agentleFS
ckorhonenckorhonen/claude-skills/skills/poke-assistant/SKILL.md

poke-assistant

Skill17 starsChanged 4 months agoMITView on GitHub

Send messages and notifications to Poke (poke.com) via webhook API. Use when alerting the user, sending task completion notifications, status updates, reminders, or any message to their Poke assistant.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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
  1. Distinctive:

    Add to your shell profile:

    line 32
  2. Distinctive:

    When running tasks that take time, notify on completion:

    line 114
  3. Distinctive:

    Every small step (avoid notification fatigue)

    line 145
  4. Distinctive:

    Keep messages concise but informative

    line 150
  5. Distinctive:

    Use clear formatting for multi-line messages

    line 152
  6. Distinctive:

    Check your internet connection.

    line 175
  7. Distinctive:

    Verify your API key is correct

    line 179
  8. Distinctive:

    Check that messaging is enabled in your Poke settings

    line 180
  9. Very specific:

    Ensure your messaging channel (iMessage/SMS/WhatsApp) is configured

    line 181

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Poke Assistant

Overview

Send messages to your Poke assistant via the inbound webhook API. Poke is a conversational AI assistant that supports iMessage, SMS, and WhatsApp messaging. This skill enables Claude to send you notifications, alerts, and updates directly to your Poke.

When to Use

  • Notifying the user when a long-running task completes
  • Sending error alerts or warnings that need attention
  • Providing status updates on build, test, or deployment progress
  • Sending reminders or summaries
  • Alerting about important events (CI failures, security issues, etc.)

Prerequisites

  • Poke account at poke.com
  • POKE_API_KEY environment variable

Installation

Getting Your API Key

  1. Go to poke.com/settings
  2. Navigate to the Advanced section
  3. Generate or copy your API key
  4. Add to your shell profile:
echo 'export POKE_API_KEY="your-api-key"' >> ~/.zshrc
source ~/.zshrc

Quick Start

Send a simple message:

python scripts/send_message.py -m "Hello from Claude Code!"

Pipe content to Poke:

echo "Build completed successfully" | python scripts/send_message.py

Command Reference

python scripts/send_message.py [options]

Options:
  -m, --message TEXT    Message to send to Poke
  -v, --verbose         Show detailed output
  -h, --help            Show help message

Input:
  Message can be provided via -m flag or piped to stdin.
  If both are provided, -m takes precedence.

Exit codes:
  0  Success
  1  Missing message or API key
  2  API error (authentication, rate limit, etc.)
  3  Network error

Examples

Task Completion Alert

python scripts/send_message.py -m "Build completed: 42 tests passed, 0 failed"

Error Notification

python scripts/send_message.py -m "ERROR: Deployment to production failed. Check logs."

Pipe Command Output

git log --oneline -5 | python scripts/send_message.py -m "Recent commits:
$(cat)"

Status Update with Details

python scripts/send_message.py -m "Code review complete:
- 3 files changed
- 2 suggestions made
- Ready for merge"

Alert on Test Failure

npm test || python scripts/send_message.py -m "Tests failed! Check the output."

Workflow Integration

Notify After Long Tasks

When running tasks that take time, notify on completion:

# Run build and notify
npm run build && python scripts/send_message.py -m "Build finished successfully" \
  || python scripts/send_message.py -m "Build failed!"

Daily Summary

Send a summary of work done:

python scripts/send_message.py -m "Daily summary:
- Implemented user auth
- Fixed 3 bugs
- Updated documentation"

Best Practices

When to Send Notifications

  • Tasks taking longer than 2-3 minutes
  • Errors requiring user attention
  • Important milestones (deployment, release)
  • Security-related alerts

When NOT to Send

  • Routine operations that complete quickly
  • Every small step (avoid notification fatigue)
  • Sensitive information (credentials, tokens)

Message Guidelines

  • Keep messages concise but informative
  • Include actionable context (what happened, what to do)
  • Use clear formatting for multi-line messages

Troubleshooting

"POKE_API_KEY environment variable not set"

Set your API key:

export POKE_API_KEY="your-api-key"

Or add to ~/.zshrc for persistence.

"API returned 401: Unauthorized"

Your API key is invalid or expired. Generate a new one at poke.com/settings.

"API returned 429: Too Many Requests"

You're being rate limited. Wait a few minutes before sending more messages.

"Network error: Connection refused"

Check your internet connection. The Poke API requires network access.

Message not appearing in Poke

  • Verify your API key is correct
  • Check that messaging is enabled in your Poke settings
  • Ensure your messaging channel (iMessage/SMS/WhatsApp) is configured

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.