Run any Skill in Manus with one click

openclaw-message

Stars1

Forks0

UpdatedMay 23, 2026 at 20:57

Send a message to Michael's OpenClaw / "puffin" agent (the WhatsApp/Telegram bot running on EC2) and get its reply back. Use whenever Michael wants to talk to, ping, test, ask, or relay something to his openclaw/puffin/clawdbot agent, or check whether the agent is responding — e.g. "ask my openclaw bot to…", "ping puffin", "is the agent replying?", "have my bot draft…". Also use to message a specific persona agent (openclaw/michael, openclaw/art, etc.).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

mshuffett

mshuffett/dotfiles

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name

openclaw-message

description

Messaging the OpenClaw agent

This sends a chat message to Michael's OpenClaw agent on EC2 and prints the reply.

How it works (and why it's indirect)

The bot's public OpenAI-compatible endpoint is currently broken — the puffin wrapper (apps/wrapper/src/server.js, port 80 → http://34.236.245.154/v1/...) hangs on every completion. The gateway behind it is healthy, but it only listens on 127.0.0.1:18789 inside the container and its auth token is regenerated on every restart. So the script reaches the gateway directly via AWS SSM: it reads the current token from the gateway's startup log, then pipes the request through docker exec to 127.0.0.1:18789.

If the wrapper proxy ever gets fixed (or the image rebuilt), prefer the public /v1/chat/completions endpoint instead — it's simpler. Until then, use this.

Usage

python3 scripts/send.py "your message here"
python3 scripts/send.py "draft a reply declining politely" --agent openclaw/michael
python3 scripts/send.py "ping" --raw          # full JSON response

Default agent/model is openclaw/default. Other personas: openclaw/michael, openclaw/michael-bot, openclaw/art, openclaw/miranda, openclaw/founders.
The script handles the SSM round-trip and prints just the assistant's text (use --raw for the full response).
Responses can take 20–90s (the agent runs a full turn), so be patient.

Prerequisites / facts

AWS account 636160605813, region us-east-1, instance i-02cef0acfa720d57b (Name puffin-openclaw, container puffin-openclaw-1).
Uses the custom SSM document PuffinRunShell (this account has AWS-managed SSM docs stripped, so a custom run-shell document was created). If SSM calls fail with InvalidDocument, recreate it: aws ssm create-document --name PuffinRunShell --document-type Command --document-format JSON --content '{"schemaVersion":"2.2","description":"run shell","parameters":{"commands":{"type":"StringList"}},"mainSteps":[{"action":"aws:runShellScript","name":"run","inputs":{"runCommand":"{{ commands }}"}}]}'
The agent's default model is openai-codex/gpt-5.4 (codex OAuth) with amazon-bedrock/...opus... as fallback.

Troubleshooting

Empty reply / timeout: the agent turn may be slow or wedged. Check the container: aws ssm send-command --region us-east-1 --instance-ids i-02cef0acfa720d57b --document-name PuffinRunShell --parameters 'commands=["docker logs --tail 30 puffin-openclaw-1"]'.
401: the gateway token rotated mid-call; just retry (the script re-reads it each run).
The WhatsApp channel is logged out (openclaw channels login needed) — unrelated to API messaging.

More from this repository

same repository

coach

mshuffett/dotfiles

Michael's operating + emotional coach. Operational mode — daily startup/shutdown, weekly review, pomodoro, inbox capture, daily notes (auto-loads in ~/ws/notes). Emotional/decision mode (Joe Hudson style) — use on "coach me"/"joe coach", stuck/looping/overthinking, harsh self- or other-judgment, a binary either/or decision that won't resolve, or fear, shame, loneliness, anxiety, burnout, or grief, when Michael wants to be met in a feeling rather than handed advice. Not for clinical crises (refer out).

2026-06-261

todoist

mshuffett/dotfiles

Use when creating or processing Todoist tasks, triaging inbox items, doing daily task review, calibrating Todoist triage behavior, or turning corrections into reusable preferences. Routes to operations (CLI actions) vs calibrated triage (policy, context recovery, preference memory, evals). Trigger this whenever the user asks what to do with Todoist items, wants better task triage, or is refining how Todoist decisions should work.

2026-06-231

deep-research-fanout

mshuffett/dotfiles

Run real Deep Research across ChatGPT, Claude, and Gemini in parallel via the user's own logged-in browser (Chrome extension, zero API cost), save each original report to Notion, then synthesize. Use whenever the user wants a "deep dive", "deep research", a thorough multi-source investigation, or to research a topic across the models and compare what each finds. Drives the paid subscription products, NOT the API. NOT for single-fact lookups or ordinary web search — use web-search for those.

2026-06-221

harness-engineering

mshuffett/dotfiles

Use when setting up, auditing, or improving AI agent infrastructure in a repo — AGENTS.md/CLAUDE.md files, linters, architectural constraints, feedback loops, context tiering, agent specialization, or entropy management. Also triggers on "harness engineering", "agent-friendly repo", "make my repo work well with coding agents", "set up my repo for agents", or "why is my agent struggling".

2026-06-221

adaptive-triage

mshuffett/dotfiles

Interactive Todoist triage with preference learning. Use when the user says "triage", "process my inbox", "clean up tasks", "triage my todoist", "file these captures", or mentions inbox zero. Also use when the user has a batch of raw items (voice notes, links, ideas) that need classifying and routing to Todoist projects or Obsidian. Runs an interactive confirm/correct loop that learns your routing preferences over time.

2026-06-161

session-save

mshuffett/dotfiles

Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working directory and session id. Works across Codex and Claude Code by detecting runtime-specific session identifiers and normalizing them into one summary.

2026-06-161

name

openclaw-message

description

Messaging the OpenClaw agent

This sends a chat message to Michael's OpenClaw agent on EC2 and prints the reply.

How it works (and why it's indirect)

If the wrapper proxy ever gets fixed (or the image rebuilt), prefer the public /v1/chat/completions endpoint instead — it's simpler. Until then, use this.

Usage

python3 scripts/send.py "your message here"
python3 scripts/send.py "draft a reply declining politely" --agent openclaw/michael
python3 scripts/send.py "ping" --raw          # full JSON response

Default agent/model is openclaw/default. Other personas: openclaw/michael, openclaw/michael-bot, openclaw/art, openclaw/miranda, openclaw/founders.
The script handles the SSM round-trip and prints just the assistant's text (use --raw for the full response).
Responses can take 20–90s (the agent runs a full turn), so be patient.

Prerequisites / facts

AWS account 636160605813, region us-east-1, instance i-02cef0acfa720d57b (Name puffin-openclaw, container puffin-openclaw-1).
Uses the custom SSM document PuffinRunShell (this account has AWS-managed SSM docs stripped, so a custom run-shell document was created). If SSM calls fail with InvalidDocument, recreate it: aws ssm create-document --name PuffinRunShell --document-type Command --document-format JSON --content '{"schemaVersion":"2.2","description":"run shell","parameters":{"commands":{"type":"StringList"}},"mainSteps":[{"action":"aws:runShellScript","name":"run","inputs":{"runCommand":"{{ commands }}"}}]}'
The agent's default model is openai-codex/gpt-5.4 (codex OAuth) with amazon-bedrock/...opus... as fallback.

Troubleshooting

Empty reply / timeout: the agent turn may be slow or wedged. Check the container: aws ssm send-command --region us-east-1 --instance-ids i-02cef0acfa720d57b --document-name PuffinRunShell --parameters 'commands=["docker logs --tail 30 puffin-openclaw-1"]'.
401: the gateway token rotated mid-call; just retry (the script re-reads it each run).
The WhatsApp channel is logged out (openclaw channels login needed) — unrelated to API messaging.