skills/imessage/SKILL.md
# iMessage Skill ## Description Send and receive iMessages via Claude Code. Get real-time input from the user via their phone, similar to how call-me enables voice conversations. ## When to Use This Skill **Use `ask_user` when:** - You've **completed significant work** and want to report status and ask what's next - You need **real-time input** for decisions - You're **blocked** and need clarification to proceed - You want to **discuss next steps** with the user **Use `notify_user` when:** -
npx skillsauth add njerschow/textme skills/imessageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Send and receive iMessages via Claude Code. Get real-time input from the user via their phone, similar to how call-me enables voice conversations.
Use ask_user when:
Use notify_user when:
Do NOT use for:
ask_userSend an iMessage and wait for the user to respond. This is the main tool - similar to initiate_call in call-me.
Parameters:
message (string, required): What to ask the user. Be conversational.timeout_seconds (number, optional): How long to wait (default: 300 = 5 minutes)Behavior:
check_messagesExample:
ask_user({ message: "Finished the auth module. Should I work on API endpoints or tests next?" })
→ User responds via phone: "API endpoints"
→ Returns: "User responded: API endpoints"
→ Claude continues working on API endpoints
notify_userSend an iMessage without waiting for a response. Fire-and-forget.
Parameters:
message (string, required): Message to sendExample:
notify_user({ message: "Starting the database migration. This will take about 10 minutes." })
→ Returns immediately: "Notification sent"
→ Claude continues working
check_messagesCheck for pending iMessages. Use this to pick up responses that arrived after a timeout.
send_messageSend a message to a specific number. Lower-level than notify_user.
get_conversationGet conversation history with a contact for context.
mark_readMark a message as processed without responding.
list_contactsList all contacts who have messaged.
clear_historyClear conversation history with a contact.
Simple question and continue:
Claude: [finishes auth module]
Claude: ask_user("Hey! Finished the auth module. API endpoints or tests next?")
→ sends iMessage, waits...
User: [responds on phone] "API endpoints please"
Claude: → receives response
Claude: [continues with API endpoints]
Status update (no response needed):
Claude: notify_user("Starting the build process. Will let you know when done.")
Claude: [runs build]
Claude: ask_user("Build complete! 0 errors. Ready to deploy to staging?")
User: "Yes, deploy it"
Claude: [deploys to staging]
Multi-turn conversation:
Claude: ask_user("I found 3 approaches for the caching layer. Want me to explain them?")
User: "Yes please"
Claude: ask_user("Option 1: Redis - fast, needs server. Option 2: In-memory - simple, no persistence. Option 3: SQLite - persistent, slower. Which sounds best?")
User: "Redis"
Claude: [implements Redis caching]
notify_user for updates - Don't block when you don't need inputask_user blocks up to 5 minutes waiting for responsedevelopment
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.