mac-bottler
CLAUDE.md0 starsChanged 48 days agoMITView on GitHub
Read AGENTS.md first: it is the main instruction set (what this is, the commands, the rules, the skills, pull requests). This file adds only what is specific to Claude Code. The skills in .claude/skills/ load automatically; invoke them as slash commands: - /cook <game folder> [recipe name]: bottle a game end to end. - /diagnose <symptom>: known causes of a symptom and how to confirm each. - /improve-bottler <problem>: a generic fix to core/, tools/ or win/, test first, as…
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cookSkill
- diagnoseSkill
- improve-bottlerSkill
The file
We split this CLAUDE.md 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: line 16
Use them whenever a task matches, rather than working from memory.
- Very specific: line 26
When the player needs to run something themselves (a login, a game session), suggest !
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md 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
Claude Code in this project
Read AGENTS.md first: it is the main instruction set (what this is, the
commands, the rules, the skills, pull requests). This file adds only what is
specific to Claude Code.
Skills
The skills in .claude/skills/ load automatically; invoke them as slash commands:
/cook <game folder> [recipe name]: bottle a game end to end./diagnose <symptom>: known causes of a symptom and how to confirm each./improve-bottler <problem>: a generic fix tocore/,tools/orwin/, test first, as a pull request.
Use them whenever a task matches, rather than working from memory.
Working here
- Game launches and some builds outlive a tool call: run them in the background, and wait for a condition (the window appearing, the process ending) instead of sleeping for a fixed time.
- To see a game, use
build/bottler shot <png> --app <app>and read the image;build/bottler windows <app>shows where its windows are and whether they are on screen. - When the player needs to run something themselves (a login, a game session),
suggest
! <command>so its output lands in the conversation.
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.

