tell-grokbot
Skill21 starsChanged 41 days agoMITView on GitHub
Send a message to the user's Grok bot primary agent through a routine webhook, e.g. to delegate a task or pass on information for later. Use only when the user explicitly asks to tell, notify, or send something to Grok bot.
- Reads credentials
In this repository5 other files it gives its agents.
- address-pr-reviewSkill
- implementSkill
- interviewSkill
- unslop-frSkill
- unslopSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 22
Write it in the user's language.
- Very specific: line 26
Run the helper script located in this skill's directory (the directory containing this SKILL.md), with the message on stdin:
- Distinctive: line 38
If a sandbox blocks network access, ask the user for permission to run the script outside the sandbox.
≈ “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
Request:
$ARGUMENTS
Send a message to the user's primary Grok bot agent. Only do this when the user explicitly asked for it.
Step 1: Write the message
Grok bot has no access to this conversation or to the repository, so the message must be self-contained:
- the project or product it is about
- what happened, or what Grok bot should do
- useful links (pull request, issue, documentation, feature URL)
Write it in the user's language. If the user dictated the content, keep their words. Don't ask the user to review the message: send it directly.
Step 2: Send it
Run the helper script located in this skill's directory (the directory containing this SKILL.md), with the message on stdin:
bash <skill-directory>/send.sh <<'EOF'
<message>
EOF- Exit code 0: Grok bot received the message.
- Exit code 2: the configuration is missing or incomplete. Follow the setup below, then send again.
- Exit code 1: the request failed. Do not retry, as the message could arrive twice.
If a sandbox blocks network access, ask the user for permission to run the script outside the sandbox.
Step 3: Report
Show the user the message you sent and the result. If the request failed, include the error printed by the script.
Setup
The webhook URL and Bearer key are stored in ~/.config/grokbot/webhook.env.
Ask the user for them. In Grok bot, they are in the routine's panel: open the agent's name at the top of the chat → Tasks → the routine → Webhook section. If the user has no routine yet, tell them to create one with a webhook trigger.
Then create the file, readable only by the user:
mkdir -p ~/.config/grokbot
touch ~/.config/grokbot/webhook.env
chmod 600 ~/.config/grokbot/webhook.env
cat > ~/.config/grokbot/webhook.env <<'EOF'
GROKBOT_WEBHOOK_URL=<url>
GROKBOT_WEBHOOK_KEY=<key>
EOFDoes 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.