of this.
Adopted by
Most recently taken up by
- brquatti/readme-styletheir own version, first seen Nov 15, 2026
- congptvinadic-debug/token-diettheir own version, first seen Nov 15, 2026
- aldohushi1-stack/glassboxtheir own version, first seen Nov 15, 2026
- stericishere/skillstheir own version, first seen Nov 15, 2026
- nrzz/claude-windows-doctortheir own version, first seen Nov 15, 2026
- warrendeanlangeveldt/code-kittheir own version, first seen Nov 15, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions87 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 87
- tw93/Waza★ 7.6ksame name
- tw93/claude-health★ 7.5ksame name
- katanemo/archgw★ 7.1ksame name
- katanemo/plano★ 7.1ksame name
- tokio-rs/topcoat★ 6.4ksame name
- Giskard-AI/giskard-oss★ 5.9ksame name
- VibiumDev/vibium★ 3ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
77 more not listed
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 repository7 other files it gives its agents.
- template/CLAUDE.mdCLAUDE.md
- template-ja/CLAUDE.mdCLAUDE.md
- assetsSkill
- newSkill
- playtestSkill
- rulesSkill
- steam-tagsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 74 edited versions we read keep these.
2
Distinctive
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: line 13
Run these inside the game's folder.
- Distinctive: line 34
Screenshot what you changed and read the image: Look for: broken layout, overlapping or unreadable text, blown-out highlights, blank areas, …
- Very specific: line 39
Use --move to check hover states.
“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify a Godot game
Run these inside the game's folder.
godot-kit check # the game's tools/check.sh if it has one, else the script-error check
godot-kit parse # script errors only
godot-kit shot shots/title.png --after 2 # one screenshot
godot-kit shot shots/play.png --after 3 --every 1 --count 8 -- --demo # numbered frames + a contact sheet (play_sheet.jpg)
godot-kit shot shots/tall.png --after 2 --res 720x1560 # another aspect ratio
godot-kit shot shots/t.png --after 1 --every 1 --count 6 -- --tap=360,1100,2 --key=Enter,4 # replay input
godot-kit record 45 # 45 s of --demo as a small mp4shot opens a real window (muted, always on top) and quits after the last frame. Everything after -- goes to the game.
It needs the Shot autoload; if the game lacks it, the command says how to add it (see the new skill).
Input replay arguments (viewport coordinates, seconds since launch; repeat as needed):
--tap=x,y,sec --hold=x,y,sec[,length] --swipe=x1,y1,x2,y2,sec --click=x,y,sec --move=x,y,sec --key=Name,sec[,length]
Procedure
- Run
godot-kit check. Fix failures before going further. - Screenshot what you changed and read the image. Look for: broken layout, overlapping or unreadable text,
blown-out highlights, blank areas, and whether pressable things look pressable. For motion, take numbered frames and
read the contact sheet. Reach specific moments with the game's own arguments (
--demo,--seed, ...; see its README). - If layout changed, shoot other ratios. Portrait mobile:
--res 720x1280,720x1440,720x1560,720x1600. - If controls changed, press them for real and shoot before and after, so the reaction is visible in the frames.
Use
--moveto check hover states. Self-play does not catch input bugs. - For a change that should not alter behavior, compare seeded self-play logs from before and after, if the game has that mechanism.
- Report what the images showed, with their paths. Do not write "verified" for anything you did not look at.
Good to know
--headlessdoes not draw. It is only for script errors and logic tests.- Each launch starts the game clock at zero. For a time-driven game, verify a sequence inside one launch.
- Godot is chosen in this order:
GODOT_CMDinkit.env, the game'stools/godot,GODOT_KIT_GODOTin the user config,godoton PATH.godot-kit doctorshows what is missing. - On Linux a display is required (a desktop session or xvfb). Only macOS has been tested so far.
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.

