package-bot
Skill0 starsChanged 5 months agoMITView on GitHub
Package a finished bot into a clean zip for handing to someone else to run or host. Use this when the user runs /package-bot, or asks to zip, package, export, or share a bot so another person can deploy it. Produces a zip with the code and config but no secrets and no installed dependencies.
- Reads credentials
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bot-styleSkill
- check-botSkill
- deploy-to-cloudSkill
- deploy-to-hostSkill
- discord-styleSkill
- edit-botSkill
- keep-runningSkill
- list-botsSkill
- make-botSkill
- remove-botSkill
- rotate-secretSkill
- security-checkSkill
- skillsSkill
- telegram-styleSkill
- test-botSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 19
If no bot was named above, look in the bots/ folder (older bots may sit at the project root.
- Distinctive: line 32
Put the zip in a dist/ folder inside the project (create the folder if needed), named after the bot, and tell the user the exact path to it.
- Distinctive: line 44
Keep it minimal and beginner-friendly.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
package-bot
Package a bot the user already made into a single zip that another person can unzip and run. Read the bot-style skill first so you know which files a bot has.
Talk to the user as if they are not a programmer. Use plain language.
The bot the user wants to package:
$ARGUMENTS
Work through these in order.
- If no bot was named above, look in the bots/ folder (older bots may sit at the project root; check there too), list the bots by name, and ask which one to package. Wait.
- Build a zip of that bot containing only what the recipient needs to run it: the source code,
package.json, tsconfig.json, .env.example, the README, and .gitignore. Leave out three things:
- the .env file, because it holds the secret token and a secret must never travel in a zip,
- the node_modules folder, because the recipient reinstalls it,
- any runtime files the bot created while running (logs, saved tallies, or other state), because the recipient should start fresh. A plain zip would include everything in the folder, so build the file list deliberately rather than zipping the whole folder as-is.
- Put the zip in a dist/ folder inside the project (create the folder if needed), named after the bot, and tell the user the exact path to it.
- Finish in plain language with no emoji:
- confirm what the zip contains and, just as importantly, that it does not contain the token,
- remind the user to send the token to the recipient through a safe, separate channel, never inside the zip,
- in one or two lines, restate how the recipient runs it: unzip, run npm install, copy .env.example to .env and add the token, then npm start (and on a host, keep it running with a process manager),
- mention the zip is a throwaway they can delete after sending and should not commit.
Keep it minimal and beginner-friendly. Never include a secret in the package.
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.

