test-bot
Skill0 starsChanged 5 months agoMITView on GitHub
Run a bot once, right now, so the user can see it work without waiting for its real schedule. Use this when the user runs /test-bot, or asks to test, try, or dry-run a bot, or to make it fire now instead of waiting. Confirms the bot starts cleanly and fires its action immediately, then leaves the real schedule untouched.
- 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
- package-botSkill
- remove-botSkill
- rotate-secretSkill
- security-checkSkill
- skillsSkill
- telegram-styleSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 20
If no bot was named above, look in the bots/ folder (older bots may sit at the project root.
- Distinctive: line 23
Make sure it can run: dependencies installed and the secret present in .env.
- Distinctive: line 27
Run the bot and watch its startup.
- Distinctive: line 37
Stop the test run when done.
- Distinctive: line 41
Keep it plain 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
test-bot
Let the user see a bot work right now, without waiting for its scheduled time. Read the matching style skill (discord-style for Discord, telegram-style for Telegram) first so you know how the bot is built.
Talk to the user as if they are not a programmer. Use plain language.
The bot the user wants to test:
$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 test. Wait.
- Make sure it can run: dependencies installed and the secret present in .env. If something is missing, say what, and stop. If the bot is plainly broken rather than just untested, check-bot is the better tool.
- Run the bot and watch its startup. Confirm in plain language that it starts cleanly: it loads its secret, connects or gets ready to send, can reach its target channel or chat, sets up its schedule, and shows no errors. This alone proves the setup is sound and it will work when its real time comes.
- To let the user see the actual action now (the post, the report), fire it once immediately. Do this without permanently changing the bot: trigger the action a single time for this test, and make sure the bot is left exactly as it was afterward, with its real schedule and any saved data untouched. Tell the user plainly that this was a one-off test fire, not a change to the schedule.
- Stop the test run when done; it does not need to keep running. Tell the user, in plain language, what happened: whether the message or report appeared where it should, and that the bot's normal schedule is unchanged. If you used a temporary trigger, confirm you removed it.
Keep it plain and beginner-friendly. Never leave the bot modified after a test; restore it to exactly how it was.
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.

