OR Key
drop another .md file to compare - side-by-side diff against imessage

imessage

Sends iMessages for you.
description: "Triggers on prompt mention of 'imessage'."
personal 2 files

What it does for you

Sends iMessages for you.

What it produces

A recent result, so you can see the kind of work it returns.

loading…

How to get it

These run inside the Snappy workspace. Want this working in your business? I set skills like this up with you, in one focused week.

Work with me
For developers how this skill is built, graded, and how it runs

at a glance- the short version

actorExported functions in state/lib/imessage.ts.
auditorNone wired yet - eval is manual (Robert review).
eval modeshape
categoryChannels
stages3
dependssettings

what's inside - the parts that make up a skill 3/4 present

A skill is just a few plain-text files. Only the main one is required. The rest are optional, added as the work needs them. This is what the skill is made of; how it runs is just below.

The skill
state/skills/imessage/SKILL.md present
the skill itself, in plain text
The main file. It says what the skill is and lays out the steps in plain English.
Code
state/lib/imessage.ts present
code the skill can run
Reusable code this skill can call when it needs to.
Scripts
state/bin/imessage/ not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/imessage/AGENTS.md present
what the AI loads on the fly
Loaded automatically the moment this skill is needed. Kept short on purpose.

how it's graded - what counts as a good run 4 criteria · 2 deterministic · 2 judge

Each row is one thing a good run has to get right. deterministic means a quick check decides, pass or fail. judge means the AI reads the result and rates it. Grading each piece on its own (instead of one overall score) shows exactly where a run fell short, so the fix is obvious.

name
kind
check
calls_send_imessage
deterministic
The skill execution log must contain a call to the sendIMessage() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls).
calls_read_recent
deterministic
The skill execution log must contain a call to the readRecent() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls).
output_matches_imessage_api
judge
The output of the skill, particularly from readRecent(), should reflect a structure consistent with the iMessage API as defined in 'state/lib/imessage.ts', exhibiting correct message formats and recipient/sender information.
side_effects_honest
judge
Any iMessage sent via sendIMessage() should be verifiable on the target device, and readRecent() should accurately reflect recent messages without unexpected side effects.

how it runs - the shared frame every skill uses 4/5 present

Every skill runs the same way. One part does the work, a separate part checks it, and a short loader hands the AI exactly what it needs for the job. Anything this skill doesn't use shows a one-line note saying why, on purpose, not by accident.

makes the work The worker
present
Exported functions in state/lib/imessage.ts. the worker
Does the actual work. Whatever it produces is what gets checked next.
checks the work The reviewer
present
None wired yet - eval is manual (Robert review). the checker
A separate checker grades the work, so the part that made it can't approve its own work.
frame
learns Self-correction
not present

This skill doesn't fix its own gaps yet.

tidies up Background fixes
present
queued for rewrite runs in the background
Bigger fixes that can't be made on the spot get queued and rewritten in the background later.
remembers Run history
present
state/log/pending-eval.ndjson pending runs
Every run is written down here, then reviewed by hand each week.
Critical rules the things this skill must not get wrong
  1. iMessage send routes through Mac Mini over SSH - there's no first-party iMessage HTTP API. The Mini is the only sending host.
  2. sendIMessage is irreversible side-effect - keep behind scope-only default per program.md

what it has learned - fixes written back in over time sample

When a run hits something this skill didn't handle, the fix gets written back into the skill so it doesn't happen again. FIXED means it was corrected on the spot. LOGGED means it's queued for a bigger rewrite. Either way, the skill gets a little better and never makes the same mistake twice.

  1. Loading feedback rows…

how the work flows- who makes it, who checks it

inputs settings
actor Exported functions in state/lib/imessage.ts.
1 generator
invoke
actor = Exported functions in state/lib/imessage.ts.
import from `state/lib/imessage.ts`  -  `sendIMessage()`, `readRecent()
auditor None wired yet - eval is manual (Robert review).
2 auditor
inspect
auditor = None wired yet - eval is manual (Robert review).
readRecent()` after a send to confirm the message landed in the local store
3 data
eval log
`state/log/pending-eval.ndjson` (manual eval - skill: "imessage")

SKILL.md- the skill, written out in plain English

imessage

iMessage sending via Mac Mini SSH.

Ported from kernel snappy-imessage in Phase 0.5. See state/lib/imessage.ts for the full API surface.

Steps

  • sendIMessage() - see state/lib/imessage.ts
  • readRecent() - see state/lib/imessage.ts

Eval

Actor: the exported functions in state/lib/imessage.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.

Score convention:

OutcomeScore
Pass on first try1.0
Failed first, auto-fix applied, re-check passed0.5
Still failing or unrecoverable0.0

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

  1. realpathSync(process.argv[1]) CLI guard wrapped in try/catch
  • See the kernel SKILL.md for the original long-form guidance if you need it

(read-only reference at the kernel path above).

Graduation

This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.

Rubric

criteria:
  - name: calls_send_imessage
    kind: deterministic
    check: "The skill execution log must contain a call to the sendIMessage() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls)."
  - name: calls_read_recent
    kind: deterministic
    check: "The skill execution log must contain a call to the readRecent() function. (e.g., check 'state/log/pending-eval.ndjson' for relevant entries indicating function calls)."
  - name: output_matches_imessage_api
    kind: judge
    check: "The output of the skill, particularly from readRecent(), should reflect a structure consistent with the iMessage API as defined in 'state/lib/imessage.ts', exhibiting correct message formats and recipient/sender information."
  - name: side_effects_honest
    kind: judge
    check: "Any iMessage sent via sendIMessage() should be verifiable on the target device, and readRecent() should accurately reflect recent messages without unexpected side effects."

AGENTS.md- what the AI loads when this skill comes up

imessage - loader

Per-turn rules for the imessage skill. Full reference: state/skills/imessage/SKILL.md. Do not skip these.

Critical Rules

  • iMessage send routes through Mac Mini over SSH - there's no first-party iMessage HTTP API. The Mini is the only sending host.
  • sendIMessage is irreversible side-effect - keep behind scope-only default per program.md

Commands

| ui model | live composition via compose_inline, persisted as artifact lang_body, reopened with OpenArtifact | |invoke: import from state/lib/imessage.ts - sendIMessage(), readRecent() |verify: readRecent() after a send to confirm the message landed in the local store |eval log: state/log/pending-eval.ndjson (manual eval - skill: "imessage")

Known Pitfalls

  • SSH path to Mac Mini must be reachable - no fallback. If the Mini is offline, sends silently fail; verify with readRecent.
  • Mac Mini server context: see mac-mini-server skill / mac-mini-remote-ops skill in the wider catalog if SSH config drifts

Self-Test

An agent reading this should correctly:

  1. [ ] Default sendIMessage to scope-only
  2. [ ] Verify sends with readRecent, not just trust the SSH return
  3. [ ] Recognize the Mac Mini SSH dependency

Found a gap? Edit this file. <!-- footer-injection-point -->

api.ts- the code it can call

#!/usr/bin/env npx tsx
/**
 * snappy-imessage/api.ts -- iMessage reading from local SQLite + sending via osascript.
 *
 * Reads: local ~/Library/Messages/chat.db via better-sqlite3
 * Sends: osascript to Messages.app
 *
 * Usage:
 *   npx tsx api.ts send +14155551212 "Hey, checking in!"
 *   npx tsx api.ts list 5
 *   npx tsx api.ts list-contact "+14155551212" 5
 *
 * Or import as module:
 *   import { sendIMessage, readRecent } from "./imessage.ts";
 */

import { execSync } from "child_process";
import { env } from "./env.ts";
import { realpathSync, existsSync } from "fs";
import { homedir } from "os";

export interface IMessageData {
  contact: string;
  text: string;
  timestamp: number;
  guid: string;
}

// Load better-sqlite3 dynamically
let Database: any = null;
async function loadDatabase() {
  if (Database) return Database;
  try {
    Database = (await import("better-sqlite3")).default;
    return Database;
  } catch {
    return null;
  }
}

/**
 * Read recent messages from local Messages SQLite database.
 * Gracefully returns error structure if DB unavailable or access denied.
 */
export async function readRecent(contact?: string, limit = 10): Promise<{ messages: IMessageData[]; not_connected?: boolean; hint?: string }> {
  const DB = await loadDatabase();
  if (!DB) {
    return {
      messages: [],
      not_connected: true,
      hint: "better-sqlite3 not available",
    };
  }

  const dbPath = `${homedir()}/Library/Messages/chat.db`;

  if (!existsSync(dbPath)) {
    return {
      messages: [],
      not_connected: true,
      hint: "Messages database not found at ~/Library/Messages/chat.db. Grant Full Disk Access to Terminal in System Settings → Privacy & Security.",
    };
  }

  try {
    const db = new DB(dbPath, { readonly: true });

    // Query: get last N messages, optionally filtered by contact
    // Apple's Messages schema:
    // - message.ROWID, text, attributedBody, date (nanoseconds since 2001-01-01)
    // - handle.ROWID, id (phone/email)
    // - chat_message_join maps messages to chats
    // - chat.ROWID, guid (group UUID), display_name

    let query = `
      SELECT
        m.ROWID as rowid,
        m.text,
        m.date,
        COALESCE(h.id, '') as contact_id,
        COALESCE(c.display_name, '') as chat_name
      FROM message m
      LEFT JOIN handle h ON m.handle_id = h.ROWID
      LEFT JOIN chat_message_join cmj ON m.ROWID = cmj.message_id
      LEFT JOIN chat c ON cmj.chat_id = c.ROWID
      WHERE 1=1
    `;

    const params: any[] = [];

    if (contact) {
      query += ` AND (h.id LIKE ? OR c.display_name LIKE ?)`;
      const pattern = `%${contact}%`;
      params.push(pattern, pattern);
    }

    query += ` ORDER BY m.date DESC LIMIT ?`;
    params.push(limit);

    const stmt = db.prepare(query);
    const rows = stmt.all(...params);

    db.close();

    // Convert to IMessageData format
    const messages: IMessageData[] = rows
      .map((row: any) => {
        // Use text field only; attributedBody is NSAttributedString binary that's hard to decode
        const text = (row.text || "").trim();

        // Skip empty messages
        if (!text) return null;

        // Convert Apple's absolute timestamp (nanoseconds since 2001-01-01) to unix ms
        // row.date is in nanoseconds relative to 2001-01-01 00:00:00 UTC
        // Seconds since 2001-01-01 to 1970-01-01: 978307200 seconds (31 years + 8 leap days)
        const appleEpochSecs = 978307200;
        const unixMs = (row.date / 1000000000) * 1000 + (appleEpochSecs * 1000); // convert nanos to ms

        // Prefer explicit contact ID over group name; both may be empty for system messages
        const sender = row.contact_id || row.chat_name || "Unknown";

        return {
          contact: sender,
          text: text,
          timestamp: Math.round(unixMs),
          guid: `imessage-${row.rowid}`,
        };
      })
      .filter((m: any) => m !== null);

    return { messages };
  } catch (err: any) {
    const msg = err?.message || String(err);
    if (msg.includes("SQLITE_CANTOPEN") || msg.includes("cannot open")) {
      return {
        messages: [],
        not_connected: true,
        hint: "Full Disk Access required for Terminal. Grant it in System Settings → Privacy & Security → Full Disk Access.",
      };
    }
    return {
      messages: [],
      not_connected: true,
      hint: `iMessage read failed: ${msg}`,
    };
  }
}

/** Send an iMessage via osascript (requires Messages.app open). */
export function sendIMessage(to: string, text: string): void {
  if (!/^\+\d{10,15}$/.test(to)) {
    throw new Error(`Invalid E.164 phone number: ${to}`);
  }
  const escapedText = text.replace(/\\/g, "\\\\").replace(/"/g, '\\"');
  const cmd = `osascript -e 'tell application "Messages" to send "${escapedText}" to buddy "${to}" of (service 1 whose service type is iMessage)'`;
  execSync(cmd, { encoding: "utf-8", timeout: 10_000 });
}

// --- CLI ---

if ((() => { try { return import.meta.url === `file://${realpathSync(process.argv[1])}`; } catch { return false; } })()) {
  (async () => {
    const [, , cmd, ...args] = process.argv;

    switch (cmd) {
      case "send": {
        const [to, ...textParts] = args;
        if (!to || !textParts.length) { console.error("Usage: api.ts send <phone> <text>"); process.exit(1); }
        try {
          sendIMessage(to, textParts.join(" "));
          console.log("sent");
        } catch (e) {
          console.error("send failed:", e);
          process.exit(1);
        }
        break;
      }
      case "list": {
        const limitStr = args[0];
        const limit = limitStr ? parseInt(limitStr, 10) : 5;
        const result = await readRecent(undefined, limit);
        for (const msg of result.messages) {
          console.log(`${new Date(msg.timestamp).toISOString().slice(0, 16)}\t${msg.contact}\t${msg.text.slice(0, 80)}`);
        }
        if (result.not_connected) {
          console.warn(`⚠ ${result.hint}`);
          process.exit(1);
        }
        break;
      }
      case "list-contact": {
        const [contact, limitStr] = args;
        if (!contact) { console.error("Usage: api.ts list-contact <contact> [limit]"); process.exit(1); }
        const limit = limitStr ? parseInt(limitStr, 10) : 5;
        const result = await readRecent(contact, limit);
        for (const msg of result.messages) {
          console.log(`${new Date(msg.timestamp).toISOString().slice(0, 16)}\t${msg.contact}\t${msg.text.slice(0, 80)}`);
        }
        if (result.not_connected) {
          console.warn(`⚠ ${result.hint}`);
          process.exit(1);
        }
        break;
      }
      default:
        console.log("Usage: npx tsx api.ts [send|list|list-contact] ...");
    }
  })();
}

scripts- helper scripts it can run

prose-only skill - 1 inline code block live in SKILL.md above (no state/bin/ sidecar yet).

how we check it- the checks, plus the last 10 runs

rubric shape schema-shape check (no inline rubric)
recent no runs actor/auditor: unverifiable
deps settings

no recent runs logged - the eval contract is declared but nothing has been graded yet